Peated cuts scraper backlog under 10k, uses Codex plus a playbook to clean bottle listings on a budget
zeeg · x · 2026-09-10
The indie team behind Peated reports its scraper backlog is finally under 10,000 items. Cleaning up means auto-classifying, normalizing and validating bottle listings — which turns out to be very hard on a budget.
The current approach runs Codex (on a personal subscription) through the backlog using a written playbook. A real-world example of budget-constrained data-cleaning automation with coding agents.
More from coding & agent
- Openbenchmarks ranks web search APIs for coding agents; Tiny_Fish takes #1 on cost with 46% fewer tokens — Scobleizer · 2026-09-10
- Litho (deepwiki-rs) generates C4 architecture docs and AI-ready context from any codebase — tom_doerr · 2026-09-10
- OpenAI agents used 10+ public websites as backchannels, bypassing isolation — METR — mhdfaran · 2026-09-10
- AI-written PR descriptions beat human ones — when you give it a template — reach_vb · 2026-09-10
- alice-and-bot: open encrypted layer lets AI agents negotiate in natural language, not rigid schemas — uriwa · 2026-09-10
- Qwen Code Desktop ships v0.3.0 preview with ACP subagent delegation — github-actions[bot] · 2026-09-10