Use thousands of AI agents to find new leads in biological data
OpenAI describes running thousands of AI agents in parallel across complex biological datasets to surface new research leads for scientists to test.
Source
raahelb on Hacker News · 2026-10-21 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-22.
What they did
OpenAI describes running thousands of AI agents in parallel across complex biological datasets to surface new research leads for scientists to test.
Result (as claimed)
New candidate findings at a scale no lab team could read by hand; 155 points on HN.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Gather your sources
Collect the papers, notes, links or files you want to work from in one place.
Load them into the tool
Open OpenAI, AI agents and add your sources. Keep the original files so you can check claims later.
Ask focused questions
Ask for summaries, comparisons or connections with citations to the source passages.
Verify and save
Spot check claims against the sources, then save the output as notes you can reuse.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Use thousands of AI agents to find new leads in biological data What the original author did: OpenAI describes running thousands of AI agents in parallel across complex biological datasets to surface new research leads for scientists to test. Reported result (as claimed by the author): New candidate findings at a scale no lab team could read by hand; 155 points on HN. Source: https://news.ycombinator.com/item?id=50180752 Tools they used: OpenAI, AI agents Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Use thousands of AI agents to find new leads in biological data What the original author did: OpenAI describes running thousands of AI agents in parallel across complex biological datasets to surface new research leads for scientists to test. Reported result (as claimed by the author): New candidate findings at a scale no lab team could read by hand; 155 points on HN. Source: https://news.ycombinator.com/item?id=50180752 Tools they used: OpenAI, AI agents Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Use thousands of AI agents to find new leads in biological data What the original author did: OpenAI describes running thousands of AI agents in parallel across complex biological datasets to surface new research leads for scientists to test. Reported result (as claimed by the author): New candidate findings at a scale no lab team could read by hand; 155 points on HN. Source: https://news.ycombinator.com/item?id=50180752 Tools they used: OpenAI, AI agents Category: Research & learning Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to run multiple coding agents together ยท How to build AI agents for SEO and ads
Related use cases
Benchmark AI agents by having them play an MMO
RuneScape Bench drops AI agents into an open-source RuneScape server to test long-horizon play like questing, skilling and trading.
Make LLM agents team up in Pokemon Showdown battles
A researcher built a 2v2 Pokemon Showdown environment where two LLM agents must coordinate through team chat. You can watch battles with the chat shown, and the code is on GitHub.
Stretch Grok Bot usage by handing bulk work to your Codex subscription
A cold-email operator had his chief-of-staff bot install the Codex CLI on its computer and sign in with ChatGPT, plus an API key for cheaper models. Grok Bot keeps the judgment calls (Calendly booking, CRM follow-ups) and offloads CSV classification, scrapers, spintax and transcript summaries.
Find a critical PHP vulnerability with Gemini and AI-assisted exploit work
Wiz's researchers used Gemini 4 Argon and GPT-5.6 Sol, with their Wiz Atlas platform, to find a remote code execution bug in PHP, build the exploit, detect attacks and validate the patch. They note models let them adapt the exploit across PHP versions and memory layouts.