LangChain and CrewAI - DataVibe Documentation

Use preview checks for pure output inspection. Before an email, CRM, payment, or other side-effecting tool runs, create a persisted gate submission.

LangChain output callback

The TypeScript SDK exposes DataVibeCallbackHandler for observing model output. A callback preview does not create human review work. Use intercept() before executing a side effect.

const proposedEmail = await draftChain.invoke(input);
const gate = await datavibe.intercept({
  recipient,
  subject,
  body_text: proposedEmail.content,
  body_html: `<p>${proposedEmail.content}</p>`,
  source_model: modelName,
  idempotency_key: toolCallId,
});

if (gate.status !== "APPROVED") {
  throw new Error(`Hold side effect: ${gate.status}`);
}

await emailTool.invoke(proposedEmail);

CrewAI preview

preview = client.check(proposed_text, content_type="agent_action")

For asynchronous preview use await client.acheck(...). If the verdict requires review, submit the final action through intercept() or intercept_async().

Never read review_url from a preview result. Stateless checks do not create an action or review record.

Last modified on July 23, 2026

⌘I

​LangChain output callback

​CrewAI preview

LangChain output callback

CrewAI preview