AI fluency gaps within teams are the hardest part of building AI software
jacob_posel · x · 2026-09-07
Developer jacobposel argues the hardest part of building AI software is the huge diversity in AI fluency within teams and across businesses — with no correlation to industry, business model, size, or role. In the same company you'll find someone who refuses to open Claude Code and someone demanding support for Claude Code, Codex and Grokbot; someone who's never heard of MCP and someone needing an MCP gateway with per-user scopes; someone wanting out-of-the-box workflows and someone customizing every skill, policy, model and approval step.
More from coding & agent
- Designer fed up with AI-generated UI inconsistency plans BaseUI refactor with strict rules — tomjohndesign · 2026-09-07
- From low-code to 'woah code': the AI coding era's new meme — jxnlco · 2026-09-07
- Developer on Astra: code as unreadable as minified JS, but tolerable to boss around — Aryvyo · 2026-09-07
- Your LLM Gateway Holds the Keys: Rethinking LiteLLM Security for Action-Taking Agents — Technical_Map_2105 · 2026-09-07
- Zero Blender skills, one prompt, 40 minutes: recreating a game with Codex — FuSheng_0306 · 2026-09-07
- LLM-powered revival of Put-That-There brings speech and gesture window control to XR — twi_mar · 2026-09-07