← All implementations

HubSpot · Task agent

Sidekick

Sidekick is HubSpot's internal AI code reviewer, built by its Developer Experience AI team. It runs on every pull request in GitHub. A second Judge Agent evaluates each draft comment for succinctness, accuracy, and actionability, and only comments that pass are posted.

1 Supports2 Contextualizes

Approach type
Task agent
Work
Code review
Human involvement
Drafts reviewed
Invocation
Event driven
Interfaces
Github
Deployment stage
Scaled
Evidence strength
Detailed primary
Entry reviewed

Where people stay involved

  • pull request → AI review commentsWork product review · Level 3

Level 3 for pull request → AI review comments; human attention boundary: work-product-review.

1

Observation date
2026-03

Implementation details

Harness

Aviator, an internal Java agent framework; replaced the earlier Claude Code review implementation on Crucible

1

Sandbox

unknown

1

Tool access

Aviator framework for precise tool control

1

Interfaces

github

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.

Reported metrics

Headline claim

Reviews every pull request and cut engineer feedback time by 90%

1

The source does not report the denominator of this figure.

Reported by
HubSpot
Scope
Time for engineers to receive code feedback from Sidekick; not overall PR completion time
Observation date
2026-03
Key observation

Reviews every pull request

1

Reported by
HubSpot
Scope
Pull-request coverage after the six-month rollout
Denominator
HubSpot pull requests
Key observation

Engineer feedback time cut by 90%

1

The source does not report the denominator of this figure.

Reported by
HubSpot
Scope
Time for engineers to receive code feedback from Sidekick; not overall PR completion time
Key observation

Over 80% thumbs-up reaction rate on review feedback during the preceding couple of months

1

Reported by
HubSpot
Scope
Developer emoji reactions on review comments during the preceding couple of months
Denominator
Thumbs-up and thumbs-down reactions; not all developers or all reviews
Method
Emoji reactions and replies on review comments

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. Automated code review, the 6-month evolutionhttps://product.hubspot.com/blog/automated-code-review-the-6-month-evolutionEngineering blog · First party · Last source verification: 2026-08-31
    Preserved copy ↗
  2. Cloud coding agents at HubSpothttps://product.hubspot.com/blog/cloud-coding-agents-at-hubspotEngineering 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. Headline claim
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    HubSpot reported the figures in its own engineering blog without independent verification.
    Reported by
    HubSpot
    Scope
    Time for engineers to receive code feedback from Sidekick; not overall PR completion time
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    2026-03
  3. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  4. Sandbox
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    Current review runs on Aviator; its execution isolation is not specified. Crucible Kubernetes workloads describe the predecessor implementation.
  5. Tool access
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  6. Interfaces
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    High
    Confidence reason
    A linked first-party source states the claim.
  7. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    HubSpot reported the figures in its own engineering blog.
    Reported by
    HubSpot
    Scope
    Pull-request coverage after the six-month rollout
    Denominator
    HubSpot pull requests
    Method
    Not reported
    Observation date
    Not reported
  8. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    HubSpot reported the figures in its own engineering blog.
    Reported by
    HubSpot
    Scope
    Time for engineers to receive code feedback from Sidekick; not overall PR completion time
    Denominator
    Not reported
    Method
    Not reported
    Observation date
    Not reported
  9. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    HubSpot reported the figures in its own engineering blog.
    Reported by
    HubSpot
    Scope
    Developer emoji reactions on review comments during the preceding couple of months
    Denominator
    Thumbs-up and thumbs-down reactions; not all developers or all reviews
    Method
    Emoji reactions and replies on review comments
    Observation date
    Not reported
  10. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The engineering blog describes engineers acting on Sidekick review comments, which locates human attention at work-product review.
    Observation date
    2026-03
Back to the directory →