Orchestration Patterns¶
Qin Yu, 21 May 2026, updated 21 Jul 2026
Primarily for platform engineers
These patterns are most directly applicable if you are building or configuring automated agent pipelines — for example, writing a multi-step CI workflow or a research automation script that chains multiple agent calls. If you use Copilot, Claude Code, or similar interactive tools day-to-day, treat this as background reading. The mental models are useful, but you won't wire them up yourself. The exception is Prompt Chaining (pattern 1): the Research → Plan → Implement → Verify discipline applies to any interactive session.
Sub-agents are not just a speed feature. They are a way to control context pollution, parallelism, and failure boundaries.
1. Prompt Chaining¶
Use for fixed workflows:
Research → Plan → Implement → Verify
Each stage has a clear input and output contract.
2. Routing¶
Classify the task first, then choose a path:
- cheap model for extraction,
- mid-tier model for routine coding,
- frontier model for ambiguous design.
3. Parallelisation¶
Use for independent work:
- review three modules independently,
- compare multiple implementation options,
- run independent sub-agents for tests, docs, and security.
4. Orchestrator–Workers¶
Use when decomposition is not known in advance. The main agent plans, delegates, and integrates.
5. Evaluator–Optimizer¶
Use when quality matters more than latency:
Generate → Critique → Revise → Validate
6. Advisor Strategy¶
Run a cheaper executor by default and consult a stronger model only when strategic ambiguity appears. This is one of the highest-leverage patterns for reducing cost without sacrificing quality.