3 articles
Slack Engineering explains how they manage context across long-running, multi-agent security investigations, using a Director's Journal, Critic's Review, and Critic's Timeline instead of accumulating raw message history.

Slack's Security Engineering team deployed a multi-persona agent system — Director, Expert, and Critic agents working together — that performed over 7,500 security investigations and 500,000 tool calls in its first quarter, with structured outputs reducing hallucinations.

Slack describes deploying AI-powered developer tools that save 10,000+ hours of engineering time yearly. Their internal AI assistant has been generally available for five months with 4,000+ monthly chat-turns and 70%+ positive satisfaction across the engineering organization.


Slack Engineering explains how they manage context across long-running, multi-agent security investigations, using a Director's Journal, Critic's Review, and Critic's Timeline instead of accumulating raw message history.

Slack's Security Engineering team deployed a multi-persona agent system — Director, Expert, and Critic agents working together — that performed over 7,500 security investigations and 500,000 tool calls in its first quarter, with structured outputs reducing hallucinations.

Slack describes deploying AI-powered developer tools that save 10,000+ hours of engineering time yearly. Their internal AI assistant has been generally available for five months with 4,000+ monthly chat-turns and 70%+ positive satisfaction across the engineering organization.