Research

Auto review

Gather context, explore prior art, and understand the problem space

Hats
2
Review Agents
1
Review
Auto
Unit Types
Research
Inputs
None

Hat Sequence

1

Analyst

Focus: Evaluate the researcher's findings, identify patterns, surface actionable insights, and assess gaps in coverage. Transform raw research into structured understanding.

Produces: Structured analysis with pattern identification, gap assessment, and prioritized insights.

Reads: Researcher's findings from the unit's ## References section.

Anti-patterns (RFC 2119):

  • The agent MUST NOT over-analyze without synthesizing into actionable takeaways
  • The agent MUST NOT ignore contradictory evidence that doesn't fit the emerging narrative
  • The agent MUST NOT treat all findings as equally important
  • The agent MUST identify what's still unknown or uncertain
2

Researcher

Focus: Explore sources, gather data, and synthesize findings across the problem space. Cast a wide net — the goal is comprehensive understanding, not premature conclusions.

Produces: Raw research notes with source annotations, organized by theme or question.

Reads: Intent problem statement, any existing project knowledge.

Anti-patterns (RFC 2119):

  • The agent MUST NOT div into creation before research is complete
  • The agent MUST NOT rely on a single source or perspective
  • The agent MUST document where information came from
  • The agent MUST NOT summariz without preserving source detail
  • The agent MUST NOT stop research after finding the first plausible answer

Review Agents

Thoroughness

Mandate: The agent MUST verify research covers the problem space without significant blind spots.

Check:

  • The agent MUST verify that multiple sources consulted, not just the first result
  • The agent MUST verify that conflicting information is acknowledged and reconciled, not ignored
  • The agent MUST verify that prior art is surveyed — the research does not reinvent known solutions
  • The agent MUST verify that assumptions are stated explicitly, not embedded silently

Research

Criteria Guidance

Good criteria examples:

  • "Research brief covers at least 3 competing approaches with pros/cons for each"
  • "All claims cite a specific source with retrieval date"
  • "Gap analysis identifies at least 2 areas requiring further investigation"

Bad criteria examples:

  • "Research is thorough"
  • "Sources are included"
  • "Analysis is complete"

Completion Signal (RFC 2119)

Research brief MUST exist with synthesized findings organized by theme. All claims are sourced. Analyst MUST have identified key patterns, ranked insights by relevance, and documented knowledge gaps with recommended next steps.