---
title: "Welcome to Evidential"
---

> Documentation Index
> Fetch the complete documentation index at: https://docs.evidential.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Welcome to Evidential

<video src="https://media.evidential.dev/docs/evidential_demo_20250709.mp4" poster="/media/evidential-demo-poster.webp" preload="none" controls width="100%" title="Evidential onboarding video"></video>

## What is it?

A free, open-source experiment engine built by and for nonprofits—putting rigorous, rapid learning in every organization’s hands.

## Get started

- **Read the quick-start guide** — Connect your data and run your first experiment.
- **Join the early-partner program** — Get in touch to start experimenting with our support.
- **Contribute on GitHub** — Evidential is open source.
- **Develop Evidential** — Set up a local development environment.

## Why Evidential?

Nonprofits are hungry for rigorous evidence, yet most teams lack the technical or financial bandwidth to test ideas quickly. Evidential lets social-sector organizations create, run, and learn from experiments with ease, speed, and no cost.

## Who is it for?

Evidential is built for nonprofits that are keen to test and learn. It is ideal when:

- You’re delivering a digital or hybrid intervention
- You have visibility into your user journeys, feedback, and behavior
- You know what outcomes you care about
- You have ideas worth testing
- But you lack the bandwidth, technical or financial, capacity to experiment rigorously on your own

## What makes it different?

- **Built for the social sector** – our roadmap is steered by a few mission-driven orgs, not by Fortune-500 advertisers
- **Free & open-source** – use our managed cloud in minutes or self-host for full control
- **Impact-first metrics** – it measures your users’ behavior change and program outcomes, not vanity clicks
- **Complex multi-source programs** – turn your various data sources into metrics once, then run experiments indefinitely
- **Hands-on support** – we guide you through hypothesis design, metric pipelines, launch and analysis, so you focus on learning what works, not on engineering

## Key Features

- Intuitive UI to create and monitor experiments
- A single dashboard centralizing all your lessons learned
- Compatible with both your Data warehouse and Event engines
- Multiple methods: frequentist A/B, Bayesian, Multi-armed & Contextual bandits
- Comprehensive API to manage experiments programmatically
- Integrations with the main messaging and survey platforms used by nonprofits

## What is it not?

Evidential is not a product analytics tool, and it’s not built for full-scale Randomized Control Trials.

If you operate a single web or mobile app and want deep behavioral analytics, tools like Mixpanel or Amplitude are a better fit. These platforms assume a product and engineering team, and a substantial annual budget.

Likewise, if you're planning a one-off RCT with full counterfactuals and enumerator-managed arms, you’ll need a different setup.

Evidential shines when you want to continuously improve your complex program against its current version—10X faster than an RCT, but preserving its rigour.

## What kind of ideas can I test out?

Here are some ideas our early partners have tested out:

- Does the personalized AI response lead to better user engagement?
- Does using a casual tone with younger users lead to higher completion rates?
- Does reducing the number of questions asked during onboarding lead to lower drop-off rates?
- What is the best time to send messages to ensure users engage with it?
- Will this new feature lead to greater time spent on the platform?

## Who are we?

Evidential is a collaboration between [IDinsight](https://www.idinsight.org) and the [Agency Fund](https://www.agencyfund.org)—two teams that heard the same need: make experimentation painless for nonprofits.

We combined complementary approaches into one shared platform ([read the blog](https://theagencyfund.substack.com/p/evidential-a-new-experiment-engine)). Our team includes data scientists, engineers, and product designers with decades of experience building tools for both commercial and social sectors.

## Acknowledgements

A heartfelt thank‑you to [Rocket Learning](https://rocketlearning.org/) for serving as our earliest – and bravest – testing ground and design partner. Special thanks as well to [Noora Health](https://noorahealth.org/), [myAgro](https://www.myagro.org/), [Jacaranda Health](https://jacarandahealth.org/) and [Saajha](https://www.linkedin.com/company/saajha/?originalSubdomain=in) for trusting us to run experiments together and for their invaluable feedback along the way.

:::note
Want to learn more? Email us at [support@evidential.dev](mailto:support@evidential.dev).
:::

Source: https://docs.evidential.dev/index.mdx
