Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

50. A Design Method for Agentic Systems

You can recite every chapter and still greenfield a mess: agents first, tools second, eval never.

ShopOps’s failure mode on a fresh build is method inversionIntake, Resolution, Policy, and Outreach sketched on a whiteboard before anyone writes the action table, send-window policy, or a golden O-1001 fixture. Week six, Outreach sends outside the window because rules lived only in a system prompt.

environment → actions → state → trust → policy (+ send window, required fields) → model niches → memory → failures → evals → HITL → observability → deploy → feedback

Reliable agency is better systems around probabilistic intelligence. Autonomy is earned; governance is designed.

This chapter adds the twelve-step delivery order — each step produces an artifact; skip a step and Chapter 49’s catalog writes itself.

First principles

Work the twelve steps in order. Skipping to models and multi-agent roleplay is how Chapter 49’s catalog writes itself.

Each step produces an artifact. No artifact means you skipped the step — not that you were agile.

The twelve-step method

1. Environment

Define what the system senses and what “done” means.
Artifact: environment notes — systems of record, SLAs, episode boundaries.
ShopOps: support ticket / exception events, OMS/CRM, payment/refund rails, channel gateways; case closes on plan, escalate, or freeze.

2. Actions

Enumerate a closed or constrained action vocabulary. Mark read vs write vs irreversible.
Artifact: action table with side effects.
ShopOps: get_order, draft_email, send_email, add_order_note, escalate, …

3. State

Specify structured state and (s_{t+1}=F(s_t,a_t,o_{t+1})). Chat is not enough.
Artifact: state schema + FSM sketch.
ShopOps: CaseState, awaiting_approval, checkpoints.

4. Trust boundaries

Label untrusted inputs (user text, ticket notes, tool bodies, retrieval).
Artifact: trust diagram.
ShopOps: ticket free text never authorizes send.

5. Policies

Encode permit/deny in code; version packs.
Artifact: policy pack + tests.
ShopOps: send window, frequency caps, required-field checks.

6. Model niches

Decide where an LM helps vs where code/rules suffice. Route models deliberately.
Artifact: niche table (task → model class → fallback).
ShopOps: tiny model for intent; larger for strategy narrative; deterministic policy first.

7. Memory semantics

Name memory kinds; write/forget policies; privacy deletes.
Artifact: memory matrix + controller rules.
ShopOps: profile facts with provenance; no raw tool JSON as memory.

8. Failures

List distributed and agent-specific failures before launch.
Artifact: failure mode and effects list (timeouts, double send, injection, loops).
ShopOps: email gateway 503, worker death, poisoned notes.

9. Evals

Trajectory properties, fixtures, simulators — before broad autonomy.
Artifact: harness + ring-0/1 tests in CI.
ShopOps: golden O-1001; hostile loop fixture; send-window properties.

10. Human authority

Define who approves what, timeouts, safe defaults.
Artifact: HITL matrix + queue UX data model.
ShopOps: refund-or-reship threshold → human; timeout → no send.

11. Observability

Traces, cost, run-diff, audit packs.
Artifact: trace schema + dashboards + evidence export.
ShopOps: reconstruct one failed send end-to-end.

12. Rollout / rollback

Shadow, stage, pin versions, rollback drills.
Artifact: rollout plan with kill switches.
ShopOps: dry-run channels → percent shadow → prod pins for prompt/policy/model.

Concrete example (compressed)

Greenfield “KYC assist” (adjacent domain) through the twelve:

StepKYC sketch
1Docs upload + registry APIs; episode = one application
2extract_fields, compare_registry, request_docs, escalate, approve_draft
3Application FSM; checkpoint each stage
4Uploaded PDFs untrusted; registry JSON structured
5Jurisdiction rules in policy pack
6LM for extraction assist; code for registry match
7Intake facts vs raw OCR blobs
8Partial docs, registry timeout, spoofed PDFs
9Fixtures for mismatched ID; never auto-approve
10Human for final approval always
11Evidence pack per decision
12Shadow extraction before any write to core

Diagram

flowchart LR
  e1[1 Environment] --> e2[2 Actions]
  e2 --> e3[3 State]
  e3 --> e4[4 Trust]
  e4 --> e5[5 Policies]
  e5 --> e6[6 Model niches]
  e6 --> e7[7 Memory]
  e7 --> e8[8 Failures]
  e8 --> e9[9 Evals]
  e9 --> e10[10 HITL]
  e10 --> e11[11 Observability]
  e11 --> e12[12 Rollout]
  e12 --> e1

Caption: The method is a loop — production learning returns to environment and evals (Ch 41), not to silent policy mutation.

Implementation

Design-doc skeleton:

# Agentic system design: <name>

## 1 Environment
## 2 Actions (table)
## 3 State / FSM / F
## 4 Trust boundaries
## 5 Policies (pack versions)
## 6 Model niches
## 7 Memory semantics
## 8 Failure modes
## 9 Evals / fixtures
## 10 Human authority
## 11 Observability / audit
## 12 Rollout / rollback

## Non-goals
## Open gaps (Ch 48 IDs)
## Chapter 49 checklist results

Refuse implementation kickoff until steps 2, 5, 9, and 10 exist as artifacts.

Failure modes

SkipTypical blow-up
2Unbounded tool use
4–5Injection → unauthorized send
9Silent policy regressions
10Rubber-stamp HITL or none
12No rollback after bad prompt

Production considerations

  • Re-run the twelve when expanding autonomy — earning autonomy is re-certification, not a one-time ceremony.
  • Map frameworks onto these steps (Appendix G); if a framework hides a step, you still own the artifact.
  • Regulated domains: keep SR 11-7-style change control on model-adjacent artifacts. [VERIFY applicability]

Chapter summary

  • Reliable agency is systems design around probabilistic intelligence.
  • Twelve steps: environment → actions → state → trust → policies → model niches → memory → failures → evals → HITL → observability → rollout/rollback.
  • Each step leaves an artifact; no artifact means skipped work.
  • Autonomy is earned through evals and governance, not declared in a kickoff slide.
  • Return outcomes through gated loops (Ch 41–46), not magical self-rewrites.

Exercises

  1. Apply: Run all twelve steps for a support-desk agent; submit the design doc skeleton filled in.
  2. Apply: Same for claims processing; mark which steps differ from ShopOps.
  3. Gap: Attach Ch 48 IDs to any step you cannot complete honestly.
  4. Review: Score a past project against the twelve; list the first skipped step and the incident it predicted.

References

  • This book’s architecture and style guides — method consolidates them.
  • SR 11-7 — model risk change control. [VERIFY]
  • Anthropic, Building Effective Agents — when workflows beat agents. [VERIFY URL]
  • Cross-links: Ch 41–49; Appendices C–E; Appendix G.

Closing the book

You started with a completion. You end with a control plane: state, policy, memory, eval, humans, traces, and a method for the next domain.

The models will improve. The need for boundaries will not expire. Build the machine that makes a sampler’s judgment safe to act on — then earn each increment of autonomy with evidence.

Go build one for a problem you actually have. Start at step 1.