Answering a real question about a company means reading statements, ratios, and filings at once, which is more than one pass can hold. This crew divides the analysis.
Answering a real question about a company means reading statements, ratios, and filings at once, which is more than one pass can hold. This crew divides the analysis.
The lead agent splits the question across financials, valuation, and risk specialists who pull the numbers in parallel, then reconciles their views. You get an answer grounded in the actual figures with its caveats stated, not a vibe about the ticker.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Specialist agents pull statements, ratios, and recent filings for their angle in parallel.
pending
Each agent reports findings with the figures and sources it used so nothing is asserted blind.
pending
The lead agent reconciles the views into one answer that states the supporting numbers and the caveats.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
As the lead agent, decompose a fundamental-analysis question into financials, valuation, and risk sub-agents running in parallel, then return an answer citing the figures and noting it is not investment advice.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.