
Collecting knowledge fails because of people. So we built an AI colleague.
Frieda reads Confluence, Slack and ten repositories, reviews every pull request and never answers without a source. How she is built — and where we deliberately stopped.
Tag archive

Frieda reads Confluence, Slack and ten repositories, reviews every pull request and never answers without a source. How she is built — and where we deliberately stopped.

On Tuesday you told the assistant that the migration script must never touch the staging database. It...
Как снизить коллизии в данных, когда три сервиса работают с разными БД, но используют одну и ту же...

Codex made Item a wire type and thread/fork a protocol call. Pi gave every session entry a parentId. Claude Code compresses the transcript in five stages.

Introduction Over the weekend of August 8 and 9, Zerops ran The Zerops Challenge in...

Reliable audio hardware verification is a daily prerequisite for remote teams, streaming setups,...
Your next AI task shouldn't have to start from zero. Past materials, results, and decisions should be...

The short version What we built: ELN Billing, a platform that consolidates billing for...
The multi-tenant SaaS checklist: seven decisions, what each costs if you defer it, and the one everyone worries about far too early.
Your LLM Isn't Bad At Math. It Was Never Doing Math In The First Place. In a tutorial, an...
When a Feature Looks Simple, Write Down Its Invariants First One of the things I've...

A while back I wrote that most "AI agents" are just pipelines in a trench coat — deterministic...