Matt Vollmer
59553b8df8
Adds a new **Enable Coder Agents** section to the Early Access doc explaining how to activate the `agents` experiment flag via `CODER_EXPERIMENTS` or `--experiments`. ## Changes ### `docs/ai-coder/agents/early-access.md` - New **Enable Coder Agents** section with env var and CLI flag examples. - Note that the `agents` flag is excluded from wildcard (`*`) opt-in. - Quick-start checklist: dashboard → Admin → configure provider/model → start chatting. - Link to GitHub issues for feedback. ### `docs/ai-coder/agents/index.md` - Updated **Product status** from "internal preview" to "Early Access" with a link to the early-access page for enablement instructions.
3.0 KiB
Early Access
Coder Agents is available through Early Access for the community to evaluate while the product is under active development. Participation comes with important expectations and limitations described below.
What Early Access includes
Early Access is a collaborative evaluation period between Coder and participating customers. It includes:
- Direct collaboration with the Coder product team — work with Coder engineers and product managers to share feedback, discuss use cases, and influence product direction.
- Architecture and functionality documentation — basic documentation covering how Coder Agents works and how it integrates into existing deployments.
- Feedback sessions — periodic check-ins with the Coder team to discuss real-world usage.
- Early exposure to new capabilities — access to new features or experimental functionality before public release.
What Early Access does not include
Early Access is not a production-ready offering. It does not include:
- Formal support coverage — no SLA-backed support.
- Stability guarantees — features and behavior may change without notice.
- Production readiness guarantees — functionality may not yet meet the reliability or scalability expectations of a GA feature.
- Complete documentation or tooling — operational guidance may be incomplete and will evolve.
- Long-term compatibility guarantees — APIs, configuration models, or workflows may change before General Availability.
Feature scope
Functionality available during Early Access may be a subset of planned capabilities. Some features may be incomplete, experimental, or subject to redesign.
Enable Coder Agents
Coder Agents is experimental and must not be deployed to production
environments. It is gated behind the agents experiment flag. To enable it,
pass the flag when starting the Coder server using an environment variable
or CLI flag:
CODER_EXPERIMENTS="agents" coder server
# or
coder server --experiments=agents
If you are already using other experiments, add agents to the
comma-separated list:
CODER_EXPERIMENTS="agents,oauth2,mcp-server-http" coder server
Once the server restarts with the experiment enabled:
- Navigate to the Agents page in the Coder dashboard.
- Open Admin settings and configure at least one LLM provider and model. See Models for detailed setup instructions.
- Developers can then start a new chat from the Agents page.
Licensing and availability
Features provided during Early Access may become paid licensed features at General Availability. Participants will receive reasonable advance notice before:
- Coder Agents reaches General Availability
- Early Access functionality transitions to a paid offering
Providing feedback
Participants are encouraged to share workflow feedback, feature requests, performance observations, and operational challenges. Feedback channels are coordinated directly with the Coder product team.