Routing and Conditional Graphs

Route work based on validated node outputs. Separate model judgment from deterministic control flow. Design light and heavy paths.

~3hroutingconditional-edgesclassification
Practice quiz (8 questions)Take final exam
Learning objectives
  • Route work based on validated node outputs.
  • Separate model judgment from deterministic control flow.
  • Design light and heavy paths.
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.

Router nodes

A router node can use model judgment to classify an input, but the route should be deterministic code over the validated classification. This prevents surprise control flow.

const { severity } = await classify(diff);
const review = severity === 'high'
  ? await fullParallelAudit(files)
  : await quickReview(diff);

Route by cost and risk

Common routes: simple vs complex, low-risk vs high-risk, enough evidence vs need retrieval, safe answer vs human approval.

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.

Routing and Conditional Graphs — 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.