Drew Breunig: most agentic work will become workflows — find desire paths, then pave them
dbreunig · x · 2026-11-05
In an Agentic AI Foundation essay, Drew Breunig argues most agentic work will eventually become code-based workflows: 'find the desire paths, then pave them.' His example: a friend had Opus 4.5 daily combine Strava pace, calendar meetings, and ferry schedules to compute the latest departure for his bike commute — useful, but the model's real value was scoping, designing, and refining the task, not running it forever. Agents excel at discovering and defining repeated tasks; once stable, those tasks should be extracted into code workflows, leaving foundation models for the open-ended parts.
Related event: Drew Breunig: Most Agent Work Will Solidify into Coded Workflows(3 posts)→
More from coding & agent
- Dev finds pi coding tool defaults to Opus 4.8 on a fresh install — lucasmeijer · 2026-11-05
- Kylon puts whole teams and agents in shared rooms, with a Neon branch per app draft — jefrankle · 2026-11-05
- "Evals > vibes": agent workflow debates are just guessing without eval stats — annetgriffin · 2026-11-05
- OpenAI hackathon winner joins YC, launches Raven, an agent-first phone — ycombinator · 2026-11-05
- Open-source Cicada brings real-time translation and AI meeting notes to any Mac call, free 50h/month — dotey · 2026-11-05
- IBM launches AI coding assistant named "Bob", devs can't stop laughing — zeeg · 2026-11-05