Real research means dozens of searches, opened tabs, and notes that fall apart halfway through. Deep Research runs that loop on its own across several rounds.
sonnet1 weekBrave SearchFirecrawlOpenAIPostgres
Claude
78ROI
77Scale
$3.1k87Saved
ROI for
README.md
Why this subagent
Real research means dozens of searches, opened tabs, and notes that fall apart halfway through. Deep Research runs that loop on its own across several rounds.
It plans sub-questions, reads sources, and saves a checkpoint after each round so a long run can resume instead of starting over. The output is a cited report where every claim links to its source, and disagreements between sources are flagged rather than smoothed away.
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.
Search, fetch, and read sources across several rounds, saving a checkpoint after each.
pending
Cross-check claims between sources and note where they disagree or fall short.
pending
Write a cited report where every finding links back to the page it came from.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Research the question across multiple rounds; produce a report where every claim carries an inline citation, and surface contradictions instead of hiding them.
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.