# Resource Library for Forward Deployed Engineering The most useful FDE learning library combines software engineering, customer discovery, data integration, AI evaluation, and operational responsibility. No single course covers those areas deeply enough to replace practical work. The recommended approach is to choose a resource for a specific project constraint, apply it, and retain evidence of what changed. This library contains 63 resources, 11 practice patterns, and 7 reading routes. Access and source checks are dated 14 September 2026. There are 47 resources with free primary content, 11 paid resources, 4 with mixed access, and 1 supplied PDF with citation and chapter notes. Access labels do not include optional model or hosting costs. Selection is editorial; no affiliate links are used. ## Recommendations For someone new to engineering, the immediate goal is to write, test, and debug useful software. Start with CS50 Python, add the Missing Semester's tool practice, and use PostgreSQL and FastAPI to connect a small application to persistent data. Full Stack Open is valuable after programming, web, database, and Git basics; its prerequisites make it a poor first programming course. These recommendations follow the published curricula and prerequisites, not a claim that one course produces better hiring outcomes. [CS50 Python](https://cs50.harvard.edu/python/), [Missing Semester](https://missing.csail.mit.edu/2026/), [Full Stack Open prerequisites](https://fullstackopen.com/en/part0/general_info/). For an experienced engineer moving into FDE work, customer discovery and production AI evaluation may add more value than repeating introductory programming. Use the Government Digital Service interview guidance to practise evidence gathering, then connect a customer's failure examples to an evaluation process. The Mom Test offers a paid, coherent treatment of customer conversations; the public interview guide is a useful free starting point. Neither substitutes for talking to a willing user. [GDS interview guidance](https://www.gov.uk/service-manual/user-research/using-in-depth-interviews), [The Mom Test](https://www.momtestbook.com/), [Hamel and Shreya's evaluation FAQ](https://hamel.dev/blog/posts/evals-faq/). For a first paid technical book, choose according to the actual gap. AI Engineering addresses foundation-model applications; Designing Machine Learning Systems is more relevant when training, serving, and monitoring predictive models are central. Fundamentals of Data Engineering covers lifecycle breadth, while DDIA goes deeper into data-system trade-offs. Reading all four at once is unlikely to help a narrow portfolio project. [AI Engineering](https://www.oreilly.com/library/view/ai-engineering/9781098166298/), [Designing Machine Learning Systems](https://www.oreilly.com/library/view/designing-machine-learning/9781098107956/), [Fundamentals of Data Engineering](https://www.oreilly.com/library/view/fundamentals-of-data/9781098108298/), [DDIA, second edition](https://www.oreilly.com/library/view/designing-data-intensive-applications/9781098119058/). Operational depth does not require an immediate book purchase. Software Engineering at Google, The Site Reliability Workbook, and Architecture Patterns with Python have authorised free online texts. They offer complementary perspectives on maintaining software, operating services, and separating domain logic from changing integrations. Their age is a reason to validate implementation details, not to dismiss the underlying ideas. [Software Engineering at Google](https://abseil.io/resources/swe-book), [SRE Workbook](https://sre.google/workbook/table-of-contents/), [Architecture Patterns with Python](https://www.cosmicpython.com/book/preface.html). Use podcasts and practitioner interviews to develop questions and judgement. A single company's description of its FDE organisation is evidence of that company's perspective, not a universal definition of the job. Pair a conversation about enterprise deployment with a concrete comparison of the work you would own, the customer champion, and the adoption measure. [Cursor FDE interview](https://www.latent.space/p/cursor-forward-deployed-engineers), [Box enterprise-agent conversation](https://www.latent.space/p/box). ## Access and currentness decisions The second edition of DDIA is a February 2026 title co-authored by Martin Kleppmann and Chris Riccomini. The library points to that edition. AI Engineering's linked publisher page labels its digital title December 2024; that exact edition metadata is retained rather than treating a broader 2025 marketing year as an update. [DDIA publisher](https://www.oreilly.com/library/view/designing-data-intensive-applications/9781098119058/), [AI Engineering publisher](https://www.oreilly.com/library/view/ai-engineering/9781098166298/). Some excellent references should be read for concepts while checking current tools elsewhere. The 2023 LLM Bootcamp is a coherent historical course, not a current framework tutorial. The versioned MCP specification identifies the protocol contract, but implementation support still depends on the SDK and peer. OpenAI's evaluation guide remains useful conceptually, while its current notice schedules the Evals platform to become read-only on 31 October 2026 and shut down on 30 November 2026. It is therefore not recommended here as a new platform investment. [LLM Bootcamp](https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/), [MCP 2026-07-28](https://modelcontextprotocol.io/specification/2026-07-28), [OpenAI evaluation guide](https://developers.openai.com/api/docs/guides/evaluation-best-practices). Paid books are classified as paid when only sample chapters or companion code are free. Hands-On Large Language Models includes a free notebook repository, but the book itself is paid. Mixed access is reserved for meaningful free material alongside paid options, with the exact distinction stated in each record. Course trial eligibility, subscriptions, institutional access, and regional checkout terms can change; no fixed purchase prices are asserted. [Hands-On LLMs publisher](https://www.oreilly.com/library/view/hands-on-large-language/9781098150952/), [Author-maintained notebooks](https://github.com/HandsOnLLM/Hands-On-Large-Language-Models). The public syllabus of Vinoo Ganesh's August 2026 LinkedIn Learning course supports recommending it as a compact FDE orientation. It does not establish a complete engineering qualification. A paid evaluation cohort is most useful when the learner has a project and wants feedback, rather than simply wanting a credential. Public syllabi and previews establish advertised content; locked lessons and full paid books were not assumed to have been assessed in their entirety. [FDE orientation course](https://www.linkedin.com/learning/becoming-a-forward-deployed-engineer-bridging-ai-products-and-customer-outcomes), [AI Evals cohort](https://maven.com/parlance-labs/evals). ## Reading routes ### From discovery to an owned AI workflow Pair Benmore’s supplied practitioner book with Agent Factory’s free online chapters. Apply them to one synthetic customer; keep claims and measured evidence separate. - [Forward Deployed: Discovery, AI-Driven Development, and the Forward Deployed Engineer](../index.html#ref-benmore) — provided - [The AI Agent Factory](https://agentfactory.panaversity.org/docs/about) — free - [Spec-Driven Development](https://agentfactory.panaversity.org/docs/spec-driven-development-crash-course) — free - [The FDE AF Model](https://agentfactory.panaversity.org/docs/ecosystem/fde-af-model) — free - [Eval-Driven Development for AI Employees](https://agentfactory.panaversity.org/docs/eval-driven-development-crash-course) — free **Build next:** An evidence-backed specification, bounded worker, evaluation report, and witnessed handoff. ### Build your engineering foundation A free route for someone who needs confidence writing and connecting software. Take the programming course at a realistic pace. - [CS50’s Introduction to Programming with Python](https://cs50.harvard.edu/python/) — free - [The Missing Semester of Your CS Education (2026)](https://missing.csail.mit.edu/2026/) — free - [PostgreSQL tutorial](https://www.postgresql.org/docs/current/tutorial.html) — free - [FastAPI tutorial](https://fastapi.tiangolo.com/tutorial/) — free **Build next:** A tested API over a small dataset, with setup instructions another person can follow. ### Move from software into applied AI Start with the free pattern and evaluation references. Use the paid book for a broader, coherent treatment if that is the gap you want to close. - [Building effective agents](https://www.anthropic.com/engineering/building-effective-agents) — free - [AI Evals: Everything You Need to Know](https://hamel.dev/blog/posts/evals-faq/) — free - [Design and develop a RAG solution](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide) — free - [AI Engineering](https://www.oreilly.com/library/view/ai-engineering/9781098166298/) — paid **Build next:** A bounded AI feature compared with a deterministic baseline, including failure and cost evidence. ### Improve discovery and customer judgement Practise the conversation alongside the reading. The free service manual and interview give an entry point; the book adds structured guidance. - [Using in-depth interviews](https://www.gov.uk/service-manual/user-research/using-in-depth-interviews) — free - [The Mom Test](https://www.momtestbook.com/) — paid - [Technical Writing Courses for Engineers](https://developers.google.com/tech-writing) — free - [How Cursor deploys AI inside the enterprise](https://www.latent.space/p/cursor-forward-deployed-engineers) — free **Build next:** A customer brief, a short decision record, and a weekly update with a specific decision request. ### Make your integration dependable A free reference route to use while building. Read the parts that correspond to an actual failure in your project. - [Making retries safe with idempotent APIs](https://aws.amazon.com/builders-library/making-retries-safe-with-idempotent-APIs/) — free - [Timeouts, retries, and backoff with jitter](https://d1.awsstatic.com/builderslibrary/pdfs/timeouts-retries-and-backoff-with-jitter.pdf) — free - [The Site Reliability Workbook](https://sre.google/workbook/table-of-contents/) — free - [Observability signals](https://opentelemetry.io/docs/concepts/signals/) — free **Build next:** A repeatable write, bounded retries, a useful operational signal, and a recovery drill. ### Deepen data-system design Choose one main paid book: Fundamentals for lifecycle breadth, or DDIA for deeper systems trade-offs. Add the free adapter pattern while implementing. - [Fundamentals of Data Engineering](https://www.oreilly.com/library/view/fundamentals-of-data/9781098108298/) — paid - [Designing Data-Intensive Applications, 2nd Edition](https://www.oreilly.com/library/view/designing-data-intensive-applications/9781098119058/) — paid - [Anti-Corruption Layer pattern](https://learn.microsoft.com/en-us/azure/architecture/patterns/anti-corruption-layer) — free **Build next:** An architecture note explaining data ownership, consistency, failure recovery, and migration constraints. ### Keep a small practitioner reading habit Use one concrete episode or article to generate a question or experiment. Paid newsletter access is optional. - [Agentic Engineering Patterns](https://simonwillison.net/guides/agentic-engineering-patterns/) — free - [SE Radio 706: Observability Tool Migration Techniques](https://se-radio.net/2026/02/se-radio-706-yechezkel-chez-rabinovich-on-observability-tool-migration-techniques/) — free - [The Pragmatic Engineer](https://newsletter.pragmaticengineer.com/about) — mixed - [Every Agent Needs a Box — Aaron Levie, Box](https://www.latent.space/p/box) — free **Build next:** One changed engineering practice each month, with evidence that it helped your work. ## Practices and patterns ### Discover a measurable vertical slice **When:** A customer asks for a broad “AI transformation” without a clear first outcome. **Apply:** Observe an existing workflow, identify one costly handoff, and agree on a narrow acceptance condition with its owner. Record assumptions and exclusions. **Exercise:** Write a one-page brief with the baseline, first user, input, output, and a failure that would invalidate the proposed solution. **Trade-off:** A narrow first delivery reduces uncertainty, but only if it tests a meaningful part of the real workflow. Reading: [Using in-depth interviews](https://www.gov.uk/service-manual/user-research/using-in-depth-interviews); [The Mom Test](https://www.momtestbook.com/). ### Put an adapter at the customer boundary **When:** Each customer names and structures the same domain differently. **Apply:** Translate external schemas into an explicit internal model and keep customer-specific mapping out of the business logic. **Exercise:** Support two synthetic customer APIs using the same workflow code; change a field in one API and show which tests fail. **Trade-off:** Another boundary has a maintenance cost. Introduce it where schema or ownership differences are real. Reading: [Anti-Corruption Layer pattern](https://learn.microsoft.com/en-us/azure/architecture/patterns/anti-corruption-layer); [Architecture Patterns with Python](https://www.cosmicpython.com/book/preface.html). ### Bound retries and make writes safe to repeat **When:** A dependency times out and you cannot tell whether the write happened. **Apply:** Set a deadline and retry budget, randomise retries, and use an explicit idempotency contract for side effects. **Exercise:** Drop a successful response, repeat the request, and verify one resulting record. Then test an outage without unbounded retries. **Trade-off:** Retries increase load. Circuit breakers add recovery state; choose them only when they address an observed failure mode. Reading: [Timeouts, retries, and backoff with jitter](https://d1.awsstatic.com/builderslibrary/pdfs/timeouts-retries-and-backoff-with-jitter.pdf); [Making retries safe with idempotent APIs](https://aws.amazon.com/builders-library/making-retries-safe-with-idempotent-APIs/); [Circuit Breaker pattern](https://learn.microsoft.com/en-us/azure/architecture/patterns/circuit-breaker). ### Use an evaluation gate before increasing autonomy **When:** A promising demo fails unpredictably on real customer tasks. **Apply:** Collect representative tasks, inspect failures with a domain expert, and use calibrated checks to compare changes. Validate the resulting system state. **Exercise:** Compare a rule-based baseline and a model workflow on held-out cases. Record a regression and decide whether the proposed change should ship. **Trade-off:** An automated score can hide a flawed rubric or unrepresentative sample. Keep human review tied to consequential errors. Reading: [AI Evals: Everything You Need to Know](https://hamel.dev/blog/posts/evals-faq/); [Demystifying evals for AI agents](https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents). ### Separate model intent from permission to act **When:** An AI workflow can read sensitive records or call write-capable tools. **Apply:** Restrict tools and resources to the user’s authority, validate arguments, and require an explicit approval step for consequential actions where appropriate. **Exercise:** Insert a malicious instruction into retrieved text, attempt cross-user access, and show the downstream system rejecting the operation. **Trade-off:** Approval only helps when the reviewer understands the actual operation; a generic confirmation can become a rubber stamp. Reading: [Excessive Agency](https://genai.owasp.org/llmrisk/llm062025-excessive-agency/); [Model Context Protocol specification — 2026-07-28](https://modelcontextprotocol.io/specification/2026-07-28). ### Replace a legacy workflow incrementally **When:** A full rewrite would postpone customer value or make cutover too risky. **Apply:** Find a replaceable boundary, deliver a small working path, and expand only after learning from its operation. Plan how coexistence ends. **Exercise:** Move one read path to the new service, preserve a rollback, and record the criteria for retiring the old path. **Trade-off:** Running two paths introduces temporary complexity and possibly duplicated data. Assign ownership for removing it. Reading: [Strangler Fig](https://martinfowler.com/bliki/StranglerFigApplication.html). ### Hand over an operating system, not just a demo **When:** The customer needs the workflow to remain useful after the engineer leaves. **Apply:** Define a user-visible service measure, a response owner, a recovery procedure, and an agreed handoff. **Exercise:** Ask a peer to diagnose a simulated failure with the logs and runbook, then revise the instructions based on where they struggle. **Trade-off:** Monitoring without an owner creates noise. Scale reliability objectives to the consequence and usage of the workflow. Reading: [The Site Reliability Workbook](https://sre.google/workbook/table-of-contents/); [Observability signals](https://opentelemetry.io/docs/concepts/signals/); [Incident Review and Postmortem Best Practices](https://newsletter.pragmaticengineer.com/p/incident-review-best-practices). ### Review agent-written code as owned code **When:** AI accelerates implementation faster than you can understand or validate it. **Apply:** Keep changes inspectable, exercise behaviour with tests, and explain the resulting code and risks before accepting the change. **Exercise:** Let an assistant propose a small integration, then identify an untested assumption and reproduce the failure yourself. **Trade-off:** Fast generation can shift work into review and maintenance; measure the end-to-end effort instead of lines produced. Reading: [Agentic Engineering Patterns](https://simonwillison.net/guides/agentic-engineering-patterns/); [Software Engineering at Google](https://abseil.io/resources/swe-book). ### Validate assumptions before they become specifications **When:** A polished brief contains claims nobody can trace to an operator or system. **Apply:** Record the source and owner of each critical claim. Resolve disagreements before committing to a scope, or make the dependency explicit. **Exercise:** Take three claims from a synthetic brief and define the observation that would falsify each one. **Trade-off:** Discovery should reduce the decisions that matter; an exhaustive document without evidence can create the same debt. Reading: [Forward Deployed: Discovery, AI-Driven Development, and the Forward Deployed Engineer](../index.html#ref-benmore); [Spec-Driven Development](https://agentfactory.panaversity.org/docs/spec-driven-development-crash-course). ### Keep authority separate from retrieval **When:** Search returns a plausible policy without a current owner or approved version. **Apply:** Track versions, approval, access, and review dates. Require complete procedures for governed actions and escalate when authoritative evidence is missing. **Exercise:** Supersede a policy and revoke a test reader. Verify citation freshness and denied access. **Trade-off:** Governance needs maintenance. Semantic relevance cannot establish authority. Reading: [The FDE AF Model](https://agentfactory.panaversity.org/docs/ecosystem/fde-af-model); [Designing the Vertical System of Record](https://agentfactory.panaversity.org/docs/ecosystem/designing-the-vertical-sor). ### Close prototype gaps before transferring ownership **When:** The demo works, but the receiver does not know which integrations or checks are still mocked. **Apply:** Link each release-critical gap to a requirement and proof. Hand over a runbook, system overview, and current specifications, then witness a recovery and change. **Exercise:** Ask another person to fix a seeded bug and roll back without coaching; revise the pack where they get stuck. **Trade-off:** The receiver needs time and access to practise. A document count is not evidence of competence. Reading: [Forward Deployed: Discovery, AI-Driven Development, and the Forward Deployed Engineer](../index.html#ref-benmore); [The Site Reliability Workbook](https://sre.google/workbook/table-of-contents/). ## How to choose and use a resource Begin by writing the decision you need to make or the behaviour you need to implement. Inspect the syllabus, table of contents, or episode chapters for that task. Check whether the assumed language, mathematics, systems background, and time commitment fit. Read a chapter or complete a small exercise before committing to a long course or subscription. Keep three roles distinct: a main learning resource provides structure, reference documentation answers implementation questions, and practitioner writing supplies examples and hypotheses. A newsletter is not an API contract. A vendor architecture guide does not independently establish that its product is the best choice. A popular interview is not evidence of a representative labour market. Apply each resource through a small artifact: a test, a decision record, a schema, a failure drill, a user-interview note, or an operating runbook. Ask another person to use or review it. Record what failed and what you changed. The value of the library is the improvement in the work, not the size of the reading list. ## Selection boundaries The catalogue prioritises original authors, official documentation, university course pages, publisher metadata, and original podcast/interview pages. Recommendations are based on fit to FDE tasks and transparent access conditions. This is a curated starting library rather than an exhaustive ranking, accredited curriculum, or review of every paid lesson. Full paid content was not required for inclusion when a public syllabus, preview, or publisher description supported a bounded recommendation; that evidence limit is visible in the record. Complete-course completion, every notebook execution, cloud cost, and future cohort availability are not asserted. Directly inaccessible course pages with uncertain current enrollment terms were omitted where a fully inspected alternative covered the same need. See the [source-method guide](source-methods.md) for the added Benmore and Agent Factory readings. ## Resource catalogue and references ### Forward Deployed: Discovery, AI-Driven Development, and the Forward Deployed Engineer Richard Buehling. Benmore. book; intermediate; provided. Publication: 2026-02. Checked 2026-09-14. [Source and chapter notes](../index.html#ref-benmore). A consulting practitioner’s method for discovery, specification-led development, deployment, handoff, and support. **Use it for:** Use Chapters 4–8 for engagement judgment and Chapters 10–15 for delivery and ownership. **Access:** User-supplied PDF; no public full-text link verified. This entry opens the source note and chapter guide. The original PDF is not hosted. **Practice:** Build an assumption register, track prototype gaps, and ask a receiver to perform a rollback. **Limit:** Benmore’s February 2026 perspective. Its support pricing and workflow percentages are company examples, not industry benchmarks. **Source scope:** Supplied PDF inspected: title, contents, discovery, specification, development and handoff chapters. Page references in the source guide use printed page numbers. ### The AI Agent Factory Panaversity. Panaversity. book; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://agentfactory.panaversity.org/docs/about). An online curriculum for specifying, building, and supervising AI workers. **Use it for:** Use its orientation to distinguish session assistance from recurring worker operation. **Access:** Public web reading; optional tools, model calls, and hosted infrastructure may cost extra. **Practice:** Compare a one-off task with a recurring version; name the owner, trigger, limits, and review. **Limit:** The 10-80-10 rule is a teaching heuristic. Economic predictions and Digital FTE terminology do not prove labor replacement. **Source scope:** Official page read on 14 September 2026. This records the author’s educational method, not independent validation of its market forecasts or ecosystem performance. ### Spec-Driven Development Panaversity. Panaversity. course; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://agentfactory.panaversity.org/docs/spec-driven-development-crash-course). A course on agreeing intent, defining acceptance, and keeping specifications current. **Use it for:** Translate a broad customer request into checks that can survive a change of implementation. **Access:** Public web reading; optional tools, model calls, and hosted infrastructure may cost extra. **Practice:** Write three acceptance examples before building; revise the spec when a constraint changes. **Limit:** Specifications need evidence and review; writing one does not establish that the customer problem is valid. **Source scope:** Official page read on 14 September 2026. This records the author’s educational method, not independent validation of its market forecasts or ecosystem performance. ### The FDE AF Model Panaversity. Panaversity. article; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://agentfactory.panaversity.org/docs/ecosystem/fde-af-model). A proposed model separating shared machinery, governed knowledge, domain assets, and customer delivery. **Use it for:** Distinguish reusable method from domain evidence and customer-specific integration. **Access:** Public web reading; optional tools, model calls, and hosted infrastructure may cost extra. **Practice:** Give every source a reviewer and version, then identify one adapter worth reusing. **Limit:** A proposed architecture and business model; named infrastructure and ecosystem claims are not independently tested here. **Source scope:** Official page read on 14 September 2026. This records the author’s educational method, not independent validation of its market forecasts or ecosystem performance. ### Designing the Vertical System of Record Panaversity. Panaversity. article; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://agentfactory.panaversity.org/docs/ecosystem/designing-the-vertical-sor). A method for examining inherited work and rebuilding it around outcomes, evidence, and enduring obligations. **Use it for:** Avoid encoding an old workaround as a permanent requirement. **Access:** Public web reading; optional tools, model calls, and hosted infrastructure may cost extra. **Practice:** Explain why one manual step can be changed while its underlying control remains intact. **Limit:** Proposed redesign still needs operator validation; an agent is not assumed to follow every step reliably. **Source scope:** Official page read on 14 September 2026. This records the author’s educational method, not independent validation of its market forecasts or ecosystem performance. ### Eval-Driven Development for AI Employees Panaversity. Panaversity. course; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://agentfactory.panaversity.org/docs/eval-driven-development-crash-course). A multi-track curriculum connecting worker behavior with evaluation and release decisions. **Use it for:** Use it beside a working project and a domain reviewer. **Access:** Public web reading; optional tools, model calls, and hosted infrastructure may cost extra. **Practice:** Record severe failures separately from average success, and use the same held-out cases to compare revisions. **Limit:** A sample exercise is not production assurance. Validate graders and cover the consequences of your particular workflow. **Source scope:** Official page read on 14 September 2026. This records the author’s educational method, not independent validation of its market forecasts or ecosystem performance. ### CS50’s Introduction to Programming with Python Harvard. Harvard. course; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://cs50.harvard.edu/python/). A structured introduction to Python with problem sets and a final project. **Use it for:** Build the coding, debugging, and testing foundation needed before deployment work. **Access:** OpenCourseWare is free. Optional verified credentials are a separate purchase. **Practice:** Turn a CSV of tickets into a validated report and test malformed rows. **Limit:** Focuses on Python rather than a complete computer-science or FDE curriculum. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### The Missing Semester of Your CS Education (2026) Missing Semester teaching team. MIT CSAIL. course; beginner; free. Publication: 2026. Checked 2026-09-14. [Original resource](https://missing.csail.mit.edu/2026/). Learn the shell, development tools, version control, debugging, packaging, and modern coding workflows. **Use it for:** Useful when you must diagnose an unfamiliar customer environment and leave a reproducible setup behind. **Access:** Public lectures and exercises; self-study does not confer MIT credit. **Practice:** Build a one-command setup script, inspect a failed process, and recover a deliberately broken Git change. **Limit:** Start with basic programming familiarity; this develops tool fluency rather than teaching your first programming language. **Source scope:** Read the official course home and 2026 lecture index. The current course is the 2026 offering; older annual archives remain available. ### Using in-depth interviews Government Digital Service. Government Digital Service. docs; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://www.gov.uk/service-manual/user-research/using-in-depth-interviews). Guidance for preparing and conducting interviews about users’ actual experience. **Use it for:** Replace assumptions about a customer workflow with observations and evidence. **Access:** The public service manual is freely accessible. **Practice:** Interview a willing user about their last task, then separate observations from assumptions. **Limit:** Public-service research context; adapt recruitment and consent to the organisation. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### PostgreSQL tutorial PostgreSQL. PostgreSQL. docs; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://www.postgresql.org/docs/current/tutorial.html). An introduction to relational concepts, SQL queries, joins, and transactions. **Use it for:** Inspect customer data, model entities, and avoid incorrect reports from joins. **Access:** Official tutorial and database software are free. Hosted database services may cost money. **Practice:** Model tickets and customers; demonstrate a join that does not double-count. **Limit:** The current URL is versioned by PostgreSQL; match reference details to your installed release. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### Building effective agents Erik S. and Barry Zhang. Anthropic Engineering. article; beginner; free. Publication: 2024-12-19. Checked 2026-09-14. [Original resource](https://www.anthropic.com/engineering/building-effective-agents). A concise pattern language for chaining, routing, parallel work, orchestration and autonomous tool use. **Use it for:** Helps choose the simplest architecture that satisfies a customer's workflow. **Access:** Public article; reproducing API examples can incur usage charges. **Practice:** Draw your workflow, implement a deterministic baseline, and justify each point where model autonomy is necessary. **Limit:** Published December 2024; the page now explicitly warns that its tooling landscape has changed. Treat it as patterns, not a current SDK selection guide. **Source scope:** Read the original article, workflow/agent distinction, pattern descriptions, tool appendix and current freshness note. ### AI Evals: Everything You Need to Know Hamel Husain and Shreya Shankar. Hamel's Blog. article; intermediate; free. Publication: 2025-05-28; updated 2026-09-01. Checked 2026-09-14. [Original resource](https://hamel.dev/blog/posts/evals-faq/). A detailed practical FAQ on product evaluations, error analysis, human labels, evaluators, RAG and production monitoring. **Use it for:** Connects deployment quality to actual customer tasks and shows how domain experts and engineers can improve a system together. **Access:** Full web guide and PDF are free; the linked live course is a separate paid offering. **Practice:** Review a small batch of realistic traces with a domain expert, group failures, then implement one targeted check and test it on both passing and failing examples. **Limit:** The authors label their guidance as contextual opinions; sample sizes and review schedules need to match your risks and data. **Source scope:** Full public FAQ read, including publication date, 1 Sep 2026 modification date, error analysis, judge validation and production sections. ### The Site Reliability Workbook Betsy Beyer, Niall Richard Murphy, David K. Rensin, Kent Kawahara, and Stephen Thorne (editors). Google / O’Reilly. book; intermediate; free. Publication: 2018-07. Checked 2026-09-14. [Original resource](https://sre.google/workbook/table-of-contents/). Worked examples for service objectives, alerting, incidents, pipelines, releases, and customer-facing reliability. **Use it for:** Provides concrete tools for agreeing what reliable means with a customer and transferring operational ownership. **Access:** Complete authorized online text is free; optional paid print or ebook editions. **Practice:** Define a user-facing SLI, propose an SLO, create a rollback drill, and write a sample incident communication. **Limit:** Basic experience running a service helps. This is a 2018 foundation: validate current monitoring syntax and cloud implementation details separately. **Source scope:** Read Google's official book register and workbook contents plus O’Reilly metadata confirming July 2018. Select chapters 2, 5, 9, 13, 16, and 19 for an FDE-oriented route. - [Chapter 19: Reaching Beyond Your Walls](https://sre.google/workbook/reaching-beyond/) ### How Cursor deploys AI inside the enterprise Richard MacManus with Pauline Brunet. Latent Space. article; beginner; free. Publication: 2026-07-01. Checked 2026-09-14. [Original resource](https://www.latent.space/p/cursor-forward-deployed-engineers). Cursor's FDE leader explains configurable deployments, production engineering experience, customer champions and feedback into the product roadmap. **Use it for:** A concrete current example of how customer work, engineering judgment and adoption fit together in an FDE team. **Access:** Public original interview with a linked conference talk. **Practice:** Compare a target FDE job with this example: identify the customer, deployed artifact, internal champion, adoption signal and product feedback path. **Limit:** One company's stated model and hiring preferences; its experience requirement and forecasts do not describe every FDE role. **Source scope:** Original interview read on publisher site; guest role, author and publication date verified. Company claims kept attributed rather than generalized. ### Agents Chip Huyen. Chip Huyen's Blog. article; intermediate; free. Publication: 2025-01-07. Checked 2026-09-14. [Original resource](https://huyenchip.com/2025/01/07/agents.html). A framework for reasoning about agent tools, planning, failure modes and evaluation rather than starting with a particular agent framework. **Use it for:** Useful for explaining architecture choices and failure handling to a customer before adding more autonomy. **Access:** Free standalone article adapted from the paid AI Engineering book. **Practice:** For one agent design, list its tools and write actions, identify planning and tool failures, and specify the checks and fallback for each. **Limit:** Published in early 2025; use the conceptual structure and verify current APIs and model capabilities in maintained documentation. **Source scope:** Original author article read, including date, table of contents, book-adaptation statement and experimental-framework caveat. ### AI Engineering Chip Huyen. O’Reilly. book; intermediate; paid. Publication: 2024-12 (digital edition). Checked 2026-09-14. [Original resource](https://www.oreilly.com/library/view/ai-engineering/9781098166298/). A foundation-model application guide covering evaluation, adaptation, retrieval, agents, data, latency, and cost. **Use it for:** Helps justify model and application choices against customer requirements rather than choosing a stack from a demo. **Access:** Book purchase or O’Reilly subscription access; free previews are not the complete book. **Practice:** Compare a simple baseline and a retrieval-based solution on the same labeled cases, reporting quality, latency, and cost. **Limit:** Comfort with application development helps. Model and framework details age quickly; pair concepts with current provider documentation. Complements Designing Machine Learning Systems. **Source scope:** Read the publisher overview, contents, and metadata. O’Reilly lists December 2024 for this digital title; this is the date recorded here. Paid full text was not accessed. ### Designing Machine Learning Systems Chip Huyen. O’Reilly. book; advanced; paid. Publication: 2022-05. Checked 2026-09-14. [Original resource](https://www.oreilly.com/library/view/designing-machine-learning/9781098107956/). An iterative approach to production ML spanning data, features, objectives, deployment, monitoring, and adaptation. **Use it for:** Useful for FDE roles deploying predictive ML or maintaining customer models and data pipelines beyond foundation-model APIs. **Access:** Book purchase or O’Reilly subscription access. **Practice:** Specify training/serving data checks, a monitoring plan, and a retraining trigger for one predictive use case. **Limit:** Requires basic ML and software knowledge. Choose AI Engineering first for foundation-model applications; choose this when training and operating ML models are central. **Source scope:** Read O’Reilly's official title metadata and overview. The May 2022 scope is complementary to AI Engineering, not a replacement for its foundation-model focus. Description is based on public publisher/author material, not a full-text review. - [Free chapter resources](https://github.com/chiphuyen/dmls-book) ### Effective context engineering for AI agents Prithvi Rajasekaran, Ethan Dixon, Carly Ryan and Jeremy Hadfield. Anthropic Engineering. article; intermediate; free. Publication: 2025-09-29. Checked 2026-09-14. [Original resource](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents). Techniques for selecting, retrieving and maintaining useful context across extended agent tasks. **Use it for:** Helps control irrelevant context, token costs and failures in long customer workflows. **Access:** Public article. **Practice:** Compare full-history, compacted-history and retrieved-context variants on the same tasks; record quality and token use. **Limit:** Provider experience and design guidance, not proof that one context strategy wins universally or that indexed retrieval is obsolete. **Source scope:** Read the original article, retrieval tradeoffs, long-horizon techniques and author acknowledgements. ### Hands-On Large Language Models Jay Alammar and Maarten Grootendorst. O’Reilly. book; beginner; paid. Publication: 2024-09. Checked 2026-09-14. [Original resource](https://www.oreilly.com/library/view/hands-on-large-language/9781098150952/). An illustrated introduction to LLM internals, embeddings, semantic search, retrieval and fine-tuning. **Use it for:** Builds the intuition needed to diagnose retrieval and model behavior rather than treating an API as a black box. **Access:** The book is paid; the authors' official example notebooks are free on GitHub. Compute/API use may cost extra. **Practice:** Run the semantic-search notebook on a small document set, inspect retrieval misses, and compare a reranker. **Limit:** Published September 2024; beginner-to-intermediate content still expects code practice, and notebook dependencies or free GPU availability can change. **Source scope:** Read the publisher metadata and the official https://github.com/HandsOnLLM/Hands-On-Large-Language-Models README/contents. Did not access paid full text or execute notebooks. - [Free companion notebooks](https://github.com/HandsOnLLM/Hands-On-Large-Language-Models) ### Hugging Face Agents Course Hugging Face education team. Hugging Face. course; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://huggingface.co/learn/agents-course/unit0/introduction). Hands-on agent fundamentals, frameworks, agentic retrieval and an evaluated final project. **Use it for:** Provides a structured first build before you connect an agent to a customer's systems. **Access:** Course and certification are free; hosted model use beyond included allowances may cost extra. **Practice:** Build one tool-using agent, record its traces, then add a timeout and a test for a failed tool call. **Limit:** Requires basic Python and basic LLM knowledge; use current framework docs when examples differ. **Source scope:** Read the official introduction, syllabus, prerequisites and certification terms. It describes a living course and requires a free Hugging Face account for Hub/Spaces activities. ### LLM Bootcamp The Full Stack instructors. The Full Stack. course; intermediate; free. Publication: 2023. Checked 2026-09-14. [Original resource](https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/). A product-oriented course covering LLM application architecture, deployment, evaluation and user experience. **Use it for:** Connects model work with the application lifecycle an FDE actually owns. **Access:** Recorded lectures are free; recreating hosted demos can incur provider charges. **Practice:** Use the LLMOps and UX lectures to write a launch plan with failure states, instrumentation and customer acceptance checks. **Limit:** Spring 2023 material: use its lifecycle and UX lessons, then check current APIs, models and framework docs. **Source scope:** Read the official syllabus, lecture descriptions and explicit free-access statement; did not watch every lecture or run the historical demo. ### Model Context Protocol specification — 2026-07-28 Model Context Protocol maintainers. Model Context Protocol. docs; advanced; free. Publication: 2026-07-28. Checked 2026-09-14. [Original resource](https://modelcontextprotocol.io/specification/2026-07-28). The authoritative contract for connecting AI applications with external context and tools. **Use it for:** Useful when designing interoperable customer integrations and understanding capability and trust boundaries. **Access:** Open specification and public documentation; connected services may have their own charges. **Practice:** Expose one read-only customer-style tool, document its authorization boundary, and test unsupported protocol versions and errors. **Limit:** Implementation requires API/JSON-RPC familiarity. Pin the protocol and SDK versions; older clients and optional extensions have different support. **Source scope:** Read the versioned specification overview, base protocol, features, extensions and security principles; checked official July release information. This entry does not claim every SDK implements every extension. ### Why AI evals are the hottest new skill for product builders Lenny Rachitsky with Hamel Husain and Shreya Shankar. Lenny's Podcast. podcast; beginner; mixed. Publication: 2025-09-25. Checked 2026-09-14. [Original resource](https://www.lennysnewsletter.com/p/why-ai-evals-are-the-hottest-new-skill). A worked conversation about analyzing real traces, grouping errors, choosing evaluators and validating a judge against human decisions. **Use it for:** Provides an accessible shared starting point for an FDE and a customer domain expert who must agree what acceptable quality means. **Access:** Episode links to public YouTube, Spotify and Apple Podcasts; the newsletter page marks its transcript/access as paid. **Practice:** Watch the trace-review walkthrough, then have an engineer and domain expert independently annotate the same ten outputs and discuss disagreements. **Limit:** The title's ranking language is promotional; this selection is based on the concrete walkthrough, not claims about course popularity. **Source scope:** Original episode page, public description and timestamped chapters read; official outbound YouTube link verified. Paid transcript was not accessed. ### Becoming a Forward Deployed Engineer: Bridging AI Products and Customer Outcomes Vinoo Ganesh. LinkedIn Learning. course; intermediate; paid. Publication: 2026-08-10. Checked 2026-09-14. [Original resource](https://www.linkedin.com/learning/becoming-a-forward-deployed-engineer-bridging-ai-products-and-customer-outcomes). A 51-minute course on FDE responsibilities, discovery, communication, deployment feedback and getting started in the role. **Use it for:** Offers a compact FDE-specific orientation before tackling a substantial technical portfolio project. **Access:** Subscription access with a public preview; trial eligibility and employer or library access vary. **Practice:** Turn the published syllabus into an engagement brief covering the customer outcome, communication plan, first deployment and feedback route to product engineering. **Limit:** An orientation course, not a complete engineering qualification or hiring guarantee; locked lessons were not reviewed. **Source scope:** Official course landing page and full public syllabus read; instructor, intermediate level, 51-minute duration, release date and locked lessons verified. ### Candidate AI guidance Anthropic. Anthropic. docs; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://www.anthropic.com/candidate-ai-guidance). Anthropic’s policy on AI assistance during applications and assessments. **Use it for:** Distinguish learning with AI from the rules that apply during an interview. **Access:** The candidate guidance is public. **Practice:** Before a mock assessment, state the permitted tools and work within that constraint. **Limit:** Employer-specific policy; the actual invitation may contain additional instructions. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### OpenAI interview guide OpenAI. OpenAI. docs; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://openai.com/interview-guide/). General guidance on OpenAI’s recruiting assessments and interview process. **Use it for:** Prepare examples and confirm the tool rules for the actual assessment. **Access:** The employer’s public interview guide is free. **Practice:** Practise explaining a debugging decision without relying on a fixed question bank. **Limit:** A general employer guide, not a guaranteed FDE interview loop. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### Staff Engineer: Leadership beyond the management track Will Larson. Will Larson / StaffEng. book; advanced; mixed. Publication: 2021. Checked 2026-09-14. [Original resource](https://staffeng.com/book/). Guides and practitioner interviews about technical leadership, choosing useful work and influencing an organization as an individual contributor. **Use it for:** Senior FDEs frequently lead across customer and product teams without controlling either team's priorities. **Access:** Most guides and interviews are free on StaffEng; the assembled book, foreword and ending are paid. **Practice:** Read Work on what matters, then write a one-page proposal identifying the outcome, decision owner, affected teams and work you will deliberately defer. **Limit:** Staff engineering and FDE are different roles; the author also notes a US and Silicon Valley bias in the examples. **Source scope:** Official book page read, including free-content FAQ, guide links, interview basis and contextual limitation; prices intentionally omitted. ### The AI-native interview Sierra. Sierra. article; intermediate; free. Publication: 2026-04-22. Checked 2026-09-14. [Original resource](https://sierra.ai/blog/the-ai-native-interview). Sierra’s description of its AI-native engineering interview design. **Use it for:** Practise scoping, implementing, and reviewing a solution with explicit tool rules. **Access:** The engineering article is freely accessible. **Practice:** Run a mock plan/build/review exercise and explain one deliberate scope cut. **Limit:** Describes Sierra’s engineering process; other employers may prohibit the same tools. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### The Pragmatic Engineer Gergely Orosz. The Pragmatic Engineer. blog; intermediate; mixed. Publication: living / undated. Checked 2026-09-14. [Original resource](https://newsletter.pragmaticengineer.com/about). An engineering publication combining company interviews, real-world delivery problems, organizational practices and career context. **Use it for:** Helps FDEs understand how engineering teams operate and compare customer practices with documented examples. **Access:** Free article previews and podcast issues; subscription for full deep dives, The Pulse and subscriber resources. **Practice:** Choose one relevant deep dive, extract a practice and its context, and write a small experiment to test whether it improves your current engagement. **Limit:** Use specific articles to solve a problem; the publication is not an FDE curriculum and industry commentary is not a universal benchmark. **Source scope:** Current official about page read: author, editorial scope, free versus paid access, schedule and subscription conditions verified. ### Anti-Corruption Layer pattern Microsoft Azure Architecture Center. Microsoft Learn. article; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://learn.microsoft.com/en-us/azure/architecture/patterns/anti-corruption-layer). Places a translation boundary between systems with different domain models. **Use it for:** Keep a customer-specific schema from spreading through the reusable application. **Access:** Public engineering reference; implementation infrastructure may incur costs. **Practice:** Map two customer APIs into one internal model and test what happens when a field changes. **Limit:** The adapter introduces operational and maintenance overhead; preserve errors and ownership across the boundary. **Source scope:** Primary engineering article read; canonical AWS PDF used where the newer landing page did not expose the article text. ### CMU 15-445/645: Intro to Database Systems (Spring 2026) Andy Pavlo and Jignesh Patel. Carnegie Mellon University. course; advanced; free. Publication: 2026. Checked 2026-09-14. [Original resource](https://15445.courses.cs.cmu.edu/spring2026/schedule.html). An implementation-focused study of SQL, indexes, query execution, concurrency, recovery, and distributed databases. **Use it for:** Deepens diagnosis of slow queries, transaction anomalies, and storage behavior in data-heavy customer deployments. **Access:** Public archived notes, slides, assignments, and video links; university enrollment and credit are separate. **Practice:** Study the query-optimization and concurrency units, then explain a slow query and a transaction anomaly in your own small database example. **Limit:** Advanced systems and C++17 skills are prerequisites for BusTub projects. Keep course solutions private; external learners do not receive the full grading infrastructure. **Source scope:** Read Spring 2026 home, complete schedule (updated April 27), and syllabus. Chosen over the in-progress Fall 2026 offering; video destinations are linked but playback was not verified. ### Data Engineering Zoomcamp Alexey Grigorev and DataTalks.Club instructors. DataTalks.Club. course; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://github.com/DataTalksClub/data-engineering-zoomcamp). A project-based data-pipeline course covering containers, infrastructure, orchestration, warehouses, modeling, batch, and streaming. **Use it for:** Builds hands-on integration skills that transfer to ingesting and validating customer data under real operational constraints. **Access:** Free videos, materials, and homework; cloud services used in exercises can create separate costs. **Practice:** Deliver an original pipeline with incremental loading, data-quality checks, recovery instructions, and a clear cost boundary. **Limit:** Basic coding and SQL are required. Self-paced study is available now without a certificate; cohort certificates require the provider's project and peer-review process. **Source scope:** Read the maintainers' current repository README, prerequisites, access table, and syllabus. It advertises January 2027 as the next cohort; live cohort means coordinated deadlines, not live lectures. ### Design and develop a RAG solution Microsoft Azure Architecture Center contributors. Microsoft Learn. docs; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide). A design-and-evaluation framework for RAG ingestion, chunking, enrichment, embeddings and retrieval. **Use it for:** Helps turn a customer document demo into a traceable series of engineering decisions. **Access:** Public architecture guidance; Azure resources used to implement it are separately billed. **Practice:** Keep an experiment log that changes one retrieval variable at a time and records both component and end-user results. **Limit:** Azure examples are vendor-specific; transfer the evaluation method without assuming every named service is required. **Source scope:** Read the primary architecture introduction, design phases, evaluation recommendations and update date of 30 Jun 2026. Did not read every linked phase article. ### Designing Data-Intensive Applications, 2nd Edition Martin Kleppmann and Chris Riccomini. O’Reilly. book; advanced; paid. Publication: 2026-02. Checked 2026-09-14. [Original resource](https://www.oreilly.com/library/view/designing-data-intensive-applications/9781098119058/). Develop judgment about storage, data models, transactions, replication, distributed failures, batch, and streaming trade-offs. **Use it for:** Use it when a customer's consistency, tenancy, recovery, or scale requirements make a simple architecture choice consequential. **Access:** Published book and subscription access; the second edition is released, not an early-access recommendation. **Practice:** Write a design decision for your project comparing one database with a distributed alternative, including partial-failure behavior. **Limit:** Best after building a backend with a database. Read relevant chapters alongside a project instead of treating all 672 pages as an entry requirement. **Source scope:** Read the publisher's second-edition page and contents: February 2026, Kleppmann and Riccomini. The older dataintensive.net marketing page still describes the earlier author/version. Description is based on public publisher/author material, not a full-text review. ### Fundamentals of Data Engineering Joe Reis and Matt Housley. O’Reilly. book; beginner; paid. Publication: 2022-06. Checked 2026-09-14. [Original resource](https://www.oreilly.com/library/view/fundamentals-of-data/9781098108298/). An end-to-end framework for ingestion, storage, transformation, orchestration, governance, and serving data. **Use it for:** Helps translate a customer's messy data estate into a coherent delivery plan before selecting products. **Access:** Buy the book or use O’Reilly access through a personal, employer, or library subscription where available. **Practice:** Map one customer's data lifecycle, identify its source of truth, and write a failure-and-ownership table for every handoff. **Limit:** Basic programming and database concepts help. The 2022 concepts remain useful, but verify contemporary tool behavior in current documentation. **Source scope:** Read the publisher overview and title page, which list June 2022 and the two authors. No claim that this is a newly updated edition. Description is based on public publisher/author material, not a full-text review. ### Making retries safe with idempotent APIs Malcolm Featonby. Amazon Builders’ Library. article; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://aws.amazon.com/builders-library/making-retries-safe-with-idempotent-APIs/). Explores request identity, duplicate calls, and the semantics of retry-safe APIs. **Use it for:** Avoid duplicate invoices, tickets, or provisioning when a response is lost. **Access:** Public engineering reference; implementation infrastructure may incur costs. **Practice:** Repeat one write with the same request ID, then reuse that ID with different input and verify rejection. **Limit:** Idempotency needs a defined lifetime, scope, and consistency contract; it is not the same as assuming exactly-once delivery. **Source scope:** Primary engineering article read; canonical AWS PDF used where the newer landing page did not expose the article text. ### Strangler Fig Martin Fowler. Martin Fowler. article; intermediate; free. Publication: 2024-08-22 (updated article). Checked 2026-09-14. [Original resource](https://martinfowler.com/bliki/StranglerFigApplication.html). Describes incremental replacement of a legacy system through a growing replacement. **Use it for:** Deliver a narrow useful slice without requiring a full customer-system rewrite. **Access:** Public engineering reference; implementation infrastructure may incur costs. **Practice:** Move one read workflow behind a routing boundary and document a reversible cutover. **Limit:** Temporary coexistence creates complexity; establish how the old path will eventually be retired. **Source scope:** Primary engineering article read; canonical AWS PDF used where the newer landing page did not expose the article text. ### Continuous Discovery Habits Teresa Torres. Product Talk. book; intermediate; paid. Publication: 2021-05-19. Checked 2026-09-14. [Original resource](https://www.producttalk.org/continuous-discovery-habits/). A structured approach to outcomes, customer interviews, opportunity mapping and testing assumptions before committing to solutions. **Use it for:** Provides a repeatable way to connect customer needs, engineering choices and measurable value throughout an engagement. **Access:** Paid book; the author's public articles offer a free introduction to the methods. **Practice:** Draw one opportunity solution tree for your deployment: one outcome, three observed customer needs, two candidate solutions and the riskiest assumption to test. **Limit:** Written for ongoing product teams; adapt its cadence and ownership model for short customer engagements. **Source scope:** Author's dated book launch page and current Product Talk course/book navigation read; book scope and purchase access verified. Paid book text was not reviewed. ### Every Agent Needs a Box — Aaron Levie, Box swyx and Jeff Huber with Aaron Levie. Latent Space. podcast; intermediate; free. Publication: 2026-03-05. Checked 2026-09-14. [Original resource](https://www.latent.space/p/box). An enterprise software conversation about agent identity, permissions, context, evaluation and workflows that read and write company information. **Use it for:** Helps frame customer discovery around the systems and operational boundaries that determine whether an agent can be deployed. **Access:** Public episode, video and transcript on the publisher's site. **Practice:** After the governance and identity segment, draw separate access boundaries for the employee, agent and administrator in your proposed workflow. **Limit:** A vendor executive's viewpoint, with product promotion and forecasts; it is not an implementation guide or independent security assessment. **Source scope:** Official episode page, chapter list and transcript sections on identity, permissions and enterprise data read; publication date and public access verified. ### Everyone Can Do Continuous Discovery—Even You! Here's How Teresa Torres. Product Talk. article; beginner; free. Publication: 2023-08-02. Checked 2026-09-14. [Original resource](https://www.producttalk.org/getting-started-with-discovery/). How to begin customer discovery in organizations that lack an established discovery cadence or resist changing their process. **Use it for:** An FDE needs a practical first step even when access to users or influence over the customer's roadmap is limited. **Access:** Free article and conference talk; the related book and training are optional paid products. **Practice:** Choose one discovery habit you can introduce this week; specify who participates, the question it should answer and the smallest useful evidence to collect. **Limit:** Organizational examples are contextual and predate current AI tooling; the customer-learning methods remain distinct from technical implementation advice. **Source scope:** Original author article and edited conference transcript read; publication date, topic and free video/text access verified. ### Technical Writing Courses for Engineers Google technical-writing educators. Google for Developers. course; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://developers.google.com/tech-writing). Practice planning clear technical documents, editing prose, improving accessibility, and writing helpful errors. **Use it for:** Useful for customer setup instructions, operational runbooks, design decisions, and unambiguous handoffs. **Access:** Free self-study lessons and facilitator materials; occasional public facilitated sessions have separate availability. **Practice:** Rewrite a setup guide for a named audience, then ask someone unfamiliar with the project to use it and report friction. **Limit:** Some English-writing proficiency and basic coding familiarity help. These courses focus on technical documentation rather than general business English. **Source scope:** Read Google's course home, audience requirements, and delivery-format guidance. Self-study lessons remain valuable without a facilitated session; no scheduled class or certification is promised. ### The Mom Test Rob Fitzpatrick. Rob Fitzpatrick. book; beginner; paid. Publication: living / undated. Checked 2026-09-14. [Original resource](https://www.momtestbook.com/). A compact guide to customer conversations that produce useful evidence instead of flattering, biased feedback. **Use it for:** FDEs need to uncover an expensive workflow problem before agreeing to a requested feature or agent demo. **Access:** Paid print, ebook, PDF and audiobook editions; the official page explains the approach before purchase. **Practice:** Rewrite five leading discovery questions, then interview a user about the last time they performed the workflow; record evidence separately from assumptions. **Limit:** Customer interviewing is one part of enterprise discovery; add security, procurement, stakeholder and deployment constraints. **Source scope:** Official author/book page read: scope, author, formats and purchase links verified; no publication date displayed and no price quoted. Practice is an editorial exercise. Description is based on public publisher/author material, not a full-text review. ### The Workshop Survival Guide Rob Fitzpatrick and Devin Hunt. Rob Fitzpatrick and Devin Hunt. book; intermediate; paid. Publication: living / undated. Checked 2026-09-14. [Original resource](https://www.workshopsurvival.com/). Practical workshop design and facilitation guidance covering exercises, teaching formats, difficult questions and time management. **Use it for:** Useful when an FDE must run customer onboarding, train operators or bring several stakeholders into a working session. **Access:** Paid book; a detailed table of contents is public on the official site. **Practice:** Design a 45-minute customer enablement session with one observable learning outcome, a hands-on task, a recovery plan and a short feedback check. **Limit:** Focuses on educational workshops, so adapt the format for discovery meetings rather than treating every meeting as a class. **Source scope:** Official book page, authors section, complete table of contents and purchase link read; publication date not displayed. Full book not reviewed. ### Agentic Engineering Patterns Simon Willison. Simon Willison's Weblog. blog; intermediate; free. Publication: 2026-02-23. Checked 2026-09-14. [Original resource](https://simonwillison.net/guides/agentic-engineering-patterns/). A living collection of coding-agent practices covering testing, Git, code review, subagents and understanding generated code. **Use it for:** FDEs can prototype integrations quickly while retaining responsibility for the code they deliver and hand over. **Access:** Free, evolving online guide; using the coding tools discussed can incur separate costs. **Practice:** Use an agent on a small integration change, establish a test baseline, inspect the diff, and produce a walkthrough another engineer can use to maintain it. **Limit:** A practitioner guide in progress, not a formal standard; tool behavior and individual chapters can change. **Source scope:** Official guide index, introductory chapter and dated launch post read; current index includes testing, review and code-understanding patterns. ### Architecture Patterns with Python Harry Percival and Bob Gregory. O’Reilly / Cosmic Python. book; intermediate; free. Publication: 2020-03. Checked 2026-09-14. [Original resource](https://www.cosmicpython.com/book/preface.html). Concrete Python examples of domain models, adapters, repositories, transactions, service layers, and events. **Use it for:** Helps separate changing customer integrations from stable business logic and make those boundaries testable. **Access:** Complete authorized online book is free; paid print, ebook, and O’Reilly options also exist. **Practice:** Wrap an external API in an adapter, test business behavior with a fake, then integration-test the real boundary. **Limit:** Requires Python and basic testing familiarity. The 2020 examples may need dependency updates; introduce only the architectural layers your project needs. **Source scope:** Read the authors' Cosmic Python home and preface plus O’Reilly metadata. Authors explicitly offer free authorized reading; publisher confirms March 2020. ### FastAPI tutorial FastAPI. FastAPI. docs; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://fastapi.tiangolo.com/tutorial/). An incremental Python API tutorial with validation, security, and testing references. **Use it for:** Connect a workflow to an explicit request/response contract and identity boundary. **Access:** Documentation is free; hosting the resulting service can incur costs. **Practice:** Add an endpoint and tests that deny a user access to another user’s record. **Limit:** Requires Python fluency; tutorial authentication examples still need deployment-specific review. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### Full Stack Open Matti Luukkainen and contributing instructors. University of Helsinki. course; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://fullstackopen.com/en/). Build web applications through connected exercises covering React, Node, APIs, testing, TypeScript, delivery, and databases. **Use it for:** Develops the breadth needed to ship a usable customer workflow across frontend, backend, and deployment boundaries. **Access:** Free materials and certificate; university credit follows the provider's registration and completion requirements. **Practice:** Complete the core application, then add one original customer workflow with permissions, tests, and a handoff document. **Limit:** Requires fluent programming plus basic web, database, and Git knowledge; it is not an introduction to programming. **Source scope:** Read the official home and https://fullstackopen.com/en/part0/general_info/. The course now updates continuously rather than using yearly editions; prerequisites and free access are explicit. ### Learn web development MDN. MDN. docs; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://developer.mozilla.org/en-US/docs/Learn_web_development). Guided web fundamentals covering the browser, HTML, CSS, and JavaScript. **Use it for:** Build a usable interface for a workflow rather than stopping at a script. **Access:** Learning articles are freely accessible. **Practice:** Implement loading, empty, success, and error states for an API-backed screen. **Limit:** A web-development pathway; backend operations and customer discovery need other resources. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### Machine Learning Crash Course Google. Google for Developers. course; beginner; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://developers.google.com/machine-learning/crash-course). A practical grounding in models, data, classification metrics, embeddings and production ML. **Use it for:** Helps explain false positives, data leakage and model limitations to a customer. **Access:** Public lessons and browser exercises; a Google account may be needed for Colab. **Practice:** Train a small classifier, vary its threshold, and explain the business cost of each error type. **Limit:** No prior ML is required, but programming, algebra and basic statistics are expected; Python, NumPy and pandas prework is provided. **Source scope:** Read Google's course modules and prerequisites page; prerequisite page updated 25 Aug 2025. The course is a concept foundation, not deep API training. ### Pro Git Scott Chacon & Ben Straub. Scott Chacon & Ben Straub. book; beginner; free. Publication: 2014 (2nd edition). Checked 2026-09-14. [Original resource](https://git-scm.com/book/en/v2). A practical reference for version control, branching, and collaboration. **Use it for:** Make your customer work reviewable and recoverable in a shared repository. **Access:** The full authorised web edition is free; print editions are sold separately. **Practice:** Create a branch, resolve a merge conflict, and safely revert a faulty change. **Limit:** Use chapters selectively; advanced internals are not a prerequisite for a first project. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### Software Engineering at Google Titus Winters, Tom Manshreck, and Hyrum Wright. O’Reilly / Google Abseil. book; intermediate; free. Publication: 2020-03. Checked 2026-09-14. [Original resource](https://abseil.io/resources/swe-book). A practical account of maintaining software through testing, documentation, code review, collaboration, and change. **Use it for:** Helps turn a customer-specific prototype into code another engineer can review, operate, and extend. **Access:** Complete authorized HTML edition is free; optional print purchase. **Practice:** Add a concise design document, review checklist, and handoff guide to a project; ask a peer to follow the guide unaided. **Limit:** Read after some coding experience. Adapt Google's scale-specific practices to the team; the book explicitly omits detailed API design and security hardening. **Source scope:** Read Google's Abseil landing page and book preface. Google confirms March 2020 publication and authorized free HTML availability. ### The Design of Web APIs, Second Edition Arnaud Lauret. Manning. book; intermediate; paid. Publication: 2025-06. Checked 2026-09-14. [Original resource](https://www.manning.com/books/the-design-of-web-apis-second-edition). Consumer-centered API design, from requirements and capabilities through HTTP contracts, documentation, security, and compatible change. **Use it for:** Useful for turning an integration request into an API contract that customers and product engineers can both maintain. **Access:** Paid ebook, print, or Manning subscription; excerpts and example source are available separately. **Practice:** Design and review an OpenAPI contract for a long-running customer import, including permissions, errors, and version evolution. **Limit:** The provider expects experience building or consuming APIs. The 2025 edition is current book guidance; verify later OpenAPI specifications and tooling separately. **Source scope:** Read Manning's second-edition page, June 2025 metadata, reader prerequisites, chapter description, and linked code/exercise resources. Chosen over an older API-pattern catalog for its requirements-to-contract coverage. Description is based on public publisher/author material, not a full-text review. ### AI Evals For Engineers & PMs Hamel Husain and Shreya Shankar. Maven / Parlance Labs. course; intermediate; paid. Publication: living / undated. Checked 2026-09-14. [Original resource](https://maven.com/parlance-labs/evals). A coached course on evaluation workflows, annotation tools, targeted tests and stakeholder alignment. **Use it for:** Most useful when you have a live AI project and want feedback on its evaluation process. **Access:** Paid live cohort. Read the free companion FAQ first; check the current cohort, schedule and fee before purchasing. **Practice:** Bring a scoped project and anonymized examples; finish with a rubric, validated checks and a review workflow. **Limit:** Familiarity with AI applications and LLMs is helpful; a substantial cohort purchase is optional, not a prerequisite for becoming an FDE. **Source scope:** Read the official public course syllabus and FAQ, which describe office hours, exercises, projects and lifetime material access. Full teaching content not accessed; no outcome guarantee or fixed fee asserted. ### Circuit Breaker pattern Microsoft Azure Architecture Center. Microsoft Learn. article; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://learn.microsoft.com/en-us/azure/architecture/patterns/circuit-breaker). A pattern for temporarily stopping calls to a failing dependency. **Use it for:** Bound cascading failure and allow an overloaded integration time to recover. **Access:** Public engineering reference; implementation infrastructure may incur costs. **Practice:** Simulate an outage, open the circuit after a threshold, and exercise a recovery probe. **Limit:** Adds state and tuning; it may be unnecessary for a simple workflow with existing queue-based recovery. **Source scope:** Primary engineering article read; canonical AWS PDF used where the newer landing page did not expose the article text. ### Demystifying evals for AI agents Anthropic Engineering. Anthropic. article; intermediate; free. Publication: 2026-01-09. Checked 2026-09-14. [Original resource](https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents). A practical guide to agent tasks, trials, graders, traces and observable outcomes. **Use it for:** Provides language for agreeing with a customer on what successful deployment actually means. **Access:** Public article; running model-based graders has usage costs. **Practice:** Create outcome checks for a tool-using agent, run repeated trials, and inspect both the trace and final system state. **Limit:** Examples come from particular agent types; adapt criteria to your domain and calibrate model graders with people. **Source scope:** Read the primary engineering article, evaluation terminology, grader discussion and development/monitoring recommendations. ### Evaluation best practices OpenAI. OpenAI API documentation. docs; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://developers.openai.com/api/docs/guides/evaluation-best-practices). Task-specific evaluation design, dataset construction, grader choices and failure cases for AI applications. **Use it for:** A second provider perspective for reviewing your acceptance tests and human calibration process. **Access:** Public conceptual guidance. Model calls and hosted services have separate usage fees. **Practice:** Map each uncertain step in your application to a failure case, an evaluation method and a human owner. **Limit:** The page announces Evals-platform read-only access on 31 Oct 2026 and shutdown on 30 Nov 2026. Use the concepts; do not start a new dependency on that retiring platform. **Source scope:** Read the current public guide body, including its explicit Evals deprecation notice, design process, architecture examples and grader caveats. Not a recommendation to adopt the retiring API. ### Excessive Agency OWASP GenAI Security Project. OWASP. docs; intermediate; free. Publication: 2025 risk edition. Checked 2026-09-14. [Original resource](https://genai.owasp.org/llmrisk/llm062025-excessive-agency/). A threat-model reference for excessive functionality, permissions, and autonomy in AI systems. **Use it for:** Design customer tool access so a model cannot exceed the intended operation or user authority. **Access:** Public security guidance; no certification or paid product is required to read it. **Practice:** Remove unnecessary tools, deny a cross-user operation, and require approval before a consequential write. **Limit:** A risk framework, not a complete security audit; enforce restrictions in the application and downstream systems. **Source scope:** Official OWASP risk description and mitigations read; practice is an editorial exercise. ### Get started with Docker Docker. Docker. docs; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://docs.docker.com/get-started/). An introduction to containers and reproducible application environments. **Use it for:** Help another engineer run the integration without relying on your laptop. **Access:** Documentation is free. Check Docker product licensing and hosting costs for your context. **Practice:** Package a service, document configuration, and run it from a fresh checkout. **Limit:** Containers are one deployment tool, not a substitute for permissions, monitoring, or rollback. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### Incident Review and Postmortem Best Practices Gergely Orosz. The Pragmatic Engineer. article; intermediate; mixed. Publication: 2021-10-19. Checked 2026-09-14. [Original resource](https://newsletter.pragmaticengineer.com/p/incident-review-best-practices). An original survey and discussion of incident handling, review, follow-up actions and learning practices across engineering teams. **Use it for:** Gives an FDE vocabulary for communicating an incident and leaving the customer with useful follow-up work instead of only a technical fix. **Access:** The article is a free edition; linked subscriber-only templates require payment. **Practice:** For a simulated outage, write the customer impact, timeline, contributing conditions and two follow-up actions with owners and verification criteria. **Limit:** Published in 2021 and explicitly affected by survey selection bias; treat its survey numbers and vendor examples as historical. **Source scope:** Original free article read, including date, author, survey limitations, incident sequence and distinction between free content and paid templates. ### Made With ML Goku Mohandas. Made With ML / Anyscale. course; intermediate; free. Publication: 2023. Checked 2026-09-14. [Original resource](https://madewithml.com/). An end-to-end production ML curriculum spanning data, training, testing, serving, CI/CD and monitoring. **Use it for:** Shows how to turn a notebook into a maintainable customer deployment. **Access:** Public written lessons and code; local CPU setup is documented. Optional cloud infrastructure costs extra. **Practice:** Package a model behind an API, add data and model tests, and demonstrate a reproducible deployment. **Limit:** Python familiarity helps. Setup examples reference older Python/Ray versions, so review dependency compatibility before reuse. **Source scope:** Read the official course overview and setup lesson, including local no-GPU instructions and the 2023 citation. Did not validate every dependency or cloud workflow. ### Observability signals OpenTelemetry. OpenTelemetry. docs; intermediate; free. Publication: living / undated. Checked 2026-09-14. [Original resource](https://opentelemetry.io/docs/concepts/signals/). A conceptual guide to traces, metrics, logs, and their role in observability. **Use it for:** Connect a customer-visible failure to the services and requests involved. **Access:** The specification and documentation are open; telemetry backends may charge. **Practice:** Trace one failed workflow and correlate its request ID with an actionable log. **Limit:** Start with useful signals; collecting everything can raise cost and expose sensitive data. **Source scope:** Official course, documentation, author, or employer page read on the check date. ### SE Radio 706: Observability Tool Migration Techniques Brijesh Ammanath with Yechezkel Rabinovich. Software Engineering Radio / IEEE. podcast; advanced; free. Publication: 2026-02-04. Checked 2026-09-14. [Original resource](https://se-radio.net/2026/02/se-radio-706-yechezkel-chez-rabinovich-on-observability-tool-migration-techniques/). A discussion of migrating dashboards, monitors, pipelines and integrations while validating that production signals still work. **Use it for:** FDE deployments often enter legacy environments where preserving existing operational behavior matters as much as adding a new feature. **Access:** Public audio, show notes and automatically generated transcript. **Practice:** Write a migration checklist with an inventory, old/new signal comparison, owner for each alert, acceptance criteria and rollback conditions. **Limit:** The guest co-founded an observability vendor; separate migration techniques from product claims and account for transcript errors. **Source scope:** Original IEEE episode page, show notes and transcript read; episode number, guest, host, date and OpenTelemetry/migration scope verified. ### Timeouts, retries, and backoff with jitter Marc Brooker. Amazon Builders’ Library. article; intermediate; free. Publication: 2019. Checked 2026-09-14. [Original resource](https://d1.awsstatic.com/builderslibrary/pdfs/timeouts-retries-and-backoff-with-jitter.pdf). Explains why retry behaviour needs deadlines, limits, and randomisation. **Use it for:** Keep a failing customer dependency from consuming the whole service. **Access:** Public engineering reference; implementation infrastructure may incur costs. **Practice:** Inject a timeout, cap retry attempts, and compare synchronised retries with jitter. **Limit:** A retry is safe only when the operation and its side effects allow it. Start with SDK behaviour before adding another retry layer. **Source scope:** Primary engineering article read; canonical AWS PDF used where the newer landing page did not expose the article text.