depthfirst shares how it built a secure agent-first cloud dev environment
andreamichi · x · 2026-11-07
depthfirst published an engineering writeup of its secure cloud dev environment for AI agents: each developer gets a persistent devbox, and each task gets its own application stack, database, and workflow state so agents work in parallel.
Key points:
- Agents work best when they can verify their own work — the environment gives them the full loop: change code, reproduce behavior, inspect results, retry, covering app, database, background workflows, and jobs
- Why own it instead of using commercial cloud-agent offerings: control (your whole system must run inside it) and portability (works out of the box)
- The team frames this as the infrastructure side of the verification idea poteto has been talking about
A useful reference architecture for teams safely running coding agents against their own codebases.
More from coding & agent
- LLM agent re-architects models during training: algorithmic reasoning 55%→84%, AIME 64%→71% — lateinteraction · 2026-11-07
- AI won't replace designers: a deep dive into the Quest team's AI iOS design workflow — JiliJeanlouis · 2026-11-07
- Developer stumbles into an accidentally recursive SKILL.md that tests itself — holdenmatt · 2026-11-07
- Anthropic details agent memory: "dreaming" helps Claude fix mistakes and organize knowledge — RLanceMartin · 2026-11-07
- TechSEO Connect talk: write SOPs as skills and use small commits when vibe coding — lilyraynyc · 2026-11-07
- Conductor AI agent orchestrator shuts down, alternatives compared — vikvang1 · 2026-11-07