AITraining2U

Programs

Resources

Case Studies

Quick Links

Enquire Now
Domain 1 · 27%% of exam

Workflow patterns: chaining, routing, parallelisation

Three of the five canonical patterns. The exam tests which one fits a described workload.

6 min read · Lesson 4 of 12 in this domain

Most production "AI systems" are not agents at all — they are workflows, where you decide the control flow in advance and the model fills in the reasoning at each step. That distinction is worth holding onto, because workflows are cheaper, faster and far easier to test. The named patterns below are just the handful of shapes that control flow tends to take. The exam gives you a scenario and expects you to recognise the shape, so read each one for its tell: what is it about the work that makes this pattern the right fit?

Key points
  • Prompt chaining — fixed, sequential steps where every stage always runs. Use when the workflow is predictable and each step is a distinct cognitive task. Isolating steps prevents attention dilution.
  • Routing — classify the input, then dispatch to exactly one specialised follow-on. Use when inputs fall into distinct categories best served by different prompts or tool sets.
  • Parallelisation — run independent work concurrently. Two flavours: sectioning (split a task into independent subtasks) and voting (run the same task several times and aggregate).
  • The tell for chaining is "all of these checks must always run". The tell for routing is "each ticket is one of these categories".
  • Voting triples cost, so it only earns its keep when you genuinely need consensus or higher confidence.
Diagram
Prompt chaining
Style#f8fafcSecurityDocsMergeevery step runs, in order — nothing is skipped
Routing
Classify#fff1f2Billing agentReturns agentTechnical agentResponseexactly one branch runs
Parallelisation
InputReviewer AReviewer BReviewer CAggregatevote / mergeall branches run concurrently, results combined
Reference
Signal in the question Pattern
Fixed steps, all always runPrompt chaining
Distinct categories, one path eachRouting
Independent subtasks, want speedParallelisation (sectioning)
Same task repeated for confidenceParallelisation (voting)
Unpredictable, model decides the stepsOrchestrator-workers
Worked example

Same task, three different shapes. "Review this pull request." If style, security and docs must all be checked every time, that is prompt chaining — three focused passes, merged. If the PR should go to whichever specialist matches its type, that is routing — classify once, dispatch to one. If you want three independent security opinions and will take the majority verdict, that is parallelisation by voting. The words in the scenario — "always", "whichever", "consensus" — are what tell you which.

Exam trap

Routing is offered where all branches must run (wrong — it picks one), and a single mega-prompt is offered where three concerns should be isolated.

Check your understanding

Style, security and docs must all be checked on every PR. Which pattern?

Correct answer: B — Prompt chaining
All steps always run, so chain them. Routing would pick one branch and skip the other two.

Tickets are billing, returns or technical, each needing a different prompt. Which pattern?

Correct answer: A — Routing
Classify once, then dispatch to exactly one specialist path.

Practise this domain with 27%%-weighted questions in the study app.

Open in study app

Source: Anthropic Engineering — Building effective agents · Independent study aid, not affiliated with or endorsed by Anthropic.