Coding Agent Infrastructure Patterns
Summary
These articles collectively outline a reusable architecture for serious unattended coding agents. The exact stack differs, but the recurring infrastructure pattern is remarkably consistent.
Repeated patterns
1. Standardized isolated environments
- Ramp uses Modal sandboxes
- Stripe uses standardized devboxes
- In both cases, each run gets its own clean workspace and services
2. Pre-warming or snapshotting
- Ramp rebuilds and snapshots environments on a schedule
- Stripe keeps devboxes hot and ready in pools
- The general lesson: move setup cost out of the critical path
3. Rich internal context hydration
- Rule files scoped by directory or file pattern
- MCP or equivalent tool calling for docs, tickets, code intelligence, build state, and internal systems
- Pre-fetching likely useful context before the main agent loop starts
4. Deterministic wrappers around agent loops
- Ramp describes plugins and explicit safeguards around write timing and synchronization
- Stripe formalizes this as blueprints that mix deterministic nodes with agentic nodes
- The broader lesson is that reliability often comes from combining LLM judgment with fixed workflow code
5. Strong feedback loops
- Run local linting and checks before expensive CI
- Limit CI retries rather than looping forever
- Feed failures back into the agent in a structured way
6. Multi-surface UX
- Slack is a major entry point in both ecosystems
- Web UIs, PR comments, browser tools, and other clients all feed the same session or run state
- Agent systems become more powerful when they meet people where they already work
Open questions worth tracking
- How much determinism is ideal before an agent becomes too constrained?
- Which verification tools most improve end-to-end success rates?
- How important is multiplayer collaboration as these systems mature?
- Where is the best boundary between local and remote execution?