Reference: Team-Scale Coding Assistant
referencecoding-assistant
framework
Agent Framework
harness
Harness / IDE
memory
Memory
CC
claude-code-memory
retrieval
Retrieval / Vector Store
eval
Eval
observability
Observability / Tracing
sandbox
Sandbox / Code Execution
deployment
Deployment Target
mcp_servers
MCP Servers
Architectural notes
Reference architecture for a coding assistant deployed across a 30+ engineer team. Differs from the single-user setup: shared plugin marketplace, centralized observability + spend dashboards, eval gates in CI. Why these picks: - Shared Claude Code config + private plugin marketplace per team. - turbopuffer over pgvector because per-repo namespaces scale better. - Centralized Helicone dashboard for org-wide spend visibility. - CI eval gates on internal "code review correctness" golden set. Common gotchas: - Skill/plugin sprawl is the failure mode at team scale; curate quarterly. - Per-user spend caps prevent runaway costs from misconfigured agents.
Embed this stack
Show off your stack on your engineering blog or company page.
<iframe src="http://testserver/embed/stacks/coding-assistant-team" width="100%" height="380" frameborder="0" style="border: 1px solid #334155; border-radius: 8px;"></iframe>