Post-Training: When a Specialist Beats a Bigger ModelI鈥檝e been experimenting with post-training lately, and I think it will become a much more common part of building AI products. A software engineer, an SRE, and a financial compliance officer each know5 min read路blog.niradler.comNov 4
Coding Agents Are Reshaping the SDLCImagine a developer handing five tasks to coding agents before starting their own work. Each agent needs code, an isolated environment, and somewhere to submit a change. Every push may start several C6 min read路blog.niradler.com1Nov 4
Version-controlling AI agent assets with git-skill and GitHubYour team has 14 versions of the same code review skill across 5 repos, with no way to sync them. when one improves, the others don't. drop a folder in .claude/skills/ and pray nothing drifts. source12 min read路blog.niradler.comMay 25
Postgres Already Is Your BackendAI agents are unreasonably good at writing SQL. They get specific error messages, fix their own mistakes in one retry, and can introspect query performance with EXPLAIN ANALYZE before you even ask. No7 min read路blog.niradler.comMay 4
Your Next Startup: The Agentic Workflow Enginen8n has over 400 integrations. Zapier claims 7,000+. Every single one was hand-built, tested against a moving API, and will eventually break when that API ships a v2. The entire workflow automation in7 min read路blog.niradler.comMay 3