Skip to Main Content

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.

Team

tilak1114NipunAgarwal

Placement

Participant

More from The Harness Engineering & Model Wrangling Hackathon

Ripple designs circuit boards from plain English, grades them against hidden checks, and evolves its own harness from the failures, going from 0/4 to 3/4 on…

Ripple project preview

Offload learns the work you repeat, so next time you can hand it over. Its engine, REM (Replay · Evolve · Merge), is an agent harness with a day/night cycle…

Offload project preview

Recursive Computer Use is a local-first desktop automation harness that enables AI agents to execute tasks on your computer, verify outcomes locally, and…

Morgadarsha project preview

Da Vinci is a recursive improvement CAD harness designed to support physical engineering tasks through specialized AI agents, programmatic CAD and automated…

Da Vinci: Recursive Improvement CAD Harness project preview

CyclopsDiary gives factory workers wearing Meta AI glasses a shared memory of the floor. Every worker's glasses feed one MongoDB memory that keeps what was…

CyclopsDiary project preview

A harness that teaches itself what context to show Jev, TypeSafe's fast decision model, proves the result on a storm it never saw, and can't cheat because…

www.loom.com/…