Getting started

Connect any AI workflow to Tracira in minutes. You need a token and one HTTP call.

Tracira is a quality and safety layer for your AI automations. Send the output of any AI step to Tracira, it evaluates that output against your rules, and flags anything that needs a human to approve or reject before it reaches your customers.

You connect in one of three ways:

Make: native Tracira app, no HTTP setup required.
n8n: built-in HTTP Request node plus an IF node to branch on the verdict.
Any HTTP client: Zapier, Pipedream, custom scripts, or your own server.

Quickstart

Create a free account

Copy your webhook token

Open the Integrations tab in your workspace and copy your token from there.

Define a rule

Go to Rules and write a plain-English rule, for example "Flag if the response mentions a discount over 20%".

Send your first output

POST the AI output to the webhook. You get a log ID back immediately; evaluation runs in the background.

cURL

curl -X POST https://tracira.com/api/logs \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "project": "my-first-project",
    "output": "Here is my AI-generated response."
  }'

Response

{
  "ok": true,
  "id": "b1c2d3e4-0000-0000-0000-ffffffffffff",
  "status": "pending"
}

Tip

Pass sync: true to receive the verdict inline. Useful when you need to gate or continue a workflow based on the result.

What you get back

Every request returns a log id immediately. By default status is pending and evaluation runs in the background. Pass sync: true to hold the connection open and receive the verdict in the same response: pass means all rules passed, flagged means at least one rule triggered.

Next: pick your integration, or jump to the full API reference.