--- title: "Use cases · SourceAnt" description: "Share skills, trace requirements, review changes across repositories, preserve engineering context and triage incoming work with SourceAnt." url: "https://sourceant.ai/use-cases/" --- Use cases # Once the system is on the record, these stop being projects Share how your team works, connect requirements to evidence, and review changes with context from across your system. Find the workflow you need and the capability behind it. ## Find your use case [ Shared team skills ### Maintain the same instructions across repositories Share a workspace skill, adapt it where a repository needs an exception, and use it from an MCP-connected coding tool. Workspace skills and repository overrides Read it ](https://sourceant.ai/skills)[ Requirements traceability ### Find requirements that still need implementation or test evidence Organise requirements into groups and connect them to code and tests. See where links are missing before treating a requirement as covered. Recorded links and coverage Read it ](https://sourceant.ai/requirements)[ Cross-repository review ### Review a change against the services that depend on it Use the system map to follow a change beyond its repository. Read findings alongside the limits of which repositories the review could access. Systems and cross-repository reviews Read it ](https://sourceant.ai/systems)[ Code review ### Check a change against the reasons behind the code Bring recorded decisions and constraints into review. Read findings on the pull request or follow their evidence in Lens. Pull request reviews and Lens Read it ](https://sourceant.ai/code-review)[ Context across sessions ### Keep the next coding session from losing what you learned Record decisions, constraints and workarounds beside the code they explain. Let teammates and MCP-connected tools retrieve that context for later tasks. Knowledge capture and MCP retrieval Read it ](https://sourceant.ai/knowledge-graph)[ Issue and pull request triage ### Catch duplicate reports before the backlog grows Compare incoming issues and pull requests with open work. Flag possible duplicates and apply labels from the repository’s existing set. Available through the Repo Manager plugin Read it ](https://sourceant.ai/issue-triage)[ Self-maintaining architecture record ### An architecture record that tells you when it has aged Read from the manifests your repositories publish, proposed rather than asserted, approved by a person, and marked stale when it stops matching the code. In the open core Read it ](https://sourceant.ai/use-cases/architecture-record)[ Contract drift ### A spec diff tells you something broke. It cannot tell you who breaks. A published interface versioned and compared against its baseline, joined to the services that declare a dependency on it, so the blast radius comes with the finding. Interfaces in the open core Read it ](https://sourceant.ai/use-cases/contract-drift)[ Onboarding ### Onboarding used to happen twice a year. Now it happens every hour. A new engineer and a new agent session ask the same questions and neither can read the answer out of the code. Both get it from the same records. In the open core Read it ](https://sourceant.ai/use-cases/onboarding)[ CVE monitoring ### A vulnerable package is installed. Does anything here call it? Advisories from the same database Dependabot reads, then checked against the code graph, so what you never call is not filed next to what you run on every request. In the open core Read it ](https://sourceant.ai/use-cases/cve-monitoring)[ Supply chain naming ### Your internal package is called acme-auth. So could anyone else’s. Every inferred dependency carries how sure SourceAnt is that it resolves to you, which makes the edges resting on an unowned name a filter rather than an audit. In the open core Read it ](https://sourceant.ai/use-cases/dependency-confusion) ## The same graph answers a few more These do not have pages of their own yet. They are the same traversal with a different question on the front of it. - Decommissioning, where nothing inbound is the answer you needed - Audit evidence, where every part cites the file it was read from - Extension points, where a manifest declares what it plugs into [How Systems works](https://sourceant.ai/systems)