← All implementations

Linear · Task agent

Linear Agent

A native agent that synthesizes workspace context, triages, creates follow-up work, runs coding sessions, and executes scheduled/event-driven 'Loops'; used by Linear's own CX, Product, and Engineering teams.

1 Supports2 Supports6 Supports

Approach type
Task agent
Work
Support, Customer success, Coding
Human involvement
Drafts reviewed
Invocation
Event driven, Interactive
Interfaces
Slack, Intercom, Linear, Github
Deployment stage
Scaled
Evidence strength
Detailed primary
Entry reviewed

How it works

The workflow the sources report for this implementation.

Auto-routes issues, flags duplicates, suggests labels

2

Agents get identities, scoped team access, and visible delegation alongside humans

3

Scheduled or event-driven agent runs that execute recurring work

1

Where people stay involved

  • assigned coding work → agent-created changeWork product review · Level 3

Level 3 for assigned coding work → agent-created change; human attention boundary: work-product-review.

1

Observation date
2026-08-11

Implementation details

Sandbox

unknown

1

Harness

Separate planning agent (triage/issue creation) and coding agent (code generation); Code Intelligence for codebase knowledge; scheduled/event-driven 'Loops'

1 Supports2 Supports

Model

Codex was used for internal pull-request review; other model choices are not detailed in the preserved sources

2

Interfaces

slack, intercom, linear, github

2

Tool access

Triage Intelligence (auto-route, dedup, label); GitHub; testing Code Intelligence + custom MCP servers

2

Knowledge

Semantic/vector search evolved into agentic context acquisition across the workspace; Datadog/Sentry customer context

2

Credentials

The Agent SDK gives agents explicit identities, scoped OAuth tokens, assignable/mentionable handles, and visible human delegation; issues stay assigned to a human; 'an agent cannot be held accountable'

3

Reported results and limitations

The catalog records what the sources report, with the scope and the denominator of every figure. A qualification below limits the figure it sits under.

Lessons and interpretation

Keep the agent close to the source of work (Intercom, Slack, Linear); the best workflows live where work already happens

2

Gradual autonomy; start by asking for suggestions, observe, add guidance, only automate once proven reliable

2

Break work into small steps to keep coding agents focused and successful

2

One Linear engineer reports that agent mistakes reveal possible failure modes during review

2

Close the loop; auto-notify the customer when their request ships

2

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

  1. How we built Linear Agenthttps://linear.app/now/how-we-built-linear-agentEngineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
  2. How we use Linear Agent at Linearhttps://linear.app/now/how-we-use-linear-agent-at-linearEngineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
  3. Our approach to building the Agent Interaction SDKhttps://linear.app/now/our-approach-to-building-the-agent-interaction-sdkEngineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
  4. Hacker News submission for how Linear built its agenthttps://news.ycombinator.com/item?id=49252304Hn thread · Community · Last source verification: 2026-08-31
    Preserved copy ↗
  5. Hacker News submission for the Linear Agent public betahttps://news.ycombinator.com/item?id=48503334Hn thread · Community · Last source verification: 2026-08-31
    Preserved copy ↗
  6. Introducing Linear Agenthttps://linear.app/changelog/2026-03-24-introducing-linear-agentRelease · First party · Last source verification: 2026-08-31
    Preserved copy ↗
Research details for every claim on this page
  1. Summary
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  2. Sandbox
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The preserved sources do not document an execution sandbox; unknown does not mean absent.
  3. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  4. Model
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  5. Interfaces
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  6. Tool access
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  7. Knowledge
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  8. Credentials
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  9. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  10. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  11. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  12. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  13. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  14. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  15. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  16. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  17. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The source documents delegated coding output while a human remains accountable for the assigned issue.
    Observation date
    2026-08-11

The catalog records no related implementation for this entry yet.

Back to the directory →