Govern AI agents on LangChain
Substitute Cordum-governed tools into your LangChain agent. The adapter builds LangChain tools from the Cordum tool path and routes each call through Cordum, so every tool invocation is evaluated by the Safety Kernel before it dispatches and logged for audit compliance.
What this pack does
- Pre-dispatch policy evaluation on every governed tool call
- Approval gates for high-risk tool invocations
- Drop-in governed tools built from the Cordum tool path
- Full audit trail of agent tool calls and decisions
Use cases
Require approval before LangChain agents execute database writes
Block agents from calling sensitive tools without policy clearance
Audit all tool call decisions in production LangChain agents
Quick setup
- 1Install the LangChain adapter: pip install cordum-adapters
- 2Build Cordum-governed tools and add them to your agent
- 3Define tool-level policy rules
- 4Run your agent with the governed tools in place
Frequently asked questions
How does Cordum govern LangChain tool calls?
The adapter builds LangChain tools from the Cordum tool path and substitutes them into your agent. Each call routes through Cordum, where the Safety Kernel evaluates it against policy before dispatch and returns Allow, Deny, or Require Approval, so a tool only runs if your policy permits it. There is no separate callback handler to install.
Can I require approval before an agent writes to a database?
Yes. Define tool-level policy so high-risk invocations, such as database writes or destructive API calls, return a Require Approval decision. The governed tool pauses on that call until a reviewer approves, while low-risk tools continue uninterrupted.
Does Cordum check the output of a tool, not just the call?
Output safety is handled by the Cordum platform's output policy, not the LangChain adapter itself. When a governed tool runs through Cordum, successful results can be scanned and allowed, redacted, or quarantined by output policy before they are returned, guarding against leaking secrets or PII.
What is captured for a production LangChain agent?
Cordum records a full audit trail of the agent's governed tool calls and the governance decision on each, giving you a reviewable history of what the agent attempted and what policy allowed. That makes it practical to run LangChain agents under compliance requirements.
Ready to govern LangChain?
Other integrations
Approval notifications and agent alerts in Slack channels.
Govern AI agent actions on GitHub repositories.
Govern AI agent read and write actions against the AWS API.
Governance for AI agents managing Jira workflows.
Govern AI agents responding to Kubernetes incidents.
Feed Datadog alerts into governed agent workflows.