Philipp Schmid on X: "Here is how @SpotifyEng uses coding background agents for thousands of code migrations and what they learned: - Define desired verifiable end states explicitly, not strict todo steps. - Code examples improved output reliability. - Agent has access to 3 tools, verify, git and https://t.co/SlXpCk3nPt" / X
To view keyboard shortcuts, press question mark View keyboard shortcuts Post See new posts Conversation Philipp Schmid @_philschmid Follow Here is how @SpotifyEng uses coding background agents for thousands of code migrations and what they learned: - Define desired verifiable end states explicitly, not strict todo steps. - Code examples improved output reliability. - Agent has access to 3 tools, verify, git and bash. - “verify” tool runs formatters, linters, and tests > AGENTS md. 3:11 PM · Dec 29, 2025 · 89.8K Views 17 63 948 1.1K Relevant View quotes Post your reply Reply Philipp Schmid @_philschmid · Dec 29, 2025 Background Coding Agents: Context Engineering (Part 2) | Spotify Engineering From engineering.atspotify.com 1 9 55 9.2K logan Wengfeng @love_deepseek · Dec 29, 2025 Fix Gemini 3 pro Agentic calling error 1 1 3.8K Philipp Schmid @_philschmid · Dec 29, 2025 Hey, can you send a DM or comment here what you mean? 3.4K Rituraj @RituWithAI · Dec 30, 2025 "Define desired end
@_philschmid: Here is how @SpotifyEng uses coding background agents for thousands of code migrations and what they learned: - Define desired verifiable end states explicitly, not strict todo steps. - Code examples improved output reliability. - Agent has access to 3 tools, verify, git and bash. - “verify” tool runs formatters, linters, and tests > AGENTS md.
Explore this link on the map →saved by
related reading
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- Coding Is No Longer the Constraint: Scaling Developer Experience to Teams and Agents at Spotify | Spotify Engineeringengineering.atspotify.com
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Best practices for coding with agents · Cursorcursor.com
- Best practices for using AI coding Agents | Augment Codeaugmentcode.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Designing agentic loopssimonwillison.net
- Cookbookcookbook.openai.com
- How I'm using coding agents in September, 2025 — Massively Parallel Procrastinationblog.fsck.com
- Agentic Coding Ascension Notes – Machine Learning (Theory)hunch.net
- Swimm - Swimmswimm.io