Fundamental questions need numbers from several filings cross-checked together, and pulling them by hand is slow and error-prone. This crew parses them in parallel.
Fundamental questions need numbers from several filings cross-checked together, and pulling them by hand is slow and error-prone. This crew parses them in parallel.
The lead agent assigns each statement to its own agent, a ratio agent does the math, and the lead assembles the answer. Every claim comes with the figure and filing it came from, so you can check the work instead of trusting a summary.
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.
Separate agents fetch and parse each statement from filings in parallel.
pending
A ratio agent computes margins, growth, and leverage from the parsed figures.
pending
The lead agent assembles a fundamentals answer that shows the numbers behind every claim.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
As the lead agent, dispatch sub-agents to parse income, balance-sheet, and cash-flow data in parallel, compute the relevant ratios, and return a fundamentals answer that shows every figure and its filing source.
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.