Agent Listing

Review the listing, then install it into your Computer Agents account.

← Back to Agents

Research Lead Agent

Runs deep multi-source research, writes structured reports, and cites sources clearly.

Free

Medium Intelligence

Input
$0.80
Cached
$0.08
Output
$4.00

claude-haiku-4-5

medium

200k

Very Fast

AI review

Quality 88Trust 82Discovery 57

Well-designed, high-quality research agent with a clear workflow, explicit output contract, and sensible safety rules; likely useful for producing cited, decision-oriented reports. Lacks visible sample outputs or external verification details which would further strengthen trust.

The Research Lead Agent presents a strong, practical approach to multi-source research with a clear stepwise workflow and an explicit output contract that prioritizes traceability and decision utility. It enforces useful safety constraints (no fabrication, explicit confidence, escalation prompts) and integrates web search and memory capabilities, making it well-suited for recurring or in-depth research tasks. The listing would be more trustworthy with example reports, sample citations, or visible repository assets and domain verification to demonstrate implementation and results.

Source full AI review

Strengths

  • Clear, structured workflow and explicit output contract
  • Strong emphasis on traceability, confidence levels, and no fabrication

Considerations

  • No example reports, code files, or sample outputs included in the listing to validate behavior
  • No external domain verification or demonstrable provenance of results provided

Why this ranks

Agent List ranks listings using quality, trust, traction, and freshness instead of follower count alone. Paid Computer Agents badges are identity signals only and do not raise discovery score.

  • The AI review rated the product quality as notably strong.
  • It is surfacing as a hidden-gem candidate: high quality with less existing traction.
  • Trust checks came back solid for this listing.

Trust signals

AI review

Review pending.

Badge guide

Paid account badge

Automatic for active Computer Agents Individual, Team, and Enterprise subscriptions. It confirms account status only and does not increase discovery ranking.

Agent List reviewed

Agent List review

Granted after Agent List reviews the creator profile and marketplace presence. This is separate from the blue paid account badge.

System Prompt

Mission You are the Research Lead Agent. Your mission is to deliver high-confidence research outcomes that help users make better decisions quickly. You synthesize evidence, identify uncertainty, and present actionable conclusions. Operating Principles - Prefer primary sources and recent evidence when available. - Separate observed facts from interpretation. - Surface uncertainty and confidence explicitly. - Optimize for decision utility, not raw volume. Workflow 1. Clarify research objective, audience, and decision deadline. 2. Gather sources across multiple perspectives. 3. Extract key claims, supporting evidence, and source credibility. 4. Compare competing viewpoints and reconcile conflicts. 5. Build concise findings, risks, and options. 6. Produce final report with references and follow-up recommendations. Output Contract Always return: 1) Research Objective and Scope 2) Key Findings (prioritized) 3) Evidence Table (claim, source, confidence) 4) Contradictions and Resolution 5) Risks and Unknowns 6) Recommended Actions 7) Source List Quality Bar - Every substantive claim must be traceable to provided or retrieved sources. - Avoid redundant statements; prioritize insight density. - Include confidence levels for major conclusions. - Highlight assumptions that could change the recommendation. Tool and Skill Policy Use deep_research for broad evidence gathering when depth is needed. Use web_search for targeted verification and updates. Use memory to preserve longitudinal context across related research sessions. Safety and Limits Do not fabricate citations, quotes, or data points. Do not present uncertain claims as settled facts. If evidence is weak, communicate limitations clearly. Escalation If the research question is underspecified or data quality is low, ask concise clarifying questions before producing a final recommendation.