Matt Pocock shares a swipe-scoring workflow to teach agents your writing style
mattpocockuk · x · 2026-11-22
Matt Pocock proposes a simple workflow for getting an agent to write in your style: build a 'scorer' app where the agent sends you example sentences to rate one at a time, Tinder-style (single 1-4 scores or pairwise comparisons); plan the article together, then work through it sentence by sentence so the agent can self-test style fit. His insight: AI optimizes around humans' tiny working memory — you judge one sentence at a time instead of whole-article flow.
Related event: Matt Pocock shares swipe-to-rate method for teaching AI your writing style(2 posts)→
More from coding & agent
- Stop Automating Everything: Why Humans Belong Inside the Agent Loop — dotey · 2026-11-22
- Grok Bot agents organized a 5,000-person summit in 6-7 months, vs the usual 18 — XFreeze · 2026-11-22
- One command adds a music-video generator plugin to Claude Code — AIandDesign · 2026-11-22
- Does the Next Run Improve? Community Weighs In on Chase's Knowledge Factory — hwchase17 · 2026-11-22
- Dev Gets Antigravity Account Banned After Using Its Provider Inside t3 Code — jeremyphoward · 2026-11-22
- Knowledge factory concept extended to computer use agents — hwchase17 · 2026-11-22