Insights
Field notes on shipping AI inside real systems.
Latest
Forward-deployed engineering: the model is the easy part
What a forward-deployed engineer does, how the role relates to staff augmentation, and what we learned connecting AI to our own platform's rules and workflows.
Read post
Your first AI project: pick the win you can measure
The first AI project decides whether there is a second one. Start behind the firewall, on data you already have, with a human gate — and pick something you can measure in weeks.
Read post
Documentation that keeps itself current: the agent proposes, your team approves
Docs drift because updating them is nobody's job. Give the job to an agent that detects the drift, drafts the fix, and opens a pull request — and keep the approval where it belongs.
Read post
Computer vision on the cameras you already have: what two proofs of concept taught us
Counting people and vehicles, tracking occupancy, checking for a hard hat — the models are ready and the cameras are already installed. The work is placement, thresholds, drift, and deciding what never gets recorded.
Read post
Support ticket triage with AI: classify, enrich, route — and measure the reassignments
The first minute of every ticket is spent deciding what it is and who should see it. That minute is automatable — and the number that tells you if it worked isn't speed, it's how many tickets bounce.
Read post
An internal knowledge assistant is only as good as its last wrong answer
People ask in Slack because searching is slower and less trusted. A knowledge assistant earns its place the same way a colleague does: by being right, saying "I don't know," and knowing who's allowed to see what.
Read post
Contract intelligence: the model reads, your playbook decides what's risky
A contract review system is not a lawyer. It is a very fast reader with your playbook in hand — and the playbook, not the model, is where the project succeeds or fails.
Read post