Source: https://internal-agents.com/agents/github-qubot

# GitHub — Qubot

GitHub's internal data-analytics agent, powered by GitHub Copilot. Any GitHub employee can ask a question about the company data warehouse in plain language and get an answer within seconds.

- Approach type: Task agent
- Deployment stage: Scaled
- Autonomy: Assistive
- Evidence strength: Detailed primary
- Status: Internal
- First reported year: 2026
- Work: Data
- Invocation: Interactive
- Entry reviewed: 2026-09-09

## Where people stay involved

- **data question → warehouse answer** — Unknown · Level unknown

## Overview

### Summary

GitHub's internal data-analytics agent, powered by GitHub Copilot. Any GitHub employee can ask a question about the company data warehouse in plain language and get an answer within seconds.

Fact · Reported · High confidence · `github-qubot--summary`

Confidence reason: A linked first-party source states the claim.

Evidence:

- Supports · [1] [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md)

## Supervision evidence

### Operating model assessment

Unclassified for data question → warehouse answer; human attention boundary: unknown.

Inference · Catalog judgment · Unverified confidence · `github-qubot--operating-models-0`

Confidence reason: The public evidence does not document where human attention returns in the question-and-answer flow.

Qualifications:

- Observation date: 2026-06

Evidence:

- Supports · [1] [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md)

## Implementation details

### Model

Powered by GitHub Copilot

Fact · Reported · High confidence · `github-qubot--architecture-model`

Confidence reason: A linked first-party source states the claim.

Evidence:

- Supports · [1] [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md)

### Tool access

Queries GitHub's data warehouse

Fact · Reported · High confidence · `github-qubot--architecture-tool-access`

Confidence reason: A linked first-party source states the claim.

Evidence:

- Supports · [1] [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md)

## Reported metrics

### Headline claim

Hundreds of users run thousands of queries; data questions in internal Slack channels dropped

Metric · Reported · Medium confidence · `github-qubot--headline-metric`

Confidence reason: GitHub reported the adoption figures in its own engineering blog without independent verification.

Qualifications:

- The source does not report the denominator of this figure.
- Reported by: GitHub
- Scope: Internal GitHub Qubot users and queries; no exact count or measurement window
- Observation date: 2026-06

Evidence:

- Supports · [1] [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md) · Preserved content.md, lines 70

### Key observation

Hundreds of users run thousands of queries

Metric · Reported · Medium confidence · `github-qubot--key-metrics-0`

Confidence reason: GitHub reported the adoption figures in its own engineering blog.

Qualifications:

- The source does not report the denominator of this figure.
- Reported by: GitHub
- Scope: Internal GitHub Qubot users and queries; no exact count or measurement window

Evidence:

- Supports · [1] [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md) · Preserved content.md, lines 70

## Reported outcomes and statements

### Key observation

Volume of data questions in internal data and analytics Slack channels dropped

Fact · Reported · Medium confidence · `github-qubot--key-metrics-1`

Confidence reason: Company reports a qualitative decrease without before-and-after counts.

Qualifications:

- Scope: Questions in GitHub internal data and analytics Slack channels

Evidence:

- Supports · [1] [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md) · Preserved content.md, lines 70

## Sources

1. [How we built an internal data analytics agent](https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/)
   - Engineering blog · First party · Evidence
   - Original URL: <https://github.blog/ai-and-ml/github-copilot/how-we-built-an-internal-data-analytics-agent/>
   - Published: 2026-06-19 · Accessed: 2026-08-13 · Last verified: 2026-08-31
   - Preserved copy in the repository: <https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/github-qubot-source-1/content.md>