Skip to content
Work

Recent work.

Each case is a short read: the brief, what we built, and what made it hold up.

Implement
Agents · Governance

A growth team's ad audit agent.

A team of specialized agents that audits an ad account and writes a safe, ready-to-run optimization plan. An independent validator checks every output.

OUTCOME
Every output validated
Read case →
Strategize
System architecture · Computer vision

A fashion venture's AI product architecture.

The venture needed to know its AI product could be built before committing budget. We designed the architecture and validated it piece by piece.

OUTCOME
Swappable by design
Read case →
Educate
Workshops · Webinars

AI upskilling for research practitioners.

Commissioned workshops and webinars on working with AI, from research ideas to analysis to writing. 300+ practitioners so far, from 60+ institutions across 17 countries.

OUTCOME
300+ practitioners
Read case →
Implement
Agents · Tool use

A B2B team's lead research agent.

A multi-agent system that researches a company, scores it against a rubric the team can tune, and writes the briefing deck and the outreach email.

OUTCOME
Hours to minutes per lead
Read case →
Implement
Evaluation · Testing

A campaign team's synthetic focus group.

AI personas shaped to the team's customers test message variants before a real send. Sequential early-stopping calls the winner, and a synthesis explains why.

OUTCOME
Hundreds of personas per test
Read case →
Implement
Local AI · Privacy

A privacy-sensitive org's on‑prem AI.

A private assistant and agent stack on the client's own hardware. A routing layer decides per request, by sensitivity, what runs locally and what may leave.

OUTCOME
Sensitive data never leaves
Read case →
Get in touch

If you're not sure what to do about AI, start here.

Book a discovery call. Thirty minutes, no charge. We'll tell you honestly whether we can help. If we can't, we'll usually know who can.

Book a discovery call