Source: https://internal-agents.com/agents/hubspot-sidekick # HubSpot — 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. - Approach type: Task agent - Deployment stage: Scaled - Autonomy: Drafts reviewed - Evidence strength: Detailed primary - Status: Internal - First reported year: 2026 - Work: Code review - Interfaces: Github - Invocation: Event driven - Entry reviewed: 2026-09-15 ## Where people stay involved - **pull request → AI review comments** — Work product review · Level 3 ## Overview ### Summary 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. Fact · Reported · High confidence · `hubspot-sidekick--summary` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) · Preserved content.md, lines 14, 24–45, 75–87 - Contextualizes · [2] [Cloud coding agents at HubSpot](https://product.hubspot.com/blog/cloud-coding-agents-at-hubspot) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-2/content.md) · Preserved content.md, lines 30–57 (earlier Crucible implementation) ## Supervision evidence ### Operating model assessment Level 3 for pull request → AI review comments; human attention boundary: work-product-review. Inference · Catalog judgment · Medium confidence · `hubspot-sidekick--operating-models-0` Confidence reason: The engineering blog describes engineers acting on Sidekick review comments, which locates human attention at work-product review. Qualifications: - Observation date: 2026-03 Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) ## Implementation details ### Harness Aviator, an internal Java agent framework; replaced the earlier Claude Code review implementation on Crucible Fact · Reported · High confidence · `hubspot-sidekick--architecture-harness` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) · Preserved content.md, lines 24–45 ### Sandbox unknown Inference · Catalog judgment · Medium confidence · `hubspot-sidekick--architecture-sandbox` Confidence reason: Current review runs on Aviator; its execution isolation is not specified. Crucible Kubernetes workloads describe the predecessor implementation. Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) · Preserved content.md, lines 39–45 ### Tool access Aviator framework for precise tool control Fact · Reported · High confidence · `hubspot-sidekick--architecture-tool-access` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) ### Interfaces github Fact · Reported · High confidence · `hubspot-sidekick--architecture-interfaces` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) ## Reported metrics ### Headline claim Reviews every pull request and cut engineer feedback time by 90% Metric · Reported · Medium confidence · `hubspot-sidekick--headline-metric` Confidence reason: HubSpot reported the figures in its own engineering blog without independent verification. Qualifications: - 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 Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) · Preserved content.md, lines 14–18 ### Key observation Reviews every pull request Metric · Reported · Medium confidence · `hubspot-sidekick--key-metrics-0` Confidence reason: HubSpot reported the figures in its own engineering blog. Qualifications: - Reported by: HubSpot - Scope: Pull-request coverage after the six-month rollout - Denominator: HubSpot pull requests Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) · Preserved content.md, lines 14 ### Key observation Engineer feedback time cut by 90% Metric · Reported · Medium confidence · `hubspot-sidekick--key-metrics-1` Confidence reason: HubSpot reported the figures in its own engineering blog. Qualifications: - 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 Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) · Preserved content.md, lines 14–18 ### Key observation Over 80% thumbs-up reaction rate on review feedback during the preceding couple of months Metric · Reported · Medium confidence · `hubspot-sidekick--key-metrics-2` Confidence reason: HubSpot reported the figures in its own engineering blog. Qualifications: - 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 Evidence: - Supports · [1] [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/hubspot-sidekick-source-1/content.md) · Preserved content.md, lines 99–116 ## Sources 1. [Automated code review, the 6-month evolution](https://product.hubspot.com/blog/automated-code-review-the-6-month-evolution) - Engineering blog · First party · Evidence - Original URL: - Published: 2026-03 · Accessed: 2026-08-13 · Last verified: 2026-08-31 - Preserved copy in the repository: 2. [Cloud coding agents at HubSpot](https://product.hubspot.com/blog/cloud-coding-agents-at-hubspot) - Engineering blog · First party · Evidence - Original URL: - Accessed: 2026-08-13 · Last verified: 2026-08-31 - Preserved copy in the repository: