# Casefile

- **Event:** [The Harness Engineering & Model Wrangling Hackathon](https://cerebralvalley.ai/e/mongodb-nyc-hackathon)
- **When:** Sat, Sep 26 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Team:** [Tilak Sharma](https://cerebralvalley.ai/u/tilak1114), [Nipun Agarwal](https://cerebralvalley.ai/u/NipunAgarwal)
- **GitHub:** https://github.com/Tilak1114/casefile
- **Demo video:** https://drive.google.com/file/d/13Zrvp2Dx-zzIb1f9QFowKRNNKRAK3JhZ/view?usp=sharing
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/95

Casefile helps review large construction claim files. It organizes the record into a chronology, party map, exhibit list, and coverage report, with a source quote and page reference for each finding.
Reviewing a project record can take weeks. Casefile breaks the work into smaller page batches. A lead claims examiner directs the review, with separate reviewers tracking parties and technical issues. Each finding is checked against the page it cites; if the quote doesn’t match, the finding is rejected. The system also checks that all relevant pages were reviewed before reporting that something wasn’t found.
Findings, page coverage, and run history are stored in MongoDB. LangGraph checkpoints let an investigation resume after an interruption. This setup lets Casefile work across about 1,700 pages without sending the entire file in one prompt.
We’re evaluating Casefile on the NTSB docket for the 2006 Big Dig ceiling collapse in Boston. The model reviews 88 documents; six investigator-analysis files are withheld and used with the NTSB final report to build the answer key. We compare its results with that key and with a single-prompt baseline.
Casefile organizes the evidence. It does not decide fault or liability; a human reviewer does. Built for Statement Two: Long Horizon Engineering.

## More from The Harness Engineering & Model Wrangling Hackathon

- [Many Lives](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/92)
- [UltraPM Console](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/93)
- [Btechs](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/94)
- [NYC-Flood-Map-Agent](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/96)
- [ShadowCFO](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/97)
- [Continuum](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/98)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/95. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt