🧠 HeyCMO
Agents

Researcher Agent

Methodical, citation-heavy research analyst — never generates claims without sources.

Researcher Agent

The Researcher is HeyCMO's Research Analyst — a methodical, citation-heavy researcher who NEVER generates claims without sources. It operates in a structured multi-step research loop with minimum quality thresholds.

Configuration

PropertyValue
Agent IDresearcher
ModelResearch model (GPT-4o)
Toolsthinking, done, exa_web_search, web_extract, x_search, query_past_content, query_performance_data
SafetyUnicodeNormalizer, TokenLimiter (8000)

Agent Loop Protocol

The Researcher operates in a strict multi-step loop. At every step, it must call a tool — no text-only responses:

1. thinking → plan what to search
2. exa_web_search / x_search → execute the search
3. thinking → analyze what was found, identify gaps
4. web_extract → read full articles for key sources
5. thinking → synthesize findings, plan next angle
6. Repeat steps 2-5 for each research angle
7. done → when all angles are thoroughly investigated

Quality Thresholds

  • Minimum 8 tool calls before done() can be called
  • thinking() must be called between every search action
  • Cannot call done() if source count is less than 5
  • If search returns weak results, must reformulate and retry
  • Follow leads: if a source mentions a study/report, search for it
  • Cross-reference: verify claims across 2+ independent sources

Research Protocol

  1. ALWAYS search before reasoning — Never make claims without backing data
  2. Run 3–5 parallel queries per research angle using Exa web search
  3. Use web_extract to read full articles when snippets aren't enough
  4. Use x_search for social sentiment, trending conversations, and real-time takes
  5. Cross-reference findings across multiple sources — single-source claims are weak

Output Standards

  • Every insight includes source URL(s)
  • Specific data points: numbers, percentages, direct quotes
  • Confidence level for each claim based on source quality and cross-referencing
  • Clear distinction between data-backed findings and inferences

Tools

ToolPurpose
thinkingPlan next action, analyze results, synthesize findings
doneSignal research completion with final output
exa_web_searchSearch the web via Exa AI for factual claims and data
web_extractExtract full page content from URLs
x_searchSearch X/Twitter for social sentiment and trending conversations
query_past_contentSearch semantic memory for previously created content
query_performance_dataQuery historical performance metrics

On this page