The Masterclass, taught
How Claude Code actually reads your instructions, the Control Surfaces you have, the one choice every failure collapses to, and why output passing review isn't proof a rule held. The same framework as the Masterclass.
Workshop · full day · private team
The framework, then your own code.
A full day for a single team: learn the method in the morning, then apply it to your repository with us in the room in the afternoon session.
The applied tier — where the deep remediation method is delivered hands-on, on your actual Claude Code setup.
Start the conversation →
Private, single-team. Priced per engagement (POA).
What it is
Teaching in the morning; your actual code in the afternoon.
A full-day, private, single-team engagement in two halves. It's for a team that wants both the model and it applied to their own setup, in one sitting — not open enrollment.
The Masterclass and the Diagnostic name the failure modes but hold the deep remediation recipe for the applied tiers. The Workshop is that applied tier: the afternoon is where the method is delivered hands-on, on your repo.
Two halves
Learn the method, then apply it.
Your own repository
A hands-on walkthrough of your repo, driven by its Diagnostic scan — we remediate the named anti-patterns together and wire in the verification so it keeps holding.
What you leave with
Not a worked example — your code, strengthened.
The shared model
Everything the Masterclass leaves you with — the shared mental model, the Control-Surface map, the verification discipline.
Your gaps, remediated
Your own repository's gaps named, scored, and with suggested remediations with us — not on a toy repo, your actual code.
Verification, wired in
The verification checks you can wire into your actual setup, so drift surfaces early rather than silently.
Your facilitator
Philip Forshaw
Olinave · ex-Apple AI Strategy & Operations
Ex-Apple AI Strategy & Operations lead, with decades of training and workshop delivery behind him. The framework is patent-pending.
The method is a named taxonomy of the recurring failure modes, grounded in controlled experiments and Anthropic's own published guidance — then measured across 300+ real Claude Code setups. Not theory; the room works from the evidence.
Get started
Tell us about your team.
Private and scoped to your team. Tell us about your setup and we'll set up a call.
Start the conversation →Full day · private · for teams already running Claude Code