Newsletter
Jev Shows That Not Every AI Call Should Generate Text
Jev returns bounded choices and probabilities instead of prose. Its real lesson for product teams is where generation should end and ordinary software should take control.
Aviral Verma
Newsletter
Voice Agents Need Two Brains
Production voice agents need one loop for live conversation, another for reliable execution, and application-owned state between them.
AI
The 24/7 Hermes Agent Setup We Actually Use
Hermes stays online on a cloud server, while Codex work moves between our MacBook and 128GB Mac Studio.
Product Management
Loop Engineering: The Work Moves From Prompting to Control
Loop engineering shifts the work from prompting agents to designing triggers, durable state, verification, limits, and human gates. Here is where it works and where it breaks.
Newsletter
Your AI Moat Is the Learning Loop
Satya Nadella’s Reverse Information Paradox points to a real enterprise risk—but data leakage is only half the story. The deeper challenge is retaining what our teams teach AI.
ai-product-management
Deploying the Stack: How to Host Your AI Prototype
A practical guide to taking AI-built prototypes beyond localhost: hosting, backends, databases, auth, and real-user readiness.
Newsletter
AI is making hardware expensive. Software is next.
AI infrastructure demand is already leaking into hardware prices through memory and storage. The next shock may be the AI subscriptions companies are building workflows around.
Newsletter
Stop Prompting. Start Delegating.
AI agents are moving from chat windows into real workflows. PMs now need to design delegation: memory, permissions, evaluation, orchestration, and accountability.
Newsletter
The Next AI Product Skill Is Designing the Loop
The next AI product advantage will not come from another AI button. It will come from designing the loop that turns model output into better work over time.
Newsletter
The Next AI Moat Is What the Product Is Allowed to Know
Model quality still matters. But the products that win will be the ones with the deepest context, the most useful memory, and the clearest permission layer around what agents can know and do.
Newsletter
AI Agents Are More Than Features. They Are a New Operating Model for Work.
AI agents are moving from demos into the operating layer of work. The product opportunity is designing how humans, agents, context, permissions, reviews, accountability, and economics work together.
Newsletter
Frontier Models Set the Ceiling. Local Models Set the Economics.
The next AI strategy question is not just which model is best. It is which model is economically right for this workflow.