PR agent

The PR Agent is a data-aware pull request reviewer that analyzes PRs modifying data models, pipelines, or transformations. Unlike generic code reviewers, it uses Monte Carlo observability data — lineage, active alerts, asset importance, and monitor coverage — to assess the real production impact of code changes.

The PR Agent is part of the MC Prevent suite alongside the CI Agent and Code Change skill.

How it works

When a PR is opened or updated, the PR Agent runs a multi-step analysis:

Code risk factor extraction — Analyzes the PR diff to identify column-level changes (added, removed, renamed, modified), upstream reference changes, and potentially risky code patterns. Each finding gets a risk and confidence score.
Downstream impact analysis — Traces Monte Carlo lineage to identify which tables, BI reports, and downstream consumers would be affected by the changes.
Risk assessment — Assigns a risk tier (Low, Medium, or High) to each affected Monte Carlo asset based on:
- Breaking changes detected in the code
- Active Monte Carlo alerts on modified or upstream assets
- Downstream blast radius
- Write query volume on affected tables
- Monitor coverage gaps
PR comment — Posts a structured comment on the PR organized by change group — related changes are merged and sorted by risk and blast radius. Each group includes its own alert breakdown, diff links, and downstream counts. Key assets are marked with a star so your most important tables are impossible to miss. A thumbs-up/down reaction footer lets you give feedback on each review.

Risk scoring

The PR Agent produces an overall risk score using configurable weight categories:

Category	Default weight	What it measures
Code review findings	40%	Risky code patterns, breaking changes, schema modifications
Lineage blast radius	15%	Number and importance of downstream assets affected
Open alerts	15%	Active Monte Carlo alerts on assets in the change's path
Monitoring gaps	15%	Unmonitored assets in the blast radius
Schema/contract changes	10%	Breaking schema changes or interface contract violations
Asset criticality	5%	Business importance score of affected assets

Review types

Review type	What's included	Cost
Free review	Risk score and high-level summary on every PR	No charge
Full review	Specific risky code sections, detailed recommendations, auto-generated SQL validation queries, and coverage gap suggestions	Charged

Accessing the PR Agent

Automatic trigger

The PR Agent triggers automatically when a PR is opened in a GitHub repository that is in your allowlist. Configure which repos are enabled in Settings > Integrations > GitHub.

📘
The PR Agent requires the pr_agent feature flag to be enabled on your account. Existing GitHub integration customers need to reauthenticate to use this feature.

Manual trigger

Comment mc review on any PR in an enabled repo to trigger the agent manually.

Configuration

Configure the PR Agent in Settings > AI Agents:

Unrestricted — Full reviews on all PRs in enabled repos
Free-only — Free reviews only (risk score and summary, no detailed findings)

Validation notebooks

When the PR Agent detects dbt SQL changes, it can automatically generate a SQL Notebook containing targeted validation queries to verify the change behaved as intended. These queries cover null checks, distribution analysis, before/after row counts, and other verifications specific to the columns and logic modified in the PR.

CI Agent integration

The PR Agent's risk assessment feeds into the CI Agent, which can enforce merge gating based on the risk score. The CI Agent is available as a GitHub Action (monte-carlo-data/mc-prevent-action) or CircleCI orb (monte-carlo-data/mc-prevent-orb).

Gate policy options:

Policy	Behavior
`low+`	Block all PRs with any risk
`medium+`	Block medium and high risk (default)
`high+`	Block only high-risk PRs
`none`	Show results without blocking

Teams can add the mc-override label to bypass the gate for a specific PR.

Security & data privacy

The PR Agent reads code diffs from GitHub and correlates them with Monte Carlo metadata (lineage, alerts, monitor coverage). It does not access the actual data in your tables. For more detail on security and data privacy, see the AI Features and Technical Information documentation.