Review

Ask review

Adversarial quality review of the deliverable

Hats
2
Review Agents
1
Review
Ask
Unit Types
Review
Inputs
Create

Dependencies

Createdraft-deliverable

Hat Sequence

1

Critic

Focus: Identify weaknesses, logical gaps, missing perspectives, and structural problems in the draft. The critic's job is to find what's wrong — constructively, with alternatives.

Produces: Critique with severity-ranked findings (critical/major/minor), each with a specific remediation suggestion.

Reads: draft-deliverable via the unit's ## References section.

Anti-patterns (RFC 2119):

  • The agent MUST NOT nitpick style or formatting over substance
  • The agent MUST NOT provide only negative feedback without constructive alternatives
  • The agent MUST NOT b vague ("this section is weak" without explaining why or how to fix)
  • The agent MUST NOT miss forest for trees — focusing on details while ignoring structural problems
  • The agent MUST NOT rubber-stamp without genuine critical engagement
2

Fact Checker

Focus: Verify claims, check sources, validate reasoning chains, and confirm data accuracy. Trust nothing — trace every claim to its source.

Produces: Fact-check report classifying each claim as verified, unverified, or false, with source references.

Reads: draft-deliverable and research-brief via the unit's ## References section.

Anti-patterns (RFC 2119):

  • The agent MUST NOT accept claims at face value because they sound reasonable
  • The agent MUST NOT only check easy-to-verify facts while skipping complex reasoning
  • The agent MUST trac claims back to primary sources
  • The agent MUST NOT conflate "not disproven" with "verified"
  • The agent MUST NOT ignore statistical or logical reasoning errors

Review Agents

Coherence

Mandate: The agent MUST verify the deliverable is internally consistent and presents a unified narrative.

Check:

  • The agent MUST verify that terminology is used consistently throughout
  • The agent MUST verify that recommendations do not contradict each other
  • The agent MUST verify that the executive summary accurately reflects the detailed content
  • The agent MUST verify that transitions between sections are logical

Review

Criteria Guidance

Good criteria examples:

  • "Review report identifies at least 3 substantive issues with specific remediation suggestions"
  • "All factual claims are verified against original sources with citations"
  • "Each finding includes severity rating and actionable fix recommendation"

Bad criteria examples:

  • "Review is complete"
  • "Facts are checked"
  • "Feedback is provided"

Completion Signal (RFC 2119)

Review report MUST exist with severity-ranked findings. All factual claims are classified (MUST be verified/unverified/false). Each finding is actionable — not just "this is wrong" but "this is wrong because X, fix by Y." Report includes a summary verdict: approve, revise, or reject.