All case studies
AI & ML
Logistics
12 min saved per query

An LLM copilot for operations teams

How Nova rolled out a grounded LLM copilot to 780 employees in four months — without hallucinations on customer data.

Client
Nova Freight
Industry
Logistics
Timeline
4 months from kickoff to launch
Business impact

Results at a glance

0 min
Time saved / query
0%
Auto-resolved
0
Active users
0.0M
Docs indexed
Situation

Where they started

  • Ops leads copy-pasted between six systems to answer routine questions.
  • Institutional knowledge lived in SharePoint, email, and one senior analyst's head.
  • Leadership wanted AI — safely.
Approach

How we did the work

  1. 1

    Grounding

    Indexed 1.4M docs and 42 structured systems into a governed retrieval layer.

  2. 2

    Evaluation

    Built a 900-question golden set as the gate for every release.

  3. 3

    Rollout

    Rolled out with structured feedback and quarterly model reviews.

  4. 4

    Governance

    Data classification, prompt logging, and role-based access from day one.

Results

What changed

12 minutes saved per query on average.

84% of queries resolved with cited sources.

780 employees active in three months.

Technology

Tools of the trade

OpenAI
LangChain
Pinecone
Azure
TypeScript
PostgreSQL

"It is the single most impactful piece of software we've rolled out in five years. Adoption was near-universal in a month."

Renata KowalskiCOO, Nova Freight
Book a consultation

Bring us your hardest problem

30 minutes with our senior specialists. No decks — just a working conversation.

We reply within one business day. Your information is kept confidential and never shared.

Ready to amplify your data?

Book a 30-minute strategy call. We'll map your data landscape and identify the three highest-leverage moves.

See case studies