# Paired reading companion: from discovery to ownership

An independent, practical reading path for Richard Buehling’s *Forward Deployed* (Benmore, February 2026) and Panaversity’s *AI Agent Factory*. Use one customer problem throughout. These prompts are original exercises, not reproductions of either book.

Read the indicated sections, close the source, answer the recall question, and build the artifact. A reviewed reading session is separate from a demonstrated learning milestone. Read the [source review scope](material-review.md) for coverage and limits.

## 1. Understand the job

**Bring this question:** What are you responsible for after the demo?

**Benmore:** Chapter 1, Compressed Like a DJ, printed pp. 2–8; Chapter 11, What is Forward Deployed?, printed pp. 72–75; Chapter 12, The Deployed Workflow, printed pp. 75–77.

**Agent Factory:** [The AI Agent Factory: About](https://agentfactory.panaversity.org/docs/about); [How to Learn from This Book](https://agentfactory.panaversity.org/docs/how-to-learn-from-this-book).

Start with a person’s task and a result they can verify. Use AI to help execute the work while retaining responsibility for the decision, the evidence, and the operating relationship.

**Keep this distinction:** Benmore describes its consulting practice. Agent Factory focuses on AI workers. FDE roles can also involve conventional software and data systems. Neither book defines every employer’s role.

**Recall with the source closed:** Explain the difference between the human FDE and an AI worker without using either acronym.

**Build: Responsibility map**

- Customer problem and daily user
- What I own: discovery, delivery, adoption, operations
- What needs another specialist or decision owner
- One outcome and how we will observe it

[Apply in the learning path](../index.html#lesson-direct-and-review).

## 2. Discover before promising

**Bring this question:** Which part of the brief is still a guess?

**Benmore:** Chapter 2, Disco Debt, printed pp. 8–14; Chapter 3, Yes, Yes! Yes if…, printed pp. 14–17; Chapter 4, What Discovery Actually Is, printed pp. 18–23; Chapter 5, Understanding the Client, printed pp. 23–32.

**Agent Factory:** [Workflow Design & Diagnosis](https://agentfactory.panaversity.org/docs/workflow-design-diagnosis-crash-course).

Treat a polished request as the beginning of an investigation. Replay recent work with its operator. Separate observed behavior, reported needs, and assumptions before agreeing a delivery date.

**Keep this distinction:** A sponsor’s preferred solution contains useful context, but it is not proof of feasibility. A generated requirement does not become a fact because it appears in several documents.

**Recall with the source closed:** Name one observation that would make you change your proposed solution.

**Build: Evidence ledger**

- Claim and source
- Observed, reported, or assumed
- Impact if wrong
- Owner and next verification step

[Apply in the learning path](../index.html#lesson-discovery-debt).

## 3. Make a conditional commitment

**Bring this question:** What can you deliver within the real constraints?

**Benmore:** Chapter 3, Yes, Yes! Yes if…, printed pp. 14–17; Chapter 6, The Relationship, printed pp. 32–35; Chapter 7, The Discovery Process, printed pp. 36–50; Chapter 8, Walking Away, printed pp. 51–56.

**Agent Factory:** [Is This an Agent Problem?](https://agentfactory.panaversity.org/docs/is-this-an-agent-problem).

Choose a small outcome with a baseline, a test, and an owner. Compare ordinary automation with a model call before committing to an agent. Make access dependencies and stop conditions visible.

**Keep this distinction:** Respectful challenge protects the relationship. Treat Benmore’s escalation and separation advice as one firm’s practice; follow the actual engagement’s authority and agreements.

**Recall with the source closed:** If access arrives two weeks late, what changes: scope, date, or the decision to continue?

**Build: Pilot brief**

- User, baseline, and desired outcome
- Included work and explicit non-goals
- Access, time, and budget assumptions
- Acceptance owner and pause condition

[Apply in the learning path](../index.html#lesson-scope).

## 4. Write intent that can be tested

**Bring this question:** Could someone build the wrong thing and still pass?

**Benmore:** Chapter 7, The Discovery Process, printed pp. 36–50; Chapter 9, General Trends in AI-Driven Development, printed pp. 57–62.

**Agent Factory:** [Spec-Driven Development](https://agentfactory.panaversity.org/docs/spec-driven-development-crash-course).

Connect project intent to a feature, then to a small implementation task and its acceptance examples. Update both the specification and the checks when new evidence changes the plan.

**Keep this distinction:** A complete-looking specification can preserve a wrong assumption. Review the intent with the operator as well as checking the resulting code.

**Recall with the source closed:** Close the document. Describe one required behavior and the exact observation that proves it.

**Build: Behavior specification**

- Input and required output
- Rules, permissions, and denied actions
- Happy path and two failure examples
- Links to evidence and changed decisions

[Apply in the learning path](../index.html#lesson-delivery-spec).

## 5. Decide who owns each step

**Bring this question:** What should change, and what must still be protected?

**Benmore:** Chapter 4, What Discovery Actually Is, printed pp. 18–23; Chapter 5, Understanding the Client, printed pp. 23–32; Chapter 7, The Discovery Process, printed pp. 36–50.

**Agent Factory:** [Designing the Vertical System of Record](https://agentfactory.panaversity.org/docs/ecosystem/designing-the-vertical-sor); [Workflow Design & Diagnosis](https://agentfactory.panaversity.org/docs/workflow-design-diagnosis-crash-course).

Study the current workflow to understand it, then redesign around the outcome. Keep obligations and useful controls; challenge repeated handoffs and data entry. Assign responsibility at each consequential step.

**Keep this distinction:** Copying an old workflow can preserve waste. Removing a step without understanding its purpose can remove a necessary control. Resolve uncertainty with the accountable operator.

**Recall with the source closed:** Why is “a human will review it” an incomplete control?

**Build: Delegation map**

- Step and purpose
- Keep, change, or remove, with evidence
- Human, AI, or collaboration, with reason
- Reviewer, check, timing, and review date

[Apply in the learning path](../index.html#lesson-redesign-work).

## 6. Give every answer a source

**Bring this question:** Is this a rule, a live fact, or someone’s interpretation?

**Benmore:** Chapter 7, The Discovery Process, printed pp. 36–50.

**Agent Factory:** [The FDE AF Model](https://agentfactory.panaversity.org/docs/ecosystem/fde-af-model); [System of Context](https://agentfactory.panaversity.org/docs/ecosystem/system-of-context).

Bring together approved knowledge, current operational facts, and relevant case notes. Preserve source identity, version, access boundaries, and missing evidence when assembling context for a task.

**Keep this distinction:** Search relevance does not establish authority. A model’s memory, an indexed copy, or a chat comment cannot silently replace the system or expert that owns the answer.

**Recall with the source closed:** What should happen when a helpful note conflicts with an approved procedure?

**Build: Context packet**

- Task, actor, and allowed action
- Applicable rule, version, owner, and citation
- Live facts from the owning system
- Supporting notes, conflicts, and missing evidence

[Apply in the learning path](../index.html#lesson-governed-knowledge).

## 7. Use the prototype to learn

**Bring this question:** What looks finished but is still simulated?

**Benmore:** Chapter 9, General Trends in AI-Driven Development, printed pp. 57–62; Chapter 10, An AI-Driven Development Process, printed pp. 63–71.

**Agent Factory:** [Spec-Driven Development](https://agentfactory.panaversity.org/docs/spec-driven-development-crash-course).

Use a working slice to test the flow with a person. Keep a gap register that distinguishes demonstrated behavior, placeholders, missing integrations, and release evidence.

**Keep this distinction:** Benmore’s prototype percentages are illustrative, not acceptance targets. Start security and permission checks with implementation; a later readiness review does not replace them.

**Recall with the source closed:** Show one prototype behavior you would not yet expose to a real user, and explain why.

**Build: Release-gap register**

- Requirement and current behavior
- Mock or incomplete dependency
- Risk, owner, and evidence needed
- Pilot exclusion or closure decision

[Apply in the learning path](../index.html#lesson-prototype-gap).

## 8. Prove the result and the checker

**Bring this question:** Which wrong answer still earns a passing grade?

**Benmore:** Chapter 10, An AI-Driven Development Process, printed pp. 63–71.

**Agent Factory:** [Trusting the Checker](https://agentfactory.panaversity.org/docs/trusting-the-checker-crash-course); [Eval-Driven Development for AI Employees](https://agentfactory.panaversity.org/docs/eval-driven-development-crash-course).

Compare a simple baseline with the proposed workflow on held-out tasks. Inspect the resulting state and failure groups. Check a model grader against independent labels before using its score to decide on release.

**Keep this distinction:** A deterministic test proves a bounded property; an evaluation describes sampled behavior. A high average can hide a serious failure in a small but important group.

**Recall with the source closed:** Give an example where the response sounds correct but the task actually failed.

**Build: Evaluation decision**

- Baseline and held-out cases
- Expected and actual final state
- False passes, false failures, and serious errors
- Release decision, limitations, and reviewer

[Apply in the learning path](../index.html#lesson-check-the-checker).

## 9. Design approval and recovery

**Bring this question:** Can the operator understand, change, and recover the action?

**Benmore:** Chapter 7, The Discovery Process, printed pp. 36–50; Chapter 10, An AI-Driven Development Process, printed pp. 63–71; Chapter 13, Knowledge Transfer and Graduation, printed pp. 77–81.

**Agent Factory:** [Designing Agent Experiences](https://agentfactory.panaversity.org/docs/designing-agent-experiences-crash-course).

Place the proposed change, evidence, and alternatives at the decision point. Show where work is waiting and who can act. Practise a wrong recommendation and an interrupted operation through the interface.

**Keep this distinction:** Correct model output does not guarantee usable software. Measure the attention and corrections the complete workflow demands from people.

**Recall with the source closed:** What information must be visible before a reviewer approves an assignment?

**Build: Supervision brief**

- Action preview and supporting evidence
- Approve, edit, reject, and stale-decision behavior
- Pending, failed, and completed states
- Recovery path and keyboard-only task result

[Apply in the learning path](../index.html#lesson-review-and-recover).

## 10. Turn repeated work into a worker

**Bring this question:** What replaces the help you give during a session?

**Benmore:** Chapter 10, An AI-Driven Development Process, printed pp. 63–71; Chapter 14, The Support Phase, printed pp. 82; Chapter 17, Support in the AI Era, printed pp. 88–90.

**Agent Factory:** [From One-Off to Worker](https://agentfactory.panaversity.org/docs/from-one-off-to-worker); [Harness Engineering](https://agentfactory.panaversity.org/docs/harness-engineering-crash-course).

Promote a proven recurring task by making its specification, checks, escalation rules, and runtime durable. Give jobs identity, bounded execution, persistent state, and an accountable operator.

**Keep this distinction:** A successful session is useful evidence, but it does not establish unattended reliability. Keep the simpler workflow if repetition and value do not justify operating a worker.

**Recall with the source closed:** If the worker stops after a remote write succeeds, how does the next run avoid repeating it?

**Build: Worker operating contract**

- Trigger, job ID, and durable state
- Allowed actions, runtime, and retry limits
- Escalation reason, recipient, and evidence
- Pause, restart, and duplicate-trigger demonstration

[Apply in the learning path](../index.html#lesson-worker-contract).

## 11. Transfer the ability to operate

**Bring this question:** Could another person fix and change the system?

**Benmore:** Chapter 11, What is Forward Deployed?, printed pp. 72–75; Chapter 12, The Deployed Workflow, printed pp. 75–77; Chapter 13, Knowledge Transfer and Graduation, printed pp. 77–81.

**Agent Factory:** [Human-Agent Teams](https://agentfactory.panaversity.org/docs/human-agent-teams-crash-course).

Prepare a runbook for incidents, a system overview for design decisions, and a maintained specification. Ask the receiver to recover a failure and make a small change using those assets.

**Keep this distinction:** Documentation delivery is not the same as knowledge transfer. Choose technology and operating practices that the receiving team can maintain.

**Recall with the source closed:** Which step did the receiver need you to explain, and what did you change afterward?

**Build: Witnessed handoff**

- Primary and backup owner
- Runbook, system overview, and current specification
- Recovery and change drill results
- Unresolved issues and accepted responsibilities

[Apply in the learning path](../index.html#lesson-support-exit).

## 12. Agree what happens after delivery

**Bring this question:** Where does support end and new work begin?

**Benmore:** Chapter 14, The Support Phase, printed pp. 82; Chapter 15, The Support Model, printed pp. 82–85; Chapter 16, When to Recommend What, printed pp. 86–87; Chapter 17, Support in the AI Era, printed pp. 88–90.

**Agent Factory:** [The FDE AF Model](https://agentfactory.panaversity.org/docs/ecosystem/fde-af-model).

Match support to actual operating needs. Separate maintaining agreed behavior from new scope, name response ownership, and set a review point. Reuse only the assets you have the right to reuse.

**Keep this distinction:** Benmore’s support percentage is its commercial example, not a market rate. Agent Factory’s vertical business model is an option, not a requirement for employment or a promise of earnings.

**Recall with the source closed:** When would the honest recommendation be no additional support contract?

**Build: Support and reuse agreement**

- Coverage, hours, escalation, and exclusions
- Maintenance versus new scope
- Operating owner and next review date
- Reusable asset, ownership, and customer-data boundary

[Apply in the learning path](../index.html#lesson-delivery-offer).

## Benmore chapter index

Printed pages are four lower than the PDF viewer page. The supplied PDF is not redistributed.

| Chapter | Printed pages | Reading question |
| --- | --- | --- |
| 1. Compressed Like a DJ | 2–8 | What does faster implementation fail to solve? |
| 2. Disco Debt | 8–14 | Which assumptions compound through your documents? |
| 3. Yes, Yes! Yes if… | 14–17 | What condition belongs beside the promise? |
| 4. What Discovery Actually Is | 18–23 | Does the proposed scope solve the underlying problem? |
| 5. Understanding the Client | 23–32 | Who decides, and what are the real constraints? |
| 6. The Relationship | 32–35 | How will you raise disagreement respectfully? |
| 7. The Discovery Process | 36–50 | Can you trace the decision from evidence to specification? |
| 8. Walking Away | 51–56 | What requires realignment or escalation? |
| 9. General Trends in AI-Driven Development | 57–62 | Which claims are observations or predictions? |
| 10. An AI-Driven Development Process | 63–71 | What evidence closes each prototype gap? |
| 11. What is Forward Deployed? | 72–75 | Which parts of strategy and delivery do you own? |
| 12. The Deployed Workflow | 75–77 | How do you make decisions and blockers visible? |
| 13. Knowledge Transfer and Graduation | 77–81 | Can the receiver recover and change the system? |
| 14. The Support Phase | 82 | Who is accountable after launch? |
| 15. The Support Model | 82–85 | What is maintenance and what is new development? |
| 16. When to Recommend What | 86–87 | Which ongoing help does the customer actually need? |
| 17. Support in the AI Era | 88–90 | Which maintenance actions still require review? |