Agent coding's new bottleneck is decision-making, and chat UIs can't keep up
_AustinCalvert_ · x · 2026-10-05
Developer @backnotprop argues that with agent coding, decision-making has become the bottleneck.
- His day is now mostly answering questions, reviewing prototype variants, and judging outputs rather than writing code.
- The chat interface is a terrible surface for staying in the loop: give an agent one instruction and it does 1000 things, throwing random questions and review artifacts at you — and two hours in, it reminds you decisions X, Y, Z are still pending, buried somewhere in the chat.
- His workaround: ask the agent to generate an HTML or Markdown review doc that consolidates context and pending decisions.
- His takeaway: the more AI does across systems and integrations, the more the human-AI interface needs to be redesigned around decision flows, not chat.
More from coding & agent
- Stop wasting your AI subscription compute: use the smartest model only when it matters — TheChuckTone · 2026-10-05
- Free AI Engineering course covers foundation models, evals, prompt engineering and security — Negative_War_65 · 2026-10-05
- ₹40,000 web dev bootcamp in 2026? Claude and Cursor already write full-stack apps — _jaydeepkarale · 2026-10-05
- Most coding agents today are hand-rolled loops, not framework abstractions — arpit_bhayani · 2026-10-05
- Indie dev tinyfool starts prototyping his next game, now stress-testing game logic engine — tinyfool · 2026-10-05
- Five questions to ask before letting an AI agent call a state-changing tool in production — ainexfinder · 2026-10-05