I build identity-based security for agentic systems.

“Our work habits are really changing, even at GitHub. Reviewing every line of AI-generated code by hand is becoming wasted time, provided the work is tightly structured and the checks are automated. For a long time we believed the quality of our tools made the quality of the result; the capabilities of harness providers now let us shrink our set of tools.”

“AI is an enabler, not an end goal. The real impact comes from rethinking business processes, not from bolting models onto legacy workflows. And there is no ROI without adoption: the most valuable use cases come straight from frontline teams, who know the operational context.”

“Tools are turning into code generated for each request. Pigment dropped its purpose-built analysis tools: the agent now writes Python that runs in a sandbox and calls MCP itself. Tools stop being a fixed catalogue and become code produced for the request.”

“Freeze the demonstration build well before the final presentation. Code changes continued until the final hour before judging, including backend commits at 17:05 and refactoring at 17:56. The live backend failed during the presentation. A stable, frozen build with a well-rehearsed demonstration path always outperforms last-minute feature additions.”

“Technical feasibility matters little if the economic model lacks clear budget ownership. While our technical pitch focused on telematics sensors mounted on municipal vehicles for predictive road repair, jury questions centered almost exclusively on procurement, contract ownership, and budget allocation. Developing a viable business case requires as much technical precision as the underlying code.”