## Summary Addresses 106 of the 113 conflicts between the docs and the code that the November audit of `main` found: 102 are fixed and 4 have an interim docs fix. Every finding was re-checked against the code before it was fixed. Most fixes are docs-only. Three are small code fixes where the docs described the intended behavior and the code was wrong, each in its own commits so it can be split out. No change in this PR alters template build or agent behavior. ## Changes Fixes by area (finding counts): templates 28, install 13, integrations and monitoring 13, auth and security 12, networking 11, Coder Agents 9, AI governance 7, reference 7, workspaces 6. Code fixes. Each needs a look from the code owner. If an owner prefers not to take one, drop its commits and I will change the docs to describe the current behavior instead. | Commits | Change | Risk to check | |---------|--------|---------------| | `fix: keep built-in listener defaults in packaged coder.env`, and three follow-up commits | `coder.env` comments out `CODER_HTTP_ADDRESS=` and the three `CODER_TLS_*` lines, so an untouched package install listens on `127.0.0.1:3000` as the docs say. Only the `CODER_HTTP_ADDRESS=` line changed behavior. The TLS options default to empty, so commenting them out is for consistency. The Lima examples rewrite the commented line and fail if the line is not found. A test compares every option that the file sets against the built-in defaults. | The deb and RPM packages were not built or installed. Every released package through v2.39.0 ships the empty line, and upgrades keep an existing file (`config\|noreplace`), so the upgrade pages now say how to fix it. | | `fix(cli/clilog): accept log sinks that are all disabled`, and three follow-up commits | `--log-human=/dev/null` with no other log location no longer fails with "no loggers provided". It is the documented way to disable logging. An empty location still fails with that error when no other sink is set, as before. | Behavior change: with `/dev/null`, the server and the provisioner daemon can start with no log output. | | `fix(cli): detect CODER_PROC_PRIO_MGMT by presence`, and a comment follow-up | Log line only. With the variable set to an empty value, the agent now logs that process priority management is enabled, which is what `agentexec` already does. No detection or behavior change. | Low. | Two option descriptions in `codersdk/deployment.go` are corrected, with the CLI reference, configuration reference, and golden files regenerated: the default quiet hours schedule (the max deadline is the quiet hours window on the next day that the template's autostop requirement applies) and `--experiments` (`*` opts in to the experiments marked safe, also in `enterprise/cli/provisionerdaemonstart.go`). ### Code fixes that were reverted after review Two code fixes from the first version of this PR are reverted in the branch. The net diff has no change under `agent/` or `coderd/`. The docs now describe what the code does, and both issues stay open for the owner. - **`error` merge strategy for `coder_env` (DOCS-1669).** The fix made `merge_strategy = "error"` fail whenever a name was set twice, whatever the resource order. Existing template versions that pair an `error` entry with a later `replace` or `append` entry would start to fail every build after `terraform apply`. That is a breaking change that needs its own PR and release note. The fix and its tests are in `dff8e7c6ce` and can be cherry-picked. `environment-variables.md` now says the check runs only when the `error` resource is processed. - **Nice value before the capability drop (DOCS-1687).** The fix let `coder agent-exec` apply a negative nice value by calling `setpriority` before it drops effective capabilities. The current order is deliberate: with the fix, any local process could run the agent binary with `--coder-nice=-20` when the binary has the `CAP_SYS_NICE` file capability. `process-priority.md` now says a nice value below the agent's own is not applied, and no longer tells admins to grant `CAP_SYS_NICE`. ## Not included Seven findings are left out. - DOCS-1629: covered by #31639. - DOCS-1703 and DOCS-1724: covered by #31980. - DOCS-1584, DOCS-1683, DOCS-1685, DOCS-1686: each needs an owner decision, and no neutral docs wording exists until that decision is made. The validation comment on each issue names the decision. Four fixes are interim, so their issues stay open: - DOCS-1600: the AI Gateway pages now agree that the legacy metric names are deprecated and "will be removed in a future release". The code still emits them, and its TODO names v2.37, which has shipped. The owner still needs to set the removal release. - DOCS-1689: the page now says **New Template** opens the builder only for users with the Owner role, because the page gates on read access to the deployment config. Whether Template Admins should get the builder is still open. - DOCS-1669 and DOCS-1687: docs-only for now. Refer to [Code fixes that were reverted after review](#code-fixes-that-were-reverted-after-review). ## Review notes - Claims that describe product intent and need an owner's yes: the Premium qualifier on per-organization workspace sharing (the API route has no license check, the dashboard needs multiple organizations), `organization` port sharing in OSS, the telemetry field list, and the `1-5` cron range in the prebuilds schedule example. - Not run end to end: the PostgreSQL TLS procedure on a cluster, the OpenShift and air-gapped examples, the BSD `date` and `tar` forms on macOS, the Windows command on the multiple Kubernetes clusters page, and the keep-alive script in `docs/reference/index.md` (only its comparison logic was run, against sample values). Nothing was checked on a live deployment. - Likely merge conflicts with open PRs: #31990 (`mcp-server.md`, `feature-stages.md`, `docker-in-workspaces.md`), #31982 (`workspace-management.md`), #31980 (`health-check.md`), #31977 (`manage-provisioner-jobs.md`), #31869 (`airgap.md`), #30486 (`add-envbuilder.md`), and #31326 and #31531 (`codersdk/deployment.go` and generated files). ## Testing - `make pre-commit` (gen, fmt, lint, slim build), before the PR opened and again after the review changes. - `go test` for `./cli/clilog/...`, `./codersdk/`, `./cli/` (`TestServer`, `TestAgent`, and golden files), and `./enterprise/cli/` (provisioner, server, and help golden files). `./agent/agentexec/...` and `./coderd/provisionerdserver/...` pass after the reverts. Linux only. CI covers macOS and Windows. - The `coder.env` test fails against the file on `main` and passes against the new one. It reads the file with `godotenv`, which accepts CRLF line endings. - An empty `CODER_HTTP_ADDRESS=` was confirmed end to end with a full build of the server (output below). - The new `sed` and `grep` lines in the Lima examples were run with GNU tools against the old and the new form of `coder.env`. The Lima VMs were not started. - `--log-human=/dev/null` and `CODER_LOGGING_HUMAN=` were confirmed with the same build (output below). - `coder agent-exec --coder-nice=-5 -- echo` from a full build, as a non-root user: `coder-agent: failed to adjust niceness to -5 ...: permission denied` on stderr, the command output on stdout, exit code 0. - `postgres-ssl.md` rendered with the GitHub Markdown API: two ordered lists with three and five items, where `main` has six lists. - markdownlint, the table formatter, `make lint/emdash`, `make lint/docs-html`, `make lint/docs-manifest`, `make lint/docs-redirects`, `make lint/style-claims`, and Vale on the changed lines. - A doc-check self-review of the docs diff by four independent reviewers. It found six problems, which are fixed. The accuracy and coverage lenses ran on every area. The language and structure lenses ran in full on only part of the diff. <details> <summary>Test and terminal output for the code fixes (Linux)</summary> ```console $ go test ./codersdk/ -run TestPackagedCoderEnvKeepsDefaults -count=1 -v --- PASS: TestPackagedCoderEnvKeepsDefaults (0.00s) ok github.com/coder/coder/v2/codersdk 0.071s $ go test ./cli/clilog/ -run TestBuilder -count=1 -v --- PASS: TestBuilder (0.00s) --- PASS: TestBuilder/NoSinks (0.00s) --- PASS: TestBuilder/NoSinks/JSONDevNull (0.00s) --- PASS: TestBuilder/NoSinks/StackdriverDevNull (0.00s) --- PASS: TestBuilder/NoSinks/NoConfiguration (0.00s) --- PASS: TestBuilder/NoSinks/HumanDevNull (0.00s) --- PASS: TestBuilder/WithHuman (0.00s) --- PASS: TestBuilder/WithFilter (0.00s) --- PASS: TestBuilder/WithJSON (0.00s) --- PASS: TestBuilder/Verbose (0.00s) --- PASS: TestBuilder/FromDeploymentValues (0.01s) --- PASS: TestBuilder/FromDeploymentValues/Defaults (0.00s) --- PASS: TestBuilder/FromDeploymentValues/EmptyHumanEnv (0.00s) --- PASS: TestBuilder/FromDeploymentValues/Override (0.00s) ok github.com/coder/coder/v2/cli/clilog 0.171s $ TMPDIR=$HOME/.cache/agentexec-tmp go test ./agent/agentexec/... ./coderd/provisionerdserver/... -count=1 ok github.com/coder/coder/v2/agent/agentexec 4.236s ok github.com/coder/coder/v2/coderd/provisionerdserver 2.404s # Full build of the server (go build ./cmd/coder). An empty value stops it before it connects to the database. $ CODER_HTTP_ADDRESS= coder server --postgres-url 'postgres://127.0.0.1:1/x?sslmode=disable' Encountered an error running "coder server", see "coder server --help" for more information error: TLS is disabled. Enable with --tls-enable or specify a HTTP address # With the variable unset, the server passes that check and goes on to the database. $ coder server --postgres-url 'postgres://127.0.0.1:1/x?sslmode=disable' 2026-11-13 02:19:41.901 [warn] ping postgres: retrying error="dial tcp 127.0.0.1:1: connect: connection refused" try=11 Encountered an error running "coder server", see "coder server --help" for more information error: connect to postgres: connect to postgres: unable to connect after 11 tries; last error: dial tcp 127.0.0.1:1: connect: connection refused # An empty log location with no other sink still stops the server. $ CODER_LOGGING_HUMAN= coder server --postgres-url 'postgres://127.0.0.1:1/x?sslmode=disable' Encountered an error running "coder server", see "coder server --help" for more information error: make logger: no loggers provided, use /dev/null to disable logging # /dev/null passes the logger check. The server prints no log lines and goes on to the database. $ coder server --log-human=/dev/null --postgres-url 'postgres://127.0.0.1:1/x?sslmode=disable' Encountered an error running "coder server", see "coder server --help" for more information error: connect to postgres: connect to postgres: unable to connect after 11 tries; last error: dial tcp 127.0.0.1:1: connect: connection refused ``` </details> ## Linear Fixes DOCS-1583, DOCS-1585, DOCS-1586, DOCS-1587, DOCS-1588, DOCS-1589, DOCS-1590, DOCS-1591, DOCS-1592, DOCS-1593, DOCS-1594, DOCS-1595, DOCS-1596, DOCS-1597, DOCS-1598, DOCS-1599, DOCS-1601, DOCS-1602, DOCS-1603, DOCS-1604, DOCS-1605, DOCS-1606, DOCS-1607, DOCS-1608, DOCS-1609, DOCS-1614, DOCS-1618, DOCS-1619, DOCS-1620, DOCS-1624, DOCS-1635, DOCS-1639, DOCS-1644, DOCS-1651, DOCS-1652, DOCS-1653, DOCS-1654, DOCS-1655, DOCS-1656, DOCS-1657, DOCS-1658, DOCS-1659, DOCS-1660, DOCS-1661, DOCS-1662, DOCS-1663, DOCS-1664, DOCS-1665, DOCS-1666, DOCS-1667, DOCS-1668, DOCS-1670, DOCS-1671, DOCS-1672, DOCS-1673, DOCS-1674, DOCS-1675, DOCS-1676, DOCS-1677, DOCS-1678, DOCS-1679, DOCS-1680, DOCS-1681, DOCS-1682, DOCS-1684, DOCS-1688, DOCS-1690, DOCS-1691, DOCS-1692, DOCS-1693, DOCS-1694, DOCS-1695, DOCS-1696, DOCS-1697, DOCS-1698, DOCS-1699, DOCS-1700, DOCS-1701, DOCS-1702, DOCS-1704, DOCS-1705, DOCS-1706, DOCS-1707, DOCS-1708, DOCS-1709, DOCS-1710, DOCS-1711, DOCS-1712, DOCS-1713, DOCS-1714, DOCS-1715, DOCS-1716, DOCS-1717, DOCS-1718, DOCS-1719, DOCS-1720, DOCS-1721, DOCS-1722, DOCS-1723, DOCS-1725, DOCS-1726, DOCS-1727 Part of DOCS-1600, DOCS-1689, DOCS-1669, DOCS-1687 <details> <summary>Decision log</summary> ### Scope - One PR for all findings, as agreed with the reviewer. The code fixes are separate commits so an owner can ask for any of them to move to its own PR. Nothing in the PR is a breaking change, so the title has no `!`. - A finding was skipped only when an open PR already covers it, or when every available wording would assert an undecided product behavior. - Each validation comment on the Linear issues records the evidence, the corrections to the original finding, and what was not verified. ### Docs or code - The default was a docs-only fix that describes what the code does. - A code fix was chosen when the docs describe a behavior the code plainly intended and the code change is small and testable: the packaged env file, the log sink check, and the log line for the environment variable presence check. - The `error` merge strategy and the nice value ordering started as code fixes and went back to docs-only after review. The first breaks existing template versions. The second weakens a deliberate security ordering. - The SCIM `userName` finding (DOCS-1609) took the docs path. The handler is unchanged. ### Wording choices worth a second look - `feature-stages.md` says `--experiments=*` enables only the experiments marked safe, and points to the "Get safe experiments" API. It does not list the other experiments, because the list would drift and those experiments are hidden on purpose. The `--experiments` flag help now says the same. - `agent-metadata.md` replaces the writes-per-second formula with a description of the batcher (each server replica writes one statement every 5 seconds, or sooner at 500 entries). - `extending-templates/index.md` no longer calls `startup_script` deprecated. The provider documents it as an alias for a `coder_script`. - `postgres-ssl.md` separates client verification from server verification, so the server verification steps work alone. - `rpm.md`, `upgrade.md`, and the 2.29 to 2.34 ESR upgrade page explain the empty `CODER_HTTP_ADDRESS=` line that older packages shipped, because upgrades keep the old file. The behavior changed in v2.34.0 with the serpent upgrade in #24926. - The keep-alive script in `docs/reference/index.md` reads the current deadline and skips the request when it is already later. The comparison is on text, so it applies only when the API returns a UTC timestamp, which needs the database to use the UTC time zone. Otherwise the script sets the deadline on every pass, as it did before, and the page says so. - `external-auth.md` anchors the new GitHub Enterprise regex example. The older unanchored examples on that page and on `git-providers.md` are not changed here. ### Self-review findings that were rejected - "The builder opens for Template Admins": the Templates page needs a successful deployment config read, which the Template Admin role does not have. - "Organization Admins can set AI model prices": the price write authorizes against a site-level object, which organization-scoped grants do not match. - "The provisioner chart sets no default resources": `helm/libcoder/templates/_coder.yaml` applies 2000m and 4096Mi when `coder.resources` is empty. ### Automated review, round 1 The `coder-agents-review` app left 45 findings on `8853332`. Fixed: the two reverts above, the anchored regex, the `coder.env` follow-ups (Lima examples, upgrade notes, a comment in the file, and a test that covers every option in the file), the clilog change, the two option descriptions, and the docs findings (CORS behavior, token lifetime example, keep-alive script, agent metadata, refresh token errors, `switch` form type, `dbcrypt` skip list, and a stray line in a YAML example). Declined, with the reason on each thread: - Refactoring the `agentexec` logging and renaming its log field: not related to a docs conflict. - Rewording the "process priority management not enabled (linux-only)" log message: the docs quote the message, and the wording predates this PR. - Problems in code and docs that this PR does not change (the `Capabilities` subtest, the Helm values comment, the AWS provider path in `airgap.md`, and others in the review's out-of-scope list). ### Automated review, round 2 The app left 14 new findings on `04925bd`, and accepted the three declined threads on `cli/agent.go`. All 14 are fixed. The main one: the round 1 change that removed the "no loggers provided" error went too far, because an empty log location would then start a server with no logs. The error is back for every case except `/dev/null`. Reported by the app as out of scope and not changed: the swagger annotation for `GET /api/v2/experiments/available` declares an array, but the handler returns an object with a `safe` array. Three Storybook fixtures keep the old `--experiments` description. ### Automated review, round 3 The app confirmed that all round 2 findings are fixed, and left 10 small findings on `f55cb6d` (8 P4, 2 Nit). All are fixed: the TLS condition and the release range in the `coder.env` notes, one place for the `/dev/null` rule in `clilog`, two test cases, a clearer test failure, and the CPU example in `agent-metadata.md`. ### Automated review, rounds 4 and 5 Round 4 left one P4 on `8fffb38` (name the `--trace` option in the logging note), which is fixed. Round 5 on `2ce754e` reports no new findings and says every earlier finding is fixed or closed. The app did not post an approval: it leaves its out-of-scope items and the code fixes to a human reviewer. Two threads on `cli/agent.go` stay open on purpose for the code owner. ### Doc-check review The doc-check workflow left 12 comments on `2ce754e` (10 blocking, 2 suggestions). All are fixed in `c888885`: "refer to" or "visit" in place of "see" for cross-references on the lines this PR added, the **New template** label as the dashboard shows it, one instruction per step in the server verification procedure of `postgres-ssl.md`, and two wording changes in `process-priority.md`. The `CAP_SYS_NICE` sentence keeps a short reason, which differs from the suggested text. The `coder-agents-review` app then reviewed that commit (rounds 6 and 7). Round 6 left two P4 findings, fixed in `30b2c79`: the `failed to adjust niceness` message is described once, in the troubleshooting entry, with where it appears, and the client verification steps in `postgres-ssl.md` render as one numbered list. Round 7 reports no new findings. `2a6035c` then softens one sentence from that fix, because the agent logs the stderr of devcontainer CLI commands. The app was not run again on that commit. ### Adjacent gaps found and not fixed here - `add-envbuilder.md` has the same `zip` command that `template-from-scratch.md` had. - `template-from-scratch.md` leaves the reader in `build/` after `cd $_`, before a step that runs from `template-tour`. </details> --- _Generated by Coder Agents on behalf of @nickvigilante._ --------- Co-authored-by: Ben Potter <me@bpmct.net>
17 KiB
title
| title |
|---|
| Getting started |
This guide walks platform teams and administrators through setting up Coder Agents, preparing your deployment, and running your first Coder Agent.
Prerequisites
Before you begin, confirm the following:
- Coder deployment running the latest release.
- Large language model (LLM) provider credentials: an API key for at least one supported provider (Anthropic, OpenAI, Google, Azure OpenAI, AWS Bedrock, OpenAI Compatible, OpenRouter, or Vercel AI Gateway).
- Network access from the control plane to your LLM provider. Workspaces do not need LLM access. Only the control plane does.
- At least one template with a descriptive name and description for the agent to select when provisioning workspaces.
- Admin access to the Coder deployment for configuring providers.
- Access to configure models in each organization where you configure models. The Organization Admin role and the Owner role include this access. A custom role with model configuration access also works.
- Organization membership for each user who uses Coder Agents. Every organization member can use Coder Agents by default. To restrict access, see Control who can use Coder Agents. Users also need read access to at least one model in the organization. New models are shared with the whole organization by default. See Manage model permissions.
Step 1: Configure an LLM provider and model
Important
Deployment administrators configure providers and deployment settings. Users with model configuration access in an organization configure that organization's models. Coder enables the edit controls for the organization that you select. Coder shows the deployment settings only to deployment administrators. Users with model access can view the relevant Models and Coder Agents pages. Users with Model Context Protocol (MCP) server access can open the MCP servers page.
To configure Coder Agents:
- Navigate to Admin settings > AI and select Providers.
- Add or update a provider with its credentials and upstream endpoint, then save it.
- Navigate to Admin settings > AI > Models.
- Select the correct organization. Coder shows the organization picker when you can access more than 1 organization.
- Select Add model and configure at least one model with its identifier, display name, and context limit.
Coder makes the first model of an organization the default model. To change the default later, open a model and select Set as Coder Agents default model, or pick a model in the Default model row under Admin settings > AI > Coder Agents > Organization settings.
Each organization has its own model list and its own default model. Repeat the model steps in every organization that uses Coder Agents. Refer to Organization scope for the settings that stay deployment-wide.
Detailed instructions for each provider and model option are in the Models documentation.
Tip
Start with a single frontier model to validate your setup before adding additional providers.
Step 2: Start your first Coder Agent
- Go to the Agents page in the Coder dashboard.
- Select a model from the dropdown (your default will be pre-selected).
- Type a prompt and send it.
The agent processes the prompt in the control plane. When the conversation and available tools are sufficient, it works without provisioning a workspace. If missing tools, skills, MCP integrations, or context block progress, the agent selects a template and provisions a workspace to continue. It also provisions a workspace for tasks that need file access, command execution, or code changes.
Control who can use Coder Agents
Organization members can use Coder Agents by default.
Access comes from the Coder Agents User (agents-access) organization role, which each organization grants to members through its default member roles.
Members who don't hold the role directly lose Coder Agents access when you remove Coder Agents User from the default roles. Role sync assigns roles at sign-in and doesn't store default roles, so members who get the role through role sync regain access at their next sign-in, and mapping the role in advance doesn't shorten the gap.
To limit Coder Agents to a subset of members in an organization (requires a Premium license):
-
Remove Coder Agents User from the organization's default roles.
In the dashboard, go to Admin settings > Organizations > Roles > Default Roles. From the CLI, run
coder organizations edit --org <organization> --default-org-member-roles organization-workspace-access, keeping any other default roles in the list. -
Grant
agents-accessto the members who need it:- With IdP organization role sync, map an IdP group or role to
agents-access. - Without role sync, assign Coder Agents User from Admin settings > Organizations > Members.
- With IdP organization role sync, map an IdP group or role to
Keep the following behavior in mind:
- Removing a user from the mapped IdP group or role removes their Coder Agents access at their next sign-in.
- Owners and Organization Admins can always use Coder Agents, whatever the default roles are.
- Service accounts don't inherit
agents-accessfrom the default roles. Assign the role to a service account directly if it needs Coder Agents. - Members without the role can't use Coder Agents or open chats they created earlier. Their chats are kept and become available again when they regain the role. A chat shared with them stays readable.
- Model permissions still apply: users also need read access to at least one model.
Optimize your templates
The agent selects templates based on their name, description, and README. It does not read Terraform. Clear, specific descriptions are the most important factor in whether the agent picks the right template.
Update your template descriptions to include:
- The language, framework, or stack the template targets.
- Which repository or service it is for, if applicable.
- What type of work it supports (backend, frontend, data pipeline, and so on).
When 128 characters is not enough, put the most important routing context near the top of the template's README.md.
The chat agent's template listing includes a bounded README excerpt (roughly the first 1,000 characters), and template detail includes the README (up to roughly 8,000 characters).
Both are reduced to plain text: frontmatter is stripped, link text is kept while link URLs are dropped, images and badges are dropped entirely, and code blocks and tables are preserved as text.
Good examples:
| Description | Why it works |
|---|---|
| Python backend services for the payments repo. Includes Poetry, Python 3.12, and PostgreSQL | Specific language, repo, and toolchain |
| React frontend development for the customer portal. Node 20, pnpm, Storybook pre-installed | Clear stack, named project, key tools listed |
| General-purpose Go development environment with Go 1.23, Docker, and common CLI tools | Broad but descriptive |
Descriptions to avoid:
| Description | Problem |
|---|---|
| Team A template v2 | No information about what the template is for |
| Dev environment | Too generic to distinguish from other templates |
| Default | Tells the agent nothing |
See Template Optimization for the full guide, including dedicated agent templates, network boundaries, credential scoping, and pre-installing dependencies.
Things to know before you start
Plan for change between releases
Coder Agents is generally available. However, APIs, behavior, and configuration might change between releases. As always, you should review release notes and the changelog before upgrading, so changes do not affect production.
Use HTTPS for push notifications
Coder Agents use browser push notifications to alert you when a task completes or needs attention. Most browsers require a secure (HTTPS) origin for the Push API to work. If your access URL uses plain HTTP, push notifications might not function.
This does not affect agents themselves, only the browser notification delivery.
If you terminate TLS at a reverse proxy, make sure the access URL is configured with an https:// scheme.
Set a deployment-wide system prompt
Administrators can set a system prompt that applies to all Coder Agents across the deployment. Use this to encode organizational conventions:
- Coding standards and style guidelines.
- Commit message formats.
- Branch naming conventions.
- Required review processes before merging.
- Any guardrails specific to your environment.
Configure the system prompt from Admin settings > AI > Coder Agents > Instructions or via the API at PUT /api/v2/chats/config/system-prompt.
In a deployment with several organizations, organization administrators can also add organization instructions under Admin settings > AI > Coder Agents > Instructions. Coder adds them after the deployment system prompt for new chats in that organization. Refer to Platform Controls for details.
Understand the security model
The agent runs in the control plane, not inside workspaces. This means:
- No LLM API keys in workspaces. Credentials stay in the control plane.
- No agent software in workspaces. No supply chain risk from third-party agent tools.
- User identity is always attached. Every action is tied to the user who submitted the prompt, with no shared bot accounts.
- No privilege escalation. The agent has exactly the same permissions as the prompting user.
Agent workspaces inherit the same network access as any manually created workspace. If your templates don't restrict egress, the agent has full internet access from the workspace. Consider creating dedicated agent templates with tighter network policies.
Plan for LLM costs
Every conversation turn sends tokens to your LLM provider. Long-running tasks, sub-agent delegation, and complex multi-step work can consume significant token volume. Consider:
- Starting with a single model to establish a cost baseline.
- Capping spend with AI Gateway budgets.
- Monitoring provider dashboards for usage trends as adoption grows.
Plan for concurrency limits
Community and Premium licenses run up to 5 agents at once. Additional agents queue and start automatically when capacity frees. An AI Premium license, which includes Agent Hours, does not impose a concurrency limit unless the Agent Hours hard limit is reached. If the Agent Hours allocation is exhausted without a configured hard limit, Coder warns about usage but does not impose a concurrency limit. When the Agent Hours hard limit is reached, additional agents queue under the concurrency limit. Refer to Concurrent agents for details.
Pilot with a small group
Identify 3–5 developers and a few concrete use cases for the initial rollout. Good starting points:
- Low-risk, high-visibility tasks: generating unit tests, writing inline documentation, small refactors.
- Investigation and triage: exploring unfamiliar code, triaging bugs, understanding legacy systems.
- Prototyping: building proof-of-concept implementations, simple dashboards, internal tools.
To limit Coder Agents to the pilot group, see Control who can use Coder Agents.
Set expectations for how the team reviews agent output. Developers should still review all agent-produced code before merging. The agent is a force multiplier, not a replacement for developer judgment.
Use the API for programmatic automation
The Chats API enables programmatic access to Coder Agents. This is useful for building automations such as:
- Triggering Coder Agents from continuous integration and continuous delivery (CI/CD) pipelines when builds fail.
- Creating Coder Agents from GitHub webhooks on new issues or PRs.
- Building internal tools or dashboards on top of the API.
- Scripting batch operations across repositories.
Quick example — create a Coder Agent via the API:
Replace <your-org-id> with the ID of an organization you belong to.
To find the ID, run coder organizations list and copy the value in the id column.
curl -X POST https://coder.example.com/api/v2/chats \
-H "Coder-Session-Token: $CODER_SESSION_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"organization_id": "<your-org-id>",
"content": [
{"type": "text", "text": "Fix the failing tests in the auth service"}
]
}'
Stream updates in real time by connecting to the WebSocket endpoint:
GET /api/v2/chats/{chat}/stream
For service-to-service automation, use API keys rather than developer session tokens. Keep automation credentials narrowly scoped.
Link to a new chat with a prompt
To send users to a new chat with a message already written, link to /agents with a prompt query parameter.
URL-encode the message (for example, with encodeURIComponent in JavaScript):
https://coder.example.com/agents?prompt=Fix%20the%20failing%20tests%20in%20the%20auth%20service
The link fills in the message box only. Coder doesn't send the message: the user reviews it, can edit it, and selects Send. Because any website can create such a link, a warning in the message box asks the user to take care before sending. The warning disappears once the user edits the message.
If the user isn't signed in, Coder keeps the message through sign-in.
Do not put secrets in these links. URLs end up in browser history and server logs.
Add workspace context with AGENTS.md
Create an AGENTS.md file in the home directory (~/.coder/AGENTS.md) or the workspace agent's working directory to provide persistent context to the agent.
This file is automatically read and included in the system prompt for every conversation with a Coder Agent that uses that workspace.
Use it for:
- Repository-specific build and test instructions.
- Important architectural decisions or constraints.
- Links to relevant documentation or runbooks.
- Any context that helps the agent work effectively in that codebase.
Consider prebuilt workspaces for faster startup
Workspace provisioning is the main source of latency when the agent starts a task. If your templates take more than a minute to provision, consider configuring prebuilt workspaces to maintain a pool of ready-to-use workspaces. The agent gets assigned an already-running workspace instead of provisioning from scratch.
Provide feedback
Report bugs and feature requests as GitHub issues. For deployment-specific problems, such as provider configuration or performance in your environment, use your usual Coder support channel.
Good reports include:
- What you tried: the prompt, the template, and the model.
- What happened: the agent's behavior, any errors, and unexpected results.
- What you expected: the outcome you were looking for.
- Context:
screenshots,
chat_idvalues, or links to the Agents page help the team investigate quickly.
Next steps
- Architecture: how the control plane, LLM providers, and workspaces interact.
- Models — configure additional providers and models.
- Platform Controls: system prompts, template routing, and admin-level configuration.
- Template Optimization: create agent-friendly templates with network boundaries and scoped credentials.
- Chats API: build programmatic integrations.