• Automated evaluations – Continuous monitoring gives you confidence in your performance and catches regressions as they happen
  • No-code interface – SMEs can run tests directly from Avido’s UI, placing responsibility where it belongs
  • Synthetic data testing – Reduces time to value significantly, allowing for faster roll-out to production
  • Powerful add-ons – Quickstart templates and RAG Optimizer save you time when building applications

Whether you’re building a support assistant, an autonomous agent, or a RAG pipeline, Avido gives you the safety net you need to move fast and sleep at night.

​
How Avido fits into your app

Diagram showing how Avido fits into your app

  1. Avido sends a webhook – When a test is triggered, Avido sends a POST request to your endpoint with synthetic input and a testId.
  2. You validate the request – Verify the webhook signature to ensure it’s really from Avido.
  3. Run your AI workflow – Process the synthetic input through your normal application flow.
  4. Log events along the way – Capture LLM calls, tool usage, retrievals, and other key steps.
  5. Send the trace to Avido – When your workflow completes, send the full event trace back to Avido.
  6. View evaluation results – Avido runs your configured evaluations and displays results in the dashboard.

​
Getting Started

  1. Install an SDK

    npm i @avidoai/sdk-node   # Node
pip install avido         # Python

  2. Setup a webhook endpoint in your application Learn more

  3. Start tracing events in your application Learn more

    client.ingest.create({ events })

  4. Upload existing data to auto-populate tasks Learn more

  5. Review your baseline performance in the dashboard

Prefer pure HTTP? All endpoints are documented here.

​
Core concepts

ConceptTL;DR
TestsAutomated runs of your workflow using synthetic input.
WebhooksAvido triggers a test with a POST. This allows us to do it automatically or through the UI.
TracesOrdered lists of events that reconstruct a conversation / agent run.
EventsAtomic pieces of work (llm, tool, retriever, log).
EvaluationsRules & metrics (naturalness, recall etc.) applied to traces.

Dive deeper with the sidebar or jump straight to Traces to see how instrumentation works.

​
Need help?

Happy building! ✨