# Om Solo

- **Event:** [RAISE Summit Hackathon](https://cerebralvalley.ai/e/raise-summit-hackathon)
- **When:** Jul 4 at 9:00 AM – Jul 5 at 7:00 PM (GMT+2)
- **Where:** Paris, France
- **Team:** [Om Morendha](https://cerebralvalley.ai/u/omkmorendha)
- **GitHub:** https://github.com/omkmorendha/diligence-agent
- **Demo video:** https://www.youtube.com/watch?v=EyPA1kLFHJo
- **Gallery:** https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/48

DiliAgent is an agentic RAG-powered solution that annotates documents, such as PDFs, with markers for misleading, inaccurate, or hallucinated information. An orchestrator agent coordinates a swarm of specialist agents, each responsible for investigating and validating specific claims made in a financial report.

The RAG system is built on top of FinanceBench and achieves a state-of-the-art score on the benchmark.

For the implementation, I used Kimi via Vultr as the primary orchestration agent. For the sub-agents and evaluation pipeline, I used Nemotron, also via Vultr, to enable faster development and iteration, at similar capabilities as larger models

## More from RAISE Summit Hackathon

- [SOAI](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/45)
- [GoTeam](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/46)
- [The Notified Bodies](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/47)
- [OpsAgents Autopilot](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/49)
- [Unit'em](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/50)
- [Blue Brick](https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/51)

---

Markdown version of https://cerebralvalley.ai/e/raise-summit-hackathon/hackathon/gallery/48. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt