Vibe-Coding Throwaway Tools: A TPM's New Habit
Frontier models now build a working tool in one prompt. Here's how I turn that into faster release planning, risk tracking, and cleaner stakeholder syncs.
27 articles on AI tools, agents and the craft of technical program management, written by Gianfranco Mileo, TPM at Google.
Frontier models now build a working tool in one prompt. Here's how I turn that into faster release planning, risk tracking, and cleaner stakeholder syncs.
Three stories this week point to the same uncomfortable truth: enterprises are shipping AI agents faster than they can govern them. Here's what TPMs need to do about it.
Stampli cut launch hours by 68% with AI. Here's how I'm using the same class of tools to compress the grunt work in real TPM workflows — without the hype.
Two decades of capacity planning assumed humans drive traffic. Autonomous agents don't play by those rules — and your autoscaler is about to find out the hard way.
Anthropic just turned Claude Code's auto mode on by default. AI agents are learning to lie. And nobody's talking about how these two trends collide. Here's what your team needs to prepare for.
Google's new Gemini Managed Agents with hooks aren't a demo toy. Here's exactly how I'm wiring them into release planning, risk tracking, and retros this week.
Epoch and METR just dropped MirrorCode, a benchmark for week-long programming tasks. This is the metric that actually matters for engineering teams — and here's why.
Four enterprise surveys just dropped and they all say the same thing: we're deploying AI agents faster than we can secure, evaluate, or afford them. Here's what TPMs need to do now.
Gemini's new background agents and the old-school DRI model are a better combination than either alone. Here's how I'm wiring AI into real TPM workflows right now.
Gemini 3.5 Flash can now operate a computer — clicking, typing, navigating UIs. Here's how it works and why your test automation and internal tooling roadmaps just changed.
Everyone's chasing agentic ROI, but Ford quietly told us the truth: AI without deep domain expertise ships broken products. Here's what TPMs should actually prepare for.
GPT-5 just solved a 3-year-old immunology mystery. Meanwhile, I'm using agentic AI to kill the busywork that eats every TPM's week. Here's what's real and what's hype.