Planner-Executor-Observer
Add an explicit Observer role between Planner and Executor so progress is checked against the plan instead of trusted blindly.
Problem
Two existing shapes both fail this requirement. Letting the executor run blind means the planner only finds out at the end whether the run was on-track, at which point fixing it requires starting over. Reporting back to the planner after every step rebuilds the ReAct loop and reintroduces the per-step planner cost the team adopted Plan-and-Execute to avoid. There is no clean place for a cheap, focused check that reads the executor's cumulative output against the plan and decides whether to keep going, stop, or replan.
Solution
Three roles: Planner produces a plan; Executor runs steps; Observer reads the cumulative result and decides loop / respond / replan. Each role has its own prompt and (optionally) its own model.
When to use
- Plan quality must be checked against execution evidence rather than trusted blindly.
- Three roles (planner, executor, observer) can be defined with their own prompts.
- Observer signals (loop, respond, replan) drive the agent's next move.
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.