# Agent PhD

- **Event:** [The Harness Engineering & Model Wrangling #SFTechWeek Hackathon](https://cerebralvalley.ai/e/mongodb-sftw-hackathon)
- **When:** Sun, Oct 11 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Christine Baek](https://cerebralvalley.ai/u/cbaek)
- **GitHub:** https://github.com/viirii/scientist_agent
- **Demo video:** https://drive.google.com/file/d/1mAXwDTHRC4LYU_rXaJqEl69QLMn5i9ho/view?usp=drive_link
- **Gallery:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/70

Laboratory automation is advancing, but scientific research still faces hard limits: available space and robots, costly reagents, and the time biological experiments take. As coding agents become more capable and robotics improves, Agent PhD connects the two through smarter scientific decision-making. It is a continuously learning research partner that reads literature, connects findings, develops hypotheses, and proposes studies toward a scientist’s long-term goal. The ambition is to make every costly ($$ and time) in vitro and in vivo experiment count by improving what we choose to validate next.
COVID-19 is our benchmark for a question with real urgency: if today’s recursive agents had existed in early 2020, could they have helped move discovery forward faster? Starting with prior coronavirus knowledge, we unlock 2020 literature month by month and compare two persistent agents. Both update their knowledge, hypotheses, and research plans; one follows a fixed strategy, while the other can revise its strategy through reviewed changes. Monthly evaluations compare their earlier ideas with newly published evidence, testing whether adaptive agents identify promising directions sooner.

## More from The Harness Engineering & Model Wrangling #SFTechWeek Hackathon

- [AgentDesk](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/67)
- [lane - gambling on your friends success](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/68)
- [Recoup](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/69)
- [hydra](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/71)
- [Forge Extended](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/72)
- [OptBench](https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/73)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/70. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt