Case studies

Six systems we built

Real problems, what we built and what changed, without client names or invented numbers.

Moving company

Instant quotes, no call-⁠back needed

Starting point
Every quote meant a call back. Slow answers put jobs at risk.
What we built
An instant-⁠quote configurator, a live queue and automatic follow-⁠up.
What changed
Customers see a price immediately; every request sits in one queue.

Read the case study

Local services business

From enquiry to follow-⁠up

Starting point
Leads landed in an inbox. Whoever saw one first followed up.
What we built
A shared lead queue with automatic routing, notifications and a status for every lead.
What changed
Every lead in one place, status visible to the whole team.

Read the case study

Media and content business

One system for content operations

Starting point
Planning, assets, review and publishing in separate tools; status by email and chat.
What we built
One dashboard with defined stages and a data layer that keeps status current.
What changed
One view of what is in progress, in review and scheduled.

Read the case study

Marketing

From brief to published content

Starting point
Every short-⁠form piece went through the same steps by hand, for several accounts.
What we built
An AI pipeline from brief to script, media and brand treatment, then scheduled publishing.
What changed
Content goes from brief to published without anyone carrying it from step to step.

Read the case study

Our own AI infrastructure

A control centre for AI agents

Starting point
AI agents across 34 projects, each with its own scripts and no record of what an agent did.
What we built
A control centre with project manifests, model routing, run records and memory in git.
What changed
Every run is recorded and can be checked. A new project needs a manifest entry, not a new script.

Read the case study

Analytics

A prototype for decision support

Starting point
A recurring decision rested on judgement and scattered history, with no consistent way to compare cases.
What we built
A prototype: a data pipeline, a prediction model and a screen a non-⁠technical user can act on.
What changed
The decision starts from the same data every time. It is a prototype, not a production system.

Read the case study