AI-written lines
Which code lines were created or changed by a MergeLoom AI run.
Audit the actual code written by MergeLoom AI runs.
MergeLoom records line-level audit evidence for AI work routed through the platform, so teams can inspect which code was written by MergeLoom, who requested it, why it ran, and when it happened.
Works with
Jira GitHub GitLab M monday.dev Linear Azure Boards Azure Repos
Jira GitHub GitLab M monday.dev Linear Azure Boards Azure Repos
Jira GitHub GitLab M monday.dev Linear Azure Boards Azure Repos
Jira GitHub GitLab M monday.dev Linear Azure Boards Azure Repos
AI job
Which job produced the change and where it ran.
Ticket
Which approved work item authorized the code change.
Requester
Which user requested the AI implementation.
Validation
What checks ran before the review request was opened.
Audit AI-written code
For work routed through MergeLoom, teams can trace AI-written lines back to the requester, ticket, date, validation, provider, and run.
Line-level evidence
See which lines were created or changed by MergeLoom AI runs, then drill from repository metrics down to the code itself.
Who asked and why
Tie the AI-written code back to the requester, ticket or issue, date, validation result, provider, worker, and PR or MR.
Close the attribution gap
Avoid commits that look purely human when AI was involved, giving security and compliance a clearer record of AI-assisted code.
Attribution works best when AI coding has a required path
MergeLoom can only provide strong attribution for work routed through its workflow.
That is why the product is designed as a required path from approved ticket to PR or MR, rather than another unmanaged local assistant.
Approved request
The ticket, issue, or task remains attached to the AI code change.
Initiating user
The run is connected to the user who asked MergeLoom to perform the work.
Worker and provider
Where the run executed and which provider configuration it used are part of the evidence trail.
Validation and review
Checks, review output, and the produced diff become part of the run record.
Trace every run
Connect tickets, PRs or MRs, agent logs, validation, self-review, diff guard, and generated code in one audit history.
Ticket to PR trail
Move from the original ticket or issue to the PR or MR, branch, validation result, review output, and produced diff.
Run logs and outcomes
Inspect what the agent did, which review items it found, whether validation passed, and whether diff guard warned.
Drill into code
Start with repository-level AI code metrics, then drill into the exact MergeLoom run and code change behind them.
Runs with
CX Codex Claude Vertex AI AWS Bedrock AZ Azure Foundry API OpenAI-compatible
CX Codex Claude Vertex AI AWS Bedrock AZ Azure Foundry API OpenAI-compatible
CX Codex Claude Vertex AI AWS Bedrock AZ Azure Foundry API OpenAI-compatible
CX Codex Claude Vertex AI AWS Bedrock AZ Azure Foundry API OpenAI-compatible
See what else MergeLoom can do.
Connect more of your stack, improve context, validate output, and keep audit evidence across every AI coding run.
Try one controlled AI coding workflow.
Start with one tracker, one repository, and one validation path before rolling AI coding across the team.