Earnings calls run an hour and the one comment about margins or guidance is buried somewhere in the middle. This RAG indexes each quarter's transcript and filing so you can just ask.
sonnet1 weekSEC EDGARWhisperpgvectorOpenAI
Claude
56ROI
73Scale
$2k91Saved
ROI for
README.md
Why this subagent
Earnings calls run an hour and the one comment about margins or guidance is buried somewhere in the middle. This RAG indexes each quarter's transcript and filing so you can just ask.
Questions like what did the CFO say about churn return the exact quoted line with company, quarter, and speaker attached. No paraphrasing you can't verify; every answer points back to the words actually said on the call.
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.
Chunk the documents and embed them into a vector store keyed by company and quarter.
pending
Answer questions by retrieving the relevant passages and quoting them directly.
pending
Return each answer with the exact transcript line and timestamp it came from.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Answer the earnings question using only retrieved passages; quote the supporting sentence and cite company, quarter, and speaker for every claim.
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.