Code Copper

Engineering the Future. Crafting Digital Excellence.

AI Solution · 2024

Atlas Copilot for Atlas Logistics

A retrieval copilot over two decades of freight contracts, evaluated on every release.

94%
Eval accuracy
5/wk
Hours saved / analyst
180k
Documents indexed

The challenge

Contract analysts spent roughly six hours a week locating clauses across 180,000 scanned documents, and confidence in generic AI search was low after a failed pilot.

What we did

  1. Built an OCR and chunking pipeline tuned for scanned freight paperwork.

  2. Combined hybrid retrieval with reranking, then grounded every answer in a citation.

  3. Shipped an eval harness of 400 analyst-written questions gating each deploy.

  4. Capped per-query cost and latency with a routing layer across model tiers.

The outcome

Analysts recovered roughly five hours each week, and answer accuracy holds at 94% against the eval suite release over release.