I help teams make AI actually stick.
Enterprise AI delivery, multi-agent & MCP systems, and the training that turns pilots into adopted, day-to-day ways of working.
Most AI pilots fail on scope, not on models.
Hand an agent the whole problem and you get sprawl you cannot review. Give it three named tools and a job with edges, and you get something a team can actually ship on a Tuesday. Same model, different blast radius.
Same model. Different blast radius.
Unbounded: the agent decides its own next move, every time.
Latest from the blog
All articles →Getting started with Ghostwriter, step by step
A plain walkthrough of installing and using the free Ghostwriter tool: where the files go, how to ask for a rewrite, what the clean-up step does, and how much of a difference it actually made in testing.
How to spot AI writing before you hit send
A quick, non-technical checklist for catching the giveaway signs of AI-written text in your own drafts: the vocabulary, the lists of three, the flat rhythm, the long dash, and the too-neat ending.
Langdrift: scoring how differently a translation lands
Langdrift compares audio of an original and its translation and returns a drift score: how far apart the two land cognitively, catching accurate but off translations.
Elsewhere
Let's connect.
Always happy to talk shop, compare notes, or just say hi. Email or LinkedIn is the fastest way to reach me.
Get in touch