Devin

Plug MCP servers into this product so it can use their tools G

Agent access

Connect an agent via an official MCP server G

Agent access

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

Drive the product through a documented public API G

Agent access

Build against official SDKs G

Agent access

Operate the product with natural-language commands G

Agentic features

Run the product headlessly / in CI for automation G

Agent access

Set up automations that run autonomously in the background G

Agentic features

Use an official CLI G

Agent access

Point an agent at llms.txt or agent-oriented docs G

Agent access

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

Issue scoped/least-privilege API credentials for an agent G

Agent access

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

Explore an interactive API reference with runnable examples G

Api quality

Rely on versioned APIs with a documented deprecation policy G

Api quality

Subscribe to events via webhooks G

Agent access

Test against a sandbox environment without touching production data G

Api quality

Add a context file describing my codebase conventions so agents generate more relevant plans and code C

Knowledge context

Assign a coding task to an agent directly from an existing issue or ticket C

Ticket driven tasking

Define rules that trigger actions automatically on events G

Describe a feature or bug in plain language and have it automatically turned into a scoped implementation task C

Natural language task intake

Have failed CI workflows automatically diagnosed and fixed with a proposed pull request C

Ci remediation

Run many agent tasks concurrently to scale delivery throughput C

Concurrent execution

Watch what a running agent is doing in real time, including its current status C

Visibility monitoring

Connect a GitHub repository so an agent can access the code and open pull requests against it C

Version control integration

Connect issue trackers like Jira, Linear, ClickUp, or Monday.com so agents can manage tickets directly C

Project management integration

Have an agent safely execute code and install dependencies inside an isolated sandbox C

Sandbox execution

Have an agent autonomously diagnose and fix a reported bug C

End to end feature delivery

Have an agent implement a requested feature end-to-end, including writing tests C

End to end feature delivery

Have every pull request automatically reviewed with AI-generated inline comments C

Pr review automation

Review a diff of an agent's changes and approve it before it becomes a pull request C

Diff review

Set tiered autonomy levels controlling what an agent can do without manual confirmation C

Approval controls

Review and approve an agent's implementation plan before any code changes are made C

Plan approval

Self-host the core product G

Export all of my data in open formats and leave G

Prevent my data from being used to train AI models G

Create agent sessions on behalf of other users in my organization C

Concurrent execution

Have an agent automatically clone the repo, install dependencies, and configure its own working environment C

Environment setup

Have each task prompt automatically routed to the most suitable underlying model C

Model control

Schedule recurring jobs or workflows G

Tag an agent in a chat thread to discuss and delegate a bug or task C

Chat integration

Take over an in-progress agent task in my editor, terminal, or browser to finish or redirect the work C

Interactive takeover

Use a managed cloud offering to run agents without operating my own backend infrastructure C

Deployment flexibility

Get notified when an agent completes a task or needs my input C

Visibility monitoring

Have an agent automatically generate and run tests to validate its own code changes before proposing them C

End to end feature delivery

Perform bulk operations across many items at once G

Run an agent headlessly inside CI/CD pipelines and shell scripts C

Headless automation

Trigger an agent from CI/CD pipelines to fix a broken build or failing test C

Ci remediation

Configure an agent to automatically open a pull request when its task completes C

Diff review

Convert user feedback submissions into structured tasks with proposed scope C

Natural language task intake

Do everything through the API that I can do in the UI G

Go from a mockup or design to a working implementation without an engineering handoff C

End to end feature delivery

Grant an agent access to my repositories with a one-click install, without complex setup C

Version control integration

Have security alerts automatically validated and remediated with an opened pull request C

Security remediation

Send follow-up instructions to an active agent session to steer its work without restarting C

Interactive takeover

Approve a task's scope and contract before an agent is allowed to modify the repository C

Plan approval

Bring my own LLM or API key so agents run on the model of my choice C

Model flexibility

Configure an agent to auto-approve all its actions instead of confirming each one C

Approval controls

Have incoming issues automatically triaged with severity suggested and routed to the right owner C

Pr review automation

See and manage plan-based daily task and concurrency limits for agent workflows G

Usage quotas

Self-host agent infrastructure locally, in containers, or on my own VMs C

Deployment flexibility

Attach a marked-up screenshot or mockup to a task so the agent implements the correct visual change C

Natural language task intake

Choose where my data is stored (region/residency) G

Control data retention and deletion G

License an enterprise deployment with SSO and commercial support for organization-wide rollout G

Enterprise licensing

Opt out of telemetry and usage tracking G

Read the product's source under an open license G

Run a readiness report that evaluates how ready my repository is for autonomous agents C

Readiness checks

Query generated documentation for any public or private repository C

Knowledge context

Switch away from automatic model selection to a specific model of my choice C

Model control

Automatically fix failing agent-readiness criteria in my repository C

Readiness checks

Version, review, and roll back my automations G

Approve key agent decisions from my phone while agents continue working C

Approval controls