diff --git a/src/content/docs/agents/capabilities/skills.mdx b/src/content/docs/agents/capabilities/skills.mdx index eed3dde8a..8767b37be 100644 --- a/src/content/docs/agents/capabilities/skills.mdx +++ b/src/content/docs/agents/capabilities/skills.mdx @@ -448,7 +448,7 @@ This is useful when you want to reuse a skill's workflow but tailor the executio Skills can be used with both local and [cloud agents](/platform/) to create reusable, automated workflows. When running an agent via the CLI, web app, or API, you can specify a skill to provide the base instructions for the agent. -For a complete guide to running skill-based agents—including CLI usage, the {VARS.WEB_APP}, scheduling, skill discovery, and API integration—see [Skills as Agents](/platform/skills-as-agents/). +For a complete guide to running skill-based agents—including CLI usage, the {VARS.WEB_APP}, scheduling, skill discovery, and API integration—see [Skills as Agents](/platform/skills-as-agents/). For procedures scoped to a factory or one of its agents, see [Factory skills](/factories/factory-skills/). ## Related features diff --git a/src/content/docs/factories/automations.mdx b/src/content/docs/factories/automations.mdx index c6a02049f..aa0927dc3 100644 --- a/src/content/docs/factories/automations.mdx +++ b/src/content/docs/factories/automations.mdx @@ -127,3 +127,4 @@ Replace `WEBHOOK_UID` with the webhook's UID. For selecting webhooks and testing * [Triggering automations with custom webhooks](/factories/webhooks/) - Configure senders and authentication * [Factory definition syntax](/factories/factory-as-code/) - Manage automations as version-controlled files * [Factory dashboard](/factories/factory-dashboard/) - Manage agents, automations, and runs +* [Scheduled agents](/platform/triggers/scheduled-agents/) - Run standalone cloud agents on a cron schedule outside a factory diff --git a/src/content/docs/factories/index.mdx b/src/content/docs/factories/index.mdx index cd966c16b..1d07aa0a7 100644 --- a/src/content/docs/factories/index.mdx +++ b/src/content/docs/factories/index.mdx @@ -96,6 +96,7 @@ Don't split the same repositories across factories by team or task, such as fron * [How Warp Factories work](/factories/how-factories-work/) - The work-item lifecycle, stage by stage. * [About factory agents](/factories/factory-agents/) - Understand default agent roles * [Configuring factory agents](/factories/factory-agents/configuration/) - Choose models, harnesses, and instructions +* [Multi-agent orchestration](/platform/orchestration/) - Fan out ad-hoc parent and child agents outside a standing factory * [Definitions as code](/factories/factory-as-code/) - The definition file format, with working examples in [warp-factory-examples](https://github.com/warpdotdev/warp-factory-examples). * [Transitioning from Oz](/platform/transitioning-from-oz/) - Assess an existing web app, CLI, SDK, or API workflow. * Get started with the Warp team - Get help choosing and setting up a workflow. diff --git a/src/content/docs/guides/agent-workflows/how-to-run-multiple-ai-coding-agents.mdx b/src/content/docs/guides/agent-workflows/how-to-run-multiple-ai-coding-agents.mdx index 9ae49f2ab..0ab6d6918 100644 --- a/src/content/docs/guides/agent-workflows/how-to-run-multiple-ai-coding-agents.mdx +++ b/src/content/docs/guides/agent-workflows/how-to-run-multiple-ai-coding-agents.mdx @@ -252,4 +252,5 @@ You set up a multi-agent workspace with vertical tabs, launched different agents * [How to review AI-generated code](/guides/agent-workflows/how-to-review-ai-generated-code/) - Review and refine the code your agents produced * [Multi-agent orchestration](/platform/orchestration/) - Coordinate parent and child agents across local and cloud runs +* [Warp Factories](/factories/) - Run a standing triage-to-merge team of cloud agents instead of one-off fan-out * [How to run unattended agents](/guides/agent-workflows/how-to-run-unattended-agents/) - Start recurring or event-driven cloud agents without staying in the terminal diff --git a/src/content/docs/guides/agent-workflows/how-to-run-unattended-agents.mdx b/src/content/docs/guides/agent-workflows/how-to-run-unattended-agents.mdx index 3cddbfada..4618191aa 100644 --- a/src/content/docs/guides/agent-workflows/how-to-run-unattended-agents.mdx +++ b/src/content/docs/guides/agent-workflows/how-to-run-unattended-agents.mdx @@ -30,6 +30,7 @@ Use this table to decide where an unattended agent should start. | GitHub Actions | A repository event, PR workflow, issue workflow, or CI failure should start the agent. | [GitHub Actions](/platform/integrations/github-actions/) | GitHub Actions logs, PR or issue comments, {VARS.WEB_APP}, and cloud agent runs | | {VARS.WARP_AGENT_CLI} | You want to start a named cloud run from a terminal, script, or local automation. | [{VARS.WARP_AGENT_CLI}](/agents/cli/oz-cli/#running-agents-remotely-oz-agent-run-cloud) | CLI output, {VARS.WEB_APP} Runs page, Agent Management Panel in the Warp app, and cloud agent session links | | {VARS.WARP_PLATFORM_API} | Your internal system should create, query, or monitor runs programmatically. | [{VARS.WARP_PLATFORM_API}](/factories/api-and-sdk/) | Your system, API results, {VARS.WEB_APP}, and run sessions | +| [Factory automations](/factories/automations/) | Work should enter a standing triage-to-merge factory from schedules, integrations, or webhooks. | [Connect your factory](/factories/connect-your-factory/) and [Warp Factories](/factories/) | Factory dashboard runs, inbox, and the source thread or issue | ## Choose a workflow pattern @@ -135,4 +136,5 @@ Start with one narrow workflow before deploying many unattended agents: * [GitHub integration](/platform/integrations/github/) - Set up `@warp-agent` mentions on issues and pull requests. * [GitHub Actions quickstart](/platform/integrations/quickstart-github-actions/) - Add an agent to a PR review workflow. * [Multi-agent orchestration](/platform/orchestration/) - Fan unattended parent runs out to child agents when the work is large enough to shard. +* [Factory automations](/factories/automations/) - Route schedules and integration events through a standing factory workflow. * [Viewing cloud agent runs](/platform/viewing-cloud-agent-runs/) - Inspect and share unattended run sessions. diff --git a/src/content/docs/platform/agents.mdx b/src/content/docs/platform/agents.mdx index c249cc120..e145231c7 100644 --- a/src/content/docs/platform/agents.mdx +++ b/src/content/docs/platform/agents.mdx @@ -58,7 +58,7 @@ When a team is over its plan limit (for example, after downgrading), the extra a ## Where cloud agents appear in the product * **Agents page** - The Agents page in the [{VARS.WEB_APP}](/platform/oz-web-app/) is where teams view, create, edit, and delete cloud agents. -* **Agent picker** - Forms that start a new run or schedule include an **Agent** dropdown. **Quick run** is the default: runs execute as the calling user, and pull requests are authored by that person. Picking a cloud agent runs as that agent instead, so with [team GitHub authorization](/platform/team-access-billing-and-identity/#team-github-authorization) configured, pull requests are authored by the **Warp Factories** GitHub App. Choose a cloud agent for any schedule that opens pull requests. See [Run identity and pull request authorship](/platform/triggers/scheduled-agents-quickstart/#run-identity-and-pull-request-authorship). +* **Agent picker** - Forms that start a new run or schedule include an **Agent** dropdown. **Quick run** is the default: runs execute as the calling user, and pull requests are authored by that person. Picking a cloud agent runs as that agent instead, so with [team GitHub authorization](/platform/team-access-billing-and-identity/#team-github-authorization) configured, pull requests are authored by the [Warp Factories](/factories/) GitHub App. Choose a cloud agent for any schedule that opens pull requests. See [Run identity and pull request authorship](/platform/triggers/scheduled-agents-quickstart/#run-identity-and-pull-request-authorship). * **Run filters and detail** - The Runs view lets you filter by cloud agent, and individual run detail pages show which agent executed the run. * **Admin Panel** - Billing usage in the [Admin Panel](/knowledge-and-collaboration/admin-panel/) attributes usage consumed by cloud agent runs to the team rather than to a person.