Case study · Mobility

Movicat — Management platform + AI knowledge base

Mobility company with 50+ technicians and hundreds of procedure manuals. They needed technicians to find the right answer in seconds.

Sector: Mobility · Technical services · movicat.cat ↗

50+
active technicians
1,200
procedures
<3s
AI response
80%
tickets solved

The challenge

Technicians had a shared folder with 1,200 procedure PDFs. When an incident arose, they spent 10-15 minutes looking for the right procedure (and often used an outdated one).

The solution

We built a semantic AI knowledge base:

Tech stack

PHP + Python (backend), MySQL + ChromaDB (vectors), Anthropic Claude (LLM), OpenAI ada-002 embeddings, responsive web app.

Results

80% incidents AI-solved

Without calling a senior colleague.

<3s response time

Natural question → answer with cited source.

4x faster onboarding

New technicians autonomous in 2 weeks instead of 2 months.

Zero hallucinations

Strict RAG: only answers with source; otherwise "I don't know".

Living documentation

System detects recurring unanswered questions and flags what to document.

Auditable

Every answer logged: who asked, what was answered, which source.

"

We cut incident resolution time by 35%. New technicians are autonomous in weeks, not months.

— Operations director

Got technical documentation your team doesn't consult?

Perfect case for semantic AI. Typical cost: €3,500-7,000 + ~€30/mo model. ROI in 2-4 months.

I want my AI knowledge base