11 posts
In six months, skills turned a single Claude chat into my personal app store. How to replace SaaS with your own skills, and why it works beyond developers.
Why 76% of AI agent tasks fail on the first try - not because of the model, but because of the harness - and what I keep in my stack.
Stripe gets 91% of recommendations not because of marketing. The coding agent has become a distribution channel - your product is either visible or doesn't exist.
How to design a pipeline of autonomous subagents for mass prompt generation. 4 hours, 9 decisions, 8 bugs caught by an agent
Stripe launched a payment protocol for AI agents, Visa joined in. Breaking down three layers of the agent internet and 8+ protocols shaping it.
Two weeks of research, 20+ frameworks in 6 categories - from BMAD to QuintCode. Comparison table, maturity model, expert quotes from practitioners.
A 5-level framework: from manual control to self-adaptation. Real-world examples and a quick self-diagnostic.
Agent Teams vs subagents - with prompts and real cases. When a team of 5 agents wins, and when it doesn't
Breaking down the AI demo agent stack with voice and screen sharing - from open-source components to cost math and PM use cases
A Claude Code agent sent an internal message to a public channel with 6k subscribers. Breaking down the incident and sharing a safety checklist for autonomous AI agents.
How I migrated prodfeat.ai from React to Astro 5 and boosted my SEO score by 34% using 10 AI agents