Mederic Burlet helps enterprise teams deploy AI into how they build software, from architecture to adoption. 700+ practitioners trained, 2-3x productivity gains, multi-agent and MCP systems. https://mederic.me/writing 2026-06-25T00:00:00.000Z Mederic Burlethttps://mederic.me https://mederic.me/writing/why-ai-pilots-stall 2026-06-25T00:00:00.000Z 2026-06-20T00:00:00.000Z

AI pilots stall because they optimise for a demo, not for adoption. Production requires architecture, guardrails, and a change in how teams work, not a better model.

https://mederic.me/writing/mcp-systems-for-real-teams 2026-05-30T00:00:00.000Z 2026-05-30T00:00:00.000Z

Good MCP systems expose a few high-leverage tools with clear boundaries, not every API you have. Scope, access control, and observability matter more than autonomy.

https://mederic.me/writing/700-engineers-on-adoption 2026-05-12T00:00:00.000Z 2026-05-12T00:00:00.000Z

After training 700+ practitioners, the pattern is clear: adoption is a behaviour change, not a tooling rollout. Role-specific practice and internal champions are what make it stick.