Proposer/Critic — How You Apply the Pattern
One component proposes, a second evaluates before it stands. Where the pattern runs across your work, from ABOM's organization-scale judgment layer to the checker agents in AI Agent for PM.
An agent pattern where one component proposes an action or judgment and a second evaluates it before it stands. The pattern itself is general. What you treat as original is using it at organization scale in ABOM: verifying that agent nodes judge well over time, rather than inspecting every handoff.
"Judgment layer" (Proposer/Critic: is it right?) is distinct from "observability layer" (health signals: is it alive?). ABOM's notes warn that conflating them loses the differentiator.
Two scales
Organization scale · ABOM
The mechanism for verifying that business-unit agent nodes judge well over time (calibration, evals, golden cases) rather than inspecting every handoff. You treat it as ABOM's original contribution, with no clean analog in competing frameworks or in OOP.
System scale · LangGraph agentic QA pipeline
The dual-loop architecture of the LangGraph GUI-testing agent, alongside a rule-based Observer and a Reviewer that refines task steps. One of three orchestration patterns you compared, with ReAct and Plan-and-Execute.
Where it runs
| Where | Proposer | Critic | Status |
|---|---|---|---|
| ABOM | Business-unit agent nodes | Calibration, evals, golden cases on how well each node judges | Framework (v2); no running deployment |
| LangGraph agentic QA pipeline | Planner (plan-guided ReAct) | Dual loop with a Reviewer; rule-based Observer flags symptoms | Built at Keysight; which agent plays which role isn't spelled out in the notes |
| JourneyDrive | Agent acting from screenshots | Separate reviewer confirms each step from the screen | Ships an act-then-review loop (repo, Sep 22) |
| AI Agent for PM v1.2 | Merge step; Problem Definition agent | Merge Checker; Problem Definition Checker | Standing design rule |
| PM decision framework | The call and its fix | Risk + Fix: would the fix have caught the failure already in the data? | Applied to product calls |
| Gas City (Yegge) | Agent that recommends | Second agent that checks and acts | External; your article names a Problem Definition checker as the next place to apply it |
The two-agent rule in AI Agent for PM
Any LLM step whose error propagates unseen gets a checker.
One of v1.2's five design principles, added in your 2026-10-20 critical review.
Merge Checker Agent
Re-reads the records behind each same_issue_as edge; confirms, downgrades or rejects.
Problem Definition Checker Agent
Verifies claims against cited records, checks one problem vs. a split, and checks the persona match.
Evidence, not reasoning
Checkers read source evidence, never the worker's reasoning, and can confirm, flag or reject but never rewrite.
Review gates
Checker flags are deterministic triggers for early human review; the worker's own confidence is one input, never the only one.
- In the LangGraph pipeline, which agents play Proposer and which play Critic?
- Is the JourneyDrive reviewer the planned LangGraph Proposer/Critic integration, or a separate, simpler loop?