A $49 Slack bot + 15 Claude Code commands turn shared company context into a working AI org
aakashgupta · x · 2026-10-14
After interviewing CPOs running AI-native product orgs (Laurel's Jiaona Zhang, OLX's Mikhail Shcheglov), the author argues most company AI bots fail because firms skip documenting how the company works and don't share skills—only context-free wiki Q&A.
Key points:
- Sharing skills alongside context is the move almost nobody makes; run-only skills let teammates get the work without the underlying setup
- Case study: a bot read 12 months of sponsor emails, found 3 prospects, and turned one Slack line into a PRD, prototype plan, engineering spec, and task list in 3 minutes, with human approval
- The screenshot shows the full "Company OS": sourced answers, 75/110 weekly active users, $57.48 monthly model cost, 3 cents median answer cost, and team context-sharing scores
He spent 10 days productizing it: a Slack bot plus 15 Claude Code commands with review gates, roles/permissions, a rollout dashboard, and a 110-person sample company—$49 one-time, about an hour to set up. Honest caveat: intake is the bottleneck; without real skills and context from the team, answers stay generic.
Related event: Building a $49 Company OS with Claude Code and Slack(2 posts)→
More from coding & agent
- DeepSeek V4.1 Rates Itself Highly—Then Distrusts Its Own Subagents — teortaxesTex · 2026-10-14
- Dev ports Wright CAD workflow to ChatGPT Desktop, wiring Codex to SteveCAD for 3D design — burhop · 2026-10-14
- Dev one-shots RightClick-Utilities: open-source Windows 11 right-click menu for video compression and audio removal — rms80 · 2026-10-14
- Gemini CLI doesn't support Gemini 4 Argon yet; workaround via '-m gemini-4-argon' — peterjliu · 2026-10-14
- Gemini 4 Argon 'thinks' surprisingly little while doing accurate multi-agent research — ChrisUniverse · 2026-10-14
- Cramer: annotate interface constraints in comments or agents will stomp over them — zeeg · 2026-10-14