Custom API

Choose Custom API if your AI system has its own URL that accepts inputs and returns responses, and it’s not built on Flowise or n8n. This works with any system — whether it’s built with LangChain, your own code, or any other framework.

Setting up your connection

1. Create the platform

   Go to your project, click Add Platform, and select Custom API.

2. Enter the endpoint address

   Paste the URL where your system receives inputs. This is the endpoint Mibo will send test messages to.

3. Choose the request method

   Select how inputs should be sent — usually POST. If you’re not sure, POST is the right choice for most systems.

4. Set up authentication (if needed)

   If your system requires credentials, choose the type:

   • Bearer Token — a single secret key that Mibo sends with each request.
   • Custom Headers — name-value pairs for more complex authentication setups.
   • None — your system is open and doesn’t require authentication.

5. Configure the message template

   This tells Mibo how to format the input sent to your system. The template includes a special placeholder that gets replaced with each test input.

   Mibo provides a default template that works for most systems. If yours expects a different format, you can customize it here.

6. Set the response path

   Tell Mibo where to find the text reply in the response. For simple systems, this is often just “text” or “response” — the name of the field that contains the answer.

7. Test your connection

   Click Test Connection to verify everything works. Mibo will send a quick input and show you the result.

Trace collection

Traces capture what happened inside your system during a test — which tools it called, what data it used, and the steps it took to build a response. Traces are optional, but they enable deeper analysis like the Failure Matrix.

You have two options for collecting traces:

Included in the response (Inline)

Your system already includes trace data alongside its answer. You just tell Mibo where to find it in the response by specifying the path to the trace field.

This is the simplest option if your system supports it.

Sent separately (Push)

Your system sends trace data to Mibo separately, after responding to the input. Mibo waits for it to arrive before completing the evaluation.

This works well for systems where trace data is generated asynchronously or by a separate service. You can configure how long Mibo should wait for the trace to arrive.

Note

Traces are optional. Mibo can still evaluate responses without them — you’ll get AI Judge scores and pass/fail results. But without traces, the Failure Matrix and stage-level analysis won’t be available.

Troubleshooting

• “Connection failed” — check that the URL is correct and your system is running. Make sure there are no typos in the address.
• “Authentication error” — verify your token or headers. The most common issue is a missing or expired key.
• “Empty response” — the response path might be wrong. Check what field name your system uses for its text reply.
• “Timeout” — your system is taking too long to respond. Check if it’s under heavy load or if the endpoint is correct.