# Twill

## Docs

- [What is Twill](https://docs.twill.ai/overview.md): Twill turns task descriptions into pull requests — built and tested in a real dev environment, with proof attached.
- [Quickstart](https://docs.twill.ai/quickstart.md): From sign-up to your first verified pull request in a few minutes.
- [What to delegate](https://docs.twill.ai/first-tasks.md): The tasks Twill handles best, and how to phrase them for a fast, reviewable PR.
- [Working with tasks](https://docs.twill.ai/tasks.md): Create tasks, pick a mode, follow up, and track progress — from the web app or anywhere else.
- [Plans & questions](https://docs.twill.ai/planning.md): Clarifying questions, plan-first workflows, and read-only Ask mode.
- [Verification](https://docs.twill.ai/verification.md): Every PR ships with proof: build, tests, lint, runtime checks, and artifacts you can review.
- [Your dev environment](https://docs.twill.ai/environment.md): A long-lived workspace sandbox that runs your whole stack — forked per task, verified against, and yours to inspect over SSH.
- [Automations](https://docs.twill.ai/automations.md): Recurring tasks on a schedule: issue triage, dependency updates, monitoring — set up once, reviewed as PRs.
- [Use with your local agent](https://docs.twill.ai/local-agents.md): Delegate implementation to Twill from Claude Code, Cursor, or any local coding agent — and pull work back down when you want hands on keys.
- [CLI](https://docs.twill.ai/cli.md): Create and manage Twill tasks, automations, and sandboxes from your terminal.
- [Desktop & mobile](https://docs.twill.ai/desktop-app.md): Twill as a native desktop app with notifications and auto-updates, and as a mobile PWA for following your factory from your phone.
- [Work from your tools](https://docs.twill.ai/integrations/overview.md): Trigger Twill from GitHub, Slack, Linear, Notion, or Asana — and give it read access to your error trackers and cloud.
- [GitHub](https://docs.twill.ai/integrations/github-issues.md): Turn issues into PRs, iterate on review feedback, and let Twill fix CI — all from GitHub.
- [Slack](https://docs.twill.ai/integrations/slack.md): Mention @twill in any channel to turn a conversation into a task — questions and results come back to the thread.
- [Linear](https://docs.twill.ai/integrations/linear-issues.md): Delegate Linear issues to Twill with a label or an assignment.
- [Notion](https://docs.twill.ai/integrations/notion.md): Turn Notion comments into tasks — specs and roadmaps become PRs without leaving the page.
- [Asana](https://docs.twill.ai/integrations/asana.md): Comment on any Asana task to hand it to Twill.
- [Sentry](https://docs.twill.ai/integrations/sentry.md): Let Twill investigate production errors with real stack traces and propose fixes.
- [Datadog](https://docs.twill.ai/integrations/datadog.md): Read-only observability context for the agent: monitors, dashboards, and host details.
- [Google Cloud](https://docs.twill.ai/integrations/gcp.md): Read-only access to Cloud Run logs and service status for debugging production issues.
- [Amazon Web Services](https://docs.twill.ai/integrations/aws.md): Read-only AWS access through a cross-account IAM role — no long-lived keys.
- [Agents & models](https://docs.twill.ai/agent-config/overview.md): Choose which coding agent and model runs each task — Claude Code, Codex, or OpenCode.
- [Routing](https://docs.twill.ai/agent-config/routing.md): Map trigger keywords to a mode, agent, and effort — so `/plan` or `/ultra` means the same thing everywhere.
- [Bring your own keys](https://docs.twill.ai/agent-config/byok.md): Run tasks on your own provider API keys at provider rates — Twill bills nothing for the AI usage.
- [MCP servers](https://docs.twill.ai/agent-config/mcp.md): Built-in MCP tools from your integrations, plus custom servers via a .mcp.json in your repo.
- [Repository skills](https://docs.twill.ai/agent-config/repository-skills.md): Teach Twill your team's procedures with SKILL.md files that live in your repos.
- [How Twill works](https://docs.twill.ai/how-it-works.md): The architecture: real CLI agents, specialized sub-agents, and self-verification against a running app.
- [Security](https://docs.twill.ai/security.md): Isolation, least-privilege access, encryption, and human review at the core of the workflow.
- [Team management](https://docs.twill.ai/team-management.md): Invite your team, assign roles, and transfer ownership.
- [Pricing](https://docs.twill.ai/pricing.md): Simple credit-based plans. Unlimited users on every tier.
- [Legibility scorecard](https://docs.twill.ai/scorecard.md): Score how ready your repository is for coding agents — free, at twill.ai/score.
- [Release Notes](https://docs.twill.ai/release-notes.md): Weekly updates on new features, improvements, and bug fixes
- [API](https://docs.twill.ai/api.md): Create and manage tasks programmatically with the Twill REST API.
- [Create task](https://docs.twill.ai/api-reference/create-task.md): Dispatch a new task and start an agent run.
- [List tasks](https://docs.twill.ai/api-reference/list-tasks.md): List the workspace's tasks, newest first.
- [Get task](https://docs.twill.ai/api-reference/get-task.md): Fetch one task by id or slug.
- [List task jobs](https://docs.twill.ai/api-reference/list-task-jobs.md): A task's chronological run history.
- [Approve plan](https://docs.twill.ai/api-reference/approve-plan.md): Approve a drafted plan and start implementation.
- [Send message](https://docs.twill.ai/api-reference/send-message.md): Send a follow-up message to a task.
- [Cancel task](https://docs.twill.ai/api-reference/cancel-task.md): Stop a task's active runs.

## OpenAPI Specs

- [openapi](https://docs.twill.ai/openapi.json)