← All implementations

Harvey · Platform

Spectre

Harvey's internal collaborative cloud agent platform; reacts to incidents, bug reports, and Slack messages and produces reviewable diffs, branches, and PRs.

1

Supporting infrastructure

This entry describes supporting infrastructure that other work builds on. The catalog classifies it as a platform. The record also reports a workflow.

Approach type
Platform
Work
Coding, Code review, On-call, Security
Human involvement
Drafts reviewed
Invocation
Interactive
Interfaces
Slack, Web, Automation
Deployment stage
Deployed
Evidence strength
Detailed primary
Entry reviewed

How it works

The workflow the sources report for this implementation.

Long-lived run state over throwaway compute

1

Outputs are summaries, diffs, branches, PRs; not silent actions

1

Where people stay involved

  • incident or request → reviewable diff or pull requestWork product review · Level 3

Level 3 for incident or request → reviewable diff or pull request; human attention boundary: work-product-review.

1

Observation date
2026

Implementation details

Sandbox

Isolated ephemeral execution environments; durable runs

1

Harness

Collaborative cloud agent platform with explicit boundaries around GitHub, Datadog, Linear, and other connected systems

1

Model

Not specified

1

Interfaces

slack, web, automation

1

Tool access

Explicit tool boundaries; reacts to incidents, bug reports, customer feedback, and Slack messages

1

Credentials

Explicit tool boundaries; outputs are reviewable

1

Context management

Durable runs over disposable execution environments

1

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

Make outputs reviewable (diffs, branches, PRs) rather than letting the agent act silently

1

Implementation speed shifts the bottleneck toward review, prioritization, and coordination

1

Harvey keeps its product-agent and security-agent platforms on separate substrates because they have different trust boundaries

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. Building Spectre; internal collaborative cloud agent platformhttps://www.harvey.ai/blog/building-spectre-internal-collaborative-cloud-agent-platformEngineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
  2. Building an agentic security operations centerhttps://www.harvey.ai/blog/building-an-agentic-security-operations-centerEngineering blog · 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
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  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. Credentials
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  8. Context management
    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. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  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. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    High
    Confidence reason
    The source explicitly frames diffs, branches, and pull requests as reviewable outputs.
    Observation date
    2026

The catalog records no related implementation for this entry yet.

Back to the directory →