Dynamic Workflow Capstone: Let Claude Draw the Graph

Prompt Claude to build an orchestration workflow. Review the generated graph before trusting it. Ship a reusable workflow pattern.

~5hdynamic-workflowsclaude-codecapstone
Practice quiz (8 questions)Take final exam
Learning objectives
  • Prompt Claude to build an orchestration workflow.
  • Review the generated graph before trusting it.
  • Ship a reusable workflow pattern.
Note

This course extends the existing Agentic Engineering track. The focus is not "more prompting"; it is shaping the work: loops, fan-out, fan-in, routing, verification, cost, and convergence.

Self-routing workflows

For jobs you cannot plan up front, ask Claude to create a workflow: decompose, fan out, verify, synthesize, and save the script if the run is good.

Capstone graph

Build one of six production graphs: route security sweep, cited deep research, module port, adversarial diff review, scheduled ecosystem scan, or unknown-size discovery loop.

// Skeleton: scope -> fanout -> verify -> synthesize
const scope = await scopeNode(objective);
const findings = await fanout(scope.items);
const verified = await verify(findings);
return synthesize(verified);

Recap

A loop is a controlled cycle. A graph is the work shape around that cycle. The production skill is knowing which parts need model judgment, which parts are deterministic edges, and where confidence gates belong.

Dynamic Workflow Capstone: Let Claude Draw the Graph — Exercises

Exercise 1 — Draw the hidden graph

Take a linear workflow you already use, such as "research sources → summarize → compare → write report". Draw every step as a node. Then remove every arrow where the downstream step does not consume upstream data.

Reference solution

A strong answer identifies independent nodes and labels edges by data, not by time. Example: "source A research" and "source B research" are independent; both feed a deterministic reduce step; the reduced evidence feeds synthesis.

Exercise 2 — Write node contracts

For three nodes in your graph, define:

  • input shape
  • output shape
  • failure mode
  • downstream consumer
Reference solution

Good contracts are narrow: { topic, sourceUrl } in; { claims: [{ text, sourceUrl, confidence }] } out. Avoid "return a useful summary" because the next node cannot validate it.

Exercise 3 — Add one safety gate

Place a verifier, schema validator, budget check, or human approval gate on the edge most likely to poison downstream work.

Reference solution

For a research graph, gate unsupported claims before synthesis. For a code graph, gate findings with reproduction or a second reviewer before reporting.