What this looks like in practice

Three engagements, start to finish. What the situation was, what we built, and how it was delivered.

Agentic Development · Enablement

A global cybersecurity company

A multi-cohort AI enablement program that moved 60–80 engineering managers from experimenting with AI coding tools to using them by default.

The situation: A cybersecurity organization with a large R&D function needed its engineering managers to move from experimenting with AI coding tools to using them as a default part of the development lifecycle. Adoption was scattered across individuals, with no shared practice.
What we did: Designed and delivered a multi-cohort AI enablement program for 60–80 engineering managers across 6–8 sessions, built on Cursor and Claude Sonnet. Full curriculum, facilitator guides, and hands-on exercises using the organization's own repositories. Extended into parallel tracks for QA architects (two-day intensive) and technical writers (~25 people, Cursor plus custom skill files).
Engagement shape: Multi-cohort series · 6–8 sessions · 60–80 participants · plus two specialist tracks

Implementation · MCP

Exposed a legacy payments portal to AI agents through an MCP server — without a risky big-bang rewrite.

The situation: A payments company running a legacy customer portal on an aging LAMP stack needed to expose its capabilities to AI agents without a risky big-bang rewrite.
What we did: Ran a discovery process across the existing portal and REST API surface, then designed and specified an MCP server in TypeScript with mock, sandbox, and live modes and a full audit trail. Recommended a parallel path — ship the AI interface now, migrate the portal incrementally using a strangler-fig pattern — rather than sequencing one behind the other.
Engagement shape: Discovery → architecture → phased build

Training · Enablement

A two-day GenAI intensive that turned program managers from AI observers into daily practitioners.

The situation: A program management organization where AI was seen as something the engineering team did. PMs needed to move from awareness to working practice.
What we did: Two-day hands-on GenAI intensive built around the team's actual program artifacts. Every session ended with participants producing something they'd use the next week — not a theory dump.
Engagement shape: 2-day intensive · Program Managers