Root Signals Docs
  • Intro
  • QUICK START
    • Getting started in 30 seconds
    • Evaluator Portfolio
  • OVERVIEW
    • Why Anything?
    • Concepts
  • USAGE
    • Usage
      • Models
      • Objectives
      • Evaluators
      • Judges
      • Datasets
        • Dataset permissions
      • Execution, Auditability and Versioning
      • Access Controls & Roles
      • Lifecycle Management
    • Cookbook
      • Add a custom evaluator
        • Add a calibration set
      • Evaluate an LLM response
      • Use evaluators and RAG
      • Connect a model
      • SDK Examples
      • Poker app
  • Integrations
    • Haystack
    • LangGraph
    • LangChain
    • LlamaIndex
  • Frequently Asked Questions
  • Breaking Change Policy
  • RESOURCES
    • Python SDK
    • Github Repo
    • REST API
    • Root Signals MCP
Powered by GitBook
On this page
Export as PDF
  1. OVERVIEW

Concepts

PreviousWhy Anything?NextUsage

Last updated 9 days ago

Root Signals design philosophy starts from the principle of extreme semantic rigor. Briefly, this means making sure that, for example

  • The definitions and references of entities are tracked with maximal (and increasing) precision

  • Entities are assumed long-term and upgradeable

  • Entities are built for re-use

  • Changes will be auditable

Objective defines what you intend to achieve. It grounds an AI automation to the business target, such as providing a feature ('transform data source X into usable format Y') or a value ('suitability for use in Z').

Evaluator is a function that assigns a numeric value to a piece of content such as text, along a semantically defined dimension (truthfulness, relevance of an answer, coherence, etc.).

Judge is a stack of evaluators with a high-level Intent.

Model is the AI model such as an LLM that provides the semantic processing of the inputs. Notably, the list contains both API-based models such as OpenAI and Anthropic models, and open source models such as Llama and Mistral models. Finally, you can add your own locally running models to the list . The organization Admin controls the availability of models enabled in your organization.

with ease