Industrial maintenance
Retrieval-augmented quoting for field maintenance
A quoting system grounded in the client’s own casebook and historical jobs, built alongside structured discovery that documented what the business needed it to decide.
Client
An industrial maintenance provider
Own
casebook, not generic knowledge
The challenge
What was in the way
Maintenance quoting depends on knowledge that lives in casebooks, historical jobs and the heads of experienced staff.
New quotes get priced by whoever is available, with the range between best and worst estimate wide enough to matter.
The solution
What we built
A retrieval-augmented quoting system over the client’s own maintenance knowledge base and historical case records.
It was developed alongside structured discovery sessions that documented what the business actually needed the system to decide.
Key technologies
- System
- Python, RAG over the client document corpus
- Data
- Structured training data from historical cases
Impact & results
A prototype grounded in their own casebook
Rather than generic knowledge.
Documented requirements
Produced as a deliverable in their own right.
Start here
Start with a problem, not a brief.
Tell us what is slow, what is manual, what is stalled, or what nobody understands any more. We will tell you honestly whether it is worth building.