Manufacturing
Manufacturing operations dashboard
Bringing machine data from four decades of equipment into one view, then using it to predict failures instead of reacting to them.
- Higher line efficiency
- 35%Higher line efficiency
- Unplanned downtime
- -48%Unplanned downtime
- Data latency, from daily
- 3 minData latency, from daily
- Client
- A precision components manufacturer
- Sector
- Manufacturing
- Duration
- 7 months
- Stack
- Python
- TimescaleDB
- Docker
- Kubernetes
- React
The problem
Six production lines ran equipment installed between 1994 and 2023. Output was reconciled manually into a spreadsheet each morning, so every decision was made against yesterday's picture, and the causes of a bad shift were reconstructed from memory.
What we did
- Built protocol adapters for each generation of equipment, including two that required reading directly from serial output.
- Established a common telemetry schema and a time-series pipeline with retention rules agreed with operations.
- Designed a control-room display for sustained attention — no auto-rotating panels, no colour as the only signal.
- Trained anomaly detection on historical failure records and surfaced predictions as maintenance suggestions, not automated actions.
The outcome
Line supervisors work from data three minutes old rather than a day old. Maintenance moved from a fixed schedule to a condition-based one, and the causes of a bad shift are now visible while it is still running.
Illustrative engagement profiles. Figures show the shape of outcomes we design for, not published client results.
Services
Practices used here
AI Agents & Workflow Automation
Language models, retrieval and agents built to run in production with evaluation and guardrails.
Learn more about AI Agents & Workflow AutomationWeb & Enterprise Applications
Typed, tested platforms that integrate with the systems already running your business.
Learn more about Web & Enterprise Applications
More work
Other engagements
Healthcare
60%
Reduction in onboarding time
Healthcare learning platform
Replacing a classroom-and-paper induction programme with a digital learning platform that new clinical staff complete at their own pace.
Read the engagement — Healthcare learning platformRetail
42%
Reduction in support tickets
AI customer assistant
A grounded assistant that answers order and product questions from real systems, and hands over to a person the moment it should.
Read the engagement — AI customer assistant
Start with a conversation
Tell us what you are trying to build and what is in the way. We will tell you whether we are the right people for it.