# Artem Mozgovoi

- **Event:** [Built with Opus 4.6: a Claude Code hackathon](https://cerebralvalley.ai/e/claude-code-hackathon)
- **When:** Feb 10 at 12:00 PM – Feb 17 at 10:00 AM (EST)
- **Where:** Location TBA
- **Team:** [Artem Mozgovoi](https://cerebralvalley.ai/u/layonez)
- **GitHub:** https://github.com/layonez/bid-buster
- **Demo video:** https://youtu.be/8Jsr86deqKE
- **Gallery:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/83

I'm a software engineer with zero procurement expertise. I used Opus 4.6 as my research team: agents surveyed open-source tools, OECD bid-rigging methodology, and anti-corruption red-flag indicators. 

That research became the knowledge base. Then I built Procurement Investigator in three days -- a CLI that codifies expertise locked behind $50K/year tools into open-source Investigation-as-Code. 
The same Opus 4.6 that taught me the domain now runs inside as an autonomous investigative agent -- looping through flagged findings, following leads across government databases, and externalizing every thought via log_reasoning so you can read its reasoning like a detective's notebook. 

Pointed at 7,259 FEMA COVID contracts with zero prior knowledge: it independently flagged Fillakit LLC (shipped soda bottles as test tubes, later investigated by the Senate) and Parkdale Mills ($532M sole-source). Every claim is automatically cross-checked against the data. Works without AI too, at zero cost.

---

Markdown version of https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/83. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt