Intro

What is it?

Root Signals is a measurement, observability, and control platform for GenAI applications, automations, and agentic workflows powered by Large Language Models (LLMs). Such applications include chatbots, Retrieval Augmented Generation (RAG) systems, agents, data extractors, summarizers, translators, AI assistants, and various automations powered by LLMs.


Key Features

Any developer can use Root Signals to:

  • Add appropriate metrics such as Truthfulness, Answer Relevance, or Coherence of responses to any LLM pipeline and optimize their design choices (which LLM to use, prompt, RAG hyper-parameters, etc.) using these measurements:

    • Log, record, and compare their changes and the corresponding measurements belonging to those

    • Integrate metrics into CI/CD pipelines (e.g. GitHub actions) to prevent regressions

  • Turn those metrics into guardrails that prevent wrong, inappropriate, undesirable, or in general sub-optimal behaviour of their LLM apps simply by adding trigger thresholds. Monitor the performance in real-time, in production.

  • Create custom metrics for attributes ranging from 'mention of politics' to 'adherence to our communications policy document v3.1'.

Dashboard

The dashboard provides a comprehensive overview of the performance of your specific LLM applications:

Main dashboard

Ready-Made Evaluators

Root Signals provides 30+ built-in, ready-to-use evaluators called Root Evaluators.

Root evaluators

Custom Evaluators

Utilizing any LLM as a judge, you can create, benchmark, and tune Custom Evaluators.

Custom evaluator for policy adherence

Monitoring

We provide complete observability to your LLM applications through our Monitoring view.

Monitoring view

Using Root Signals

Root Signals is available via

Root Signals can be used by individuals and organizations. Role-based Access Controls (RBAC), SLA, and security definitions are available for organizations. Enterprise customers also enjoy SSO signups via Okta and SAML.

Create a free Root Signals account and get started in 30 seconds.

Last updated