50 Claude Agents Working Simultaneously
Quick Review of Claude Code Dynamic Workflows
Yan Gao | Founder of alphaguru.ai & momtalk.ai
Anthropic released a new cool function of Dynamic Workflows yesterday. Basically you can now launch 50, 100 or more agents inside Claude Code to work simultaneously. It reminded me of the Wide Research function by Manus, which I wrote about this Jan.
This is a task I use Claude Workflows to do: Years ago when I started working in the investment industry, I spent weeks of time to just gather genuine organic growth data for companies by manually cleaning and calculating data from filings and earnings call transcripts. Now I have AI.
Prompt for Claude Code:
Create a workflow - I want to gather real organic growth excluding FX effect for top 50 S&P companies for the past 5 years. Use existing sec filings to do that.
This is an overview of the workflow agents - 50 of them working together.
In 8 mins Claude Code returned this:
Workflow complete — 100 agents, 4.17M tokens, ~8 min. The verifier surfaced an important data-quality issue (NVDA’s reported FY2021 YoY of 401% is an XBRL artifact). Let me parse the full result, assemble the outputs, and audit the reported-fallback figures for similar artifacts.
Then Claude Code reviewed its own work.
This is a snapshot of the output - it’s far from being perfect. More work needs to be done and more data needs to be collected. But the magnitude of time required is a tiny fraction of what it used to take.
The bottleneck moves downstream. Running 50 in parallel is the easy part. The expensive part is the human who has to spot-check what came out of each one. Compute got cheap. Attention didn’t. The first AI investor who builds a real audit layer on top of these swarms wins the round, not the one with the most agents.