Enterprise AI coding fails on people, docs and process — not the codebase
_jaydeepkarale · x · 2026-11-16
jaydeepkarale argues the codebase is the least problematic part of enterprise AI coding — the real blockers are people lacking knowledge, poor documentation, and horrible processes.
The quoted post notes you can't just ask AI to write code and push to production in large enterprise codebases: established coding standards, shared files, dependencies, predefined workflows and architectural patterns all require deep understanding, which is why software developers aren't going anywhere anytime soon.
More from coding & agent
- User's $300 subscription generated $7,492 of usage — 25x value on Codex and Claude — theteknosaur · 2026-11-16
- Your agent's inference endpoint sees all its memory: treat it as a data boundary — krishnan · 2026-11-16
- Dev ships a gladiator management game built entirely with Claude Code — StarDrifterG · 2026-11-16
- Rust rewrite of mcbench-lite cuts first start from ~71s to under 1s with AI coding — adonis_singh · 2026-11-16
- Solo dev ships his son's game idea to iOS and Android for under $300 — morganinuk2 · 2026-11-16
- Anthropic: agent memory works best by forgetting selectively—notes beat 400+ archives 4x in Pokémon Red — The Decoder · 2026-11-16