Capability 01 of 04 · Development

Coding Agent Usage

How your team uses AI coding assistants - from autocomplete to autonomous agent fleets.

5
maturity levels
15
practices
15
guides
L1 · Stage 01Assisted
Criteria - what to measure
  1. 01At least one AI coding assistant (Copilot, Cursor, Claude Code) is installed and active for at least one developer
  2. 02AI autocomplete or chat is used at least once per week by the team
  3. 03Developers have access to AI chat in their IDE sidebar
  4. 04Team has experimented with AI-assisted code generation on non-critical tasks
L2 · Stage 02Delegated
Criteria - what to measure
  1. 01Agents operate in multi-step agentic mode (edits without per-step approval)
  2. 02At least one agentic IDE (Cursor, Windsurf, or Claude Code) is used by 50%+ of the team
  3. 03CLAUDE.md, .cursorrules, or equivalent agent instruction file exists in 100% of active repositories
  4. 04Developers use two or more AI tools in parallel (e.g., Copilot + Claude Code)
  5. 05Agent instruction files are reviewed and updated at least quarterly
  6. 06Agent autonomy is bounded by a written permission ruleset (deny/ask) committed to the repo, not by per-prompt clicking
L3 · Stage 03Systematic
L4 · Stage 04GovernedMost teams aim here
Criteria - what to measure
  1. 01Unattended agents execute tasks without developer presence
  2. 02Agents are invocable from at least two channels (Slack, CLI, Web, PagerDuty)
  3. 03Developers routinely run several agent sessions concurrently, against a documented span-of-control limit
  4. 04Agent task completion rate without human intervention exceeds 60%
  5. 05Agent invocation produces a PR within a defined SLA (e.g., under 30 minutes for standard tasks)
L5 · Stage 05Self-improving
Criteria - what to measure
  1. 01Multi-agent orchestration system (planner-worker hierarchy) is in production
  2. 02The agent fleet scales past what a single team could supervise, bounded by compute and review capacity rather than by tooling
  3. 03Agent fleet produces 1,000+ commits per week without manual dispatch
  4. 04Planner agents decompose epics into tasks and assign to worker agents autonomously
  5. 05Agent fleet self-recovers from failures without human escalation for 90%+ of error cases

Which level is your team at in Coding Agent Usage?

The criteria above are what we check in a facilitated assessment. Run it yourself to place this capability, see which gates you have passed, and compare it against the other 3 in Development.

Start the assessment →