Platform
Developers
Resources
Feature Management
Ship faster and more confidently
Experimentation
Run 100s of randomized, multivariate experiments
Data Warehouse
Run experiments natively, in your warehouse
Analytics
Actionable intelligence at your fingertips
ROLES
Engineering
Ship features quickly and confidently
Dev Ops
Build with gates, configs, and more
Data Science
Automate experiment & metric computation
Product Management
Manage metrics & experiments in one place
VERTICALS
Artificial Intelligence
Launch & improve your AI applications
Gaming
Win big with data-driven decisions
B2B Saas
Drive growth with tailored experiments
E-Commerce
Unlock growth from visit to checkout
Documentation
Documentation to get you started with implementation, completely self-servable
Walkthrough Guides
Guides to get you started on your first Experiment, all the way to advanced Holdouts
SDKs and APIs
Explore REST API and Open Source SDKs in more than 20 languages/frameworks
Open Source Code
All our SDKs and supporting libraries are Open Source and regularly updated
Integration
Learn more about running on the edge, or ingesting data from your Data warehouse
Product Updates
We ship fast, to help you ship faster. Check out all our product updates
How Statsig Works
Get under the hood and check out how Statsig scales with you, without compromising on reliability
Build vs. Buy
Looking to build your own? We understand, and we'll gladly help you build it
Experimentation Community
Have more technical questions? Join the experimentation community, we're there to answer your questions
Peak Velocity
The Statsig Blog. Peak Velocity covers the latest in experimentation, A/B testing and more
Customer Stories
Find out how leading companies are leveraging experimentation to achieve awesome results
A/B Testing Calculator
Looking for a place to start your A/B test? Try different combinations in our calculators
Feature Flags Liberated
Gating features is a core part of the development process. And with Statsig, it's free.
Optimizing AI Model Temp
Autotune can optimize model temperature for any apps that use language models.
What is Product Observability?
Product observability means being able to monitor, control, and gain insight into all of your features.
Experiments with Generative AI
We built a generative AI app in reactJS using OpenAI’s API and Statsig. Here’s what we learned:
Experimentation Platforms
The decision to build versus buy an experimentation and feature flagging platform is not an easy one.
CUPED Explained
CUPED is an implementation that uses pre-experiment data to explain the variance in the result data.
Feature Management
Ship faster and more confidently
Experimentation
Run 100s of randomized, multivariate experiments
Data Warehouse
Run experiments natively, in your warehouse
Analytics
Actionable intelligence at your fingertips
ROLES
Engineering
Ship features quickly and confidently
Dev Ops
Build with gates, configs, and more
Data Science
Automate experiment & metric computation
Product Management
Manage metrics & experiments in one place
VERTICALS
Artificial Intelligence
Launch & improve your AI applications
Gaming
Win big with data-driven decisions
B2B Saas
Drive growth with tailored experiments
E-Commerce
Unlock growth from visit to checkout
Documentation
Documentation to get you started with implementation, completely self-servable
Walkthrough Guides
Guides to get you started on your first Experiment, all the way to advanced Holdouts
SDKs and APIs
Explore REST API and Open Source SDKs in more than 20 languages/frameworks
Open Source Code
All our SDKs and supporting libraries are Open Source and regularly updated
Integration
Learn more about running on the edge, or ingesting data from your Data warehouse
Product Updates
We ship fast, to help you ship faster. Check out all our product updates
How Statsig Works
Get under the hood and check out how Statsig scales with you, without compromising on reliability
Build vs. Buy
Looking to build your own? We understand, and we'll gladly help you build it
Experimentation Community
Have more technical questions? Join the experimentation community, we're there to answer your questions
Peak Velocity
The Statsig Blog. Peak Velocity covers the latest in experimentation, A/B testing and more
Customer Stories
Find out how leading companies are leveraging experimentation to achieve awesome results
A/B Testing Calculator
Looking for a place to start your A/B test? Try different combinations in our calculators
Feature Flags Liberated
Gating features is a core part of the development process. And with Statsig, it's free.
Optimizing AI Model Temp
Autotune can optimize model temperature for any apps that use language models.
What is Product Observability?
Product observability means being able to monitor, control, and gain insight into all of your features.
Experiments with Generative AI
We built a generative AI app in reactJS using OpenAI’s API and Statsig. Here’s what we learned:
Experimentation Platforms
The decision to build versus buy an experimentation and feature flagging platform is not an easy one.
CUPED Explained
CUPED is an implementation that uses pre-experiment data to explain the variance in the result data.
Enough talking from us
We'll let our customers do the talking now
At Notion, we're continuously learning what our users value and want every team to run experiments to learn more. It’s also critical to maintain speed as a habit. Statsig's experimentation platform enables both this speed and learning for us.
The Understood team chose Statsig for its fast integration and quick setup, which allows us to run more experiments and gives us confidence in data informed decision making.
...There's no way to ship things fast, safely without feature flags. ... The ability to conduct experiments, of course, is where feature flags shine the most. Statsig is a relatively new player in the space, but the team's responsiveness to feature requests and questions is what won us over.
From a technical perspective, the architecture is fantastic for handling scale and any potential outages of Statsig once the SDK has been initialized
The UI is intuitive and straightforward, and the documentation answered my questions. The prompts for an experiment force you (and your management) to think through what success and failure mean.
Statsig has solved both the feature management and our experimentation use cases. For feature management, we have been more confident while deploying, and it has cleaned up our code and implementation quite a bit since we've used Statsig. For experimentation, Statsig has provided us with an easy and comprehensive framework to just run our experiments without worrying too much about the setup.
Out of the experimentation platforms that I was looking at, Statsig is by far the most modern. The features that have been rolled out, the speed that new features are being rolled out, and the level of customization - it's the closest thing to a long term in-house built experimentation platform. Comparing this to the other platforms makes them seem just honestly like… dinosaurs.
As someone who worked at Facebook, it's easy to recognize how valuable A/B testing is, and how complex it can be. Statsig took the core principals from the Facebook internal testing systems, to the startups community, and they did it very grace and honor (as its free tier is amazing).
You can tell that Statsig is a tool built by qualified data scientists and engineers - it is intuitive, developer friendly and easy to implement. The help service is also incredible, with the support team just a slack away.
Statsig enables us to run large numbers of hypothesis tests of various forms with a tiny data team. We trust our results and that lets us move quickly through the product development process.
It is easy to set up experiments, collect the results and analyze the metrics. If needed, one can export their data and analyze it externally.
We have loads of A/B tests running concurrently, so it’s useful to have a dashboard to configure them.
It is insanely easy to get started with statsig. They support our frontend frameworks and our backend systems not just to feature flag, but to also conduct A/B tests.
Setting up our first feature gate was a breeze. Documentation is thorough and placed conveniently throughout the application to make learning new functionality relatively easy.
Statsig as a product is on point. It's easy to use and it provides the features we wanted without workarounds.
Brex’s mission is to help businesses move fast. Statsig is now helping our engineers move fast. It has been a game changer to automate the manual lift typical to running experiments and has helped product teams ship the right features to their users quickly.
Adoption was very easy. Multiple teams create experiments meaning we're reaching decisions easier and faster with Statsig.
Statsig pricing is significantly more favorable to startups where we have been able to run our experiments without worrying about breaking the bank.
I know Firebase has had some updates recently, but the wealth of features Statsig offers, as well as its intelligence and accuracy for A/B testing results, makes it well worth the switch!
We use Statsig for A/B testing in scale, connected to our Mixpanel events, making it extremely easy and powerful
We chose to partner with Statsig because we believed in what their team was building. The Statsig team has been there every step of the way, from implementation to understanding results. They are building something special and we are excited to be apart of the journey!
I know that what Statsig’s building is on par with and meant to be comparable to a large consumer scale, massive application. That’s what we’re moving towards so this partnership makes sense.
Statsig has enabled Numan to move and test at a lightning pace.
I know that for our key business metrics, we are able to impact them in a positive way with Statsig. Directionally, I can say that we're heading in the right direction with Statsig.
Statsig is solving the ability to A/B our consumer checkout process, so that we can accurately measure, test and validate optimizations. We have just started with this program but feel that Statsig fully fulfills our needs.
Statsig helped our team determine the specific impact of features in ways we could only estimate before. Now, we can communicate to business the value we bring with each feature.
What I like best about Statsig is the real time insights into how changes in our product our impacting our funnel. It makes it very clear when an experiment has changed a metric. Stastig helps me test new product offerings without committing to a full roll out. It also gives me greater confidence when making changes to critical parts of out order flow that if there is an unforseen bug we can roll something back.
We chose Statsig to build a culture of experimentation it allows us measure the business impact of changes we shipped; we’re no longer limited to deciphering insights based on pre/post trends and have meaningfully increased both the quantity and quality of tests we can support. This is important as we design products, platforms, and algorithms to improve clinical outcomes and give our patients and providers the best experience with in-home medical care.
Fast-moving product, super responsive team!
I love being able to drill to the daily level of the trends, run reports using the metadata, and having control over metric aggregations as well as how our events are propagated.
We’re just getting better at it. There’s conversations around best practices to figure out what’s working, the whole conversation Statsig is not just for tests, it’s everything we’re shipping in general.
Statsig has helped us to follow the experiments, raise the feature gates and achieve dynamic configurations.
Our experiments are at times nuanced and Statsig has enabled us to quickly understand the impact of the features we ship. This speed to understanding removes the need for guesswork in analyzing the data, and in the end helps us improve our customer's experience faster.
The most helpful aspect of Statsig is that rather than complicating and diluting their platform by attempting to solve every development problem, they've focused on one widespread pain point in software development and created a comprehensive, intuitive solution that simplifies the process of feature access management.
At WeQuilt, we are building a new kind of social network and Statsig has removed the guesswork on what causes our business metrics to move on a daily basis. With Statsig, our team can now create experiments within minutes and get a full picture of how our users are responding at a speed like never before.
The first thing that made us see we need something like Statsig is the need for feature gates to really separate who is going to see a new feature and who is not going to see a feature. That’s super useful for us. Experimentation was a plus.
With Statsig, you’re able to see more, and more clearly. That comes from the tool itself when but there’s also the experience itself that flows into the info you actually end up getting.
We greatly appreciate their sequential analysis engine and BigQuery ingestion that allow us to create a full view of how our new features are benefiting the lives of our patients and help us ship high impact features without waiting for full test durations.
Statsig is modern, easy to use, and has great customer support. The ability to turn any feature gate into an experiment is incredibly powerful -- it takes all the guesswork out of feature rollouts.
We have been using Statsig for 4 months now, having migrated from LaunchDarkly and it's been critical to the adoption of more intelligent experimentation. The product offering is vast while being simple enough to use for small experiments and the analysis options are extensive. We use feature gating and experimentation at large now as a result of adopting Statsig.
Statsig checked all my requirements when evaluating it. It has good documentation, many SDK options, and a clean dashboard UX. From my experience, they blow the competition out of the water. The best part is an entirely self-serve signup process without the need to talk to sales reps or sign enterprise contracts.
Statsig is the best experimentation platform I’ve used
Statsig is our primary A/B testing tool. It has enabled us to better refine how we approach feature launches and changed how we talk about success of features within our business. It has helped us lean into a culture that values real results.
The platform is simple to use and implement into our products. It provides powerful testing solutions that have improved our core business metrics.
I've been super happy with using Statsig and would recommend it to anyone in the industry.
Statsig makes it easy to create and analyze experiments and features. This enables shipping software 10x faster, each feature can be in production from day 0 and no big bang releases are needed, each feature can then be A/B tested and the results analyzed and see the impact on important metrics
Statsig provides out of the box all the important metrics a company need by just installing the SDK. With all the metrics in one easy-to-find place, Statsig then provides all the instruments to meaningfully move those metrics through experiments, making it incredibly easy to create, analyze, and roll out. If all of that wasn't enough, Statsig provides some incredible tools like dynamic configs that make it easy for the company to move faster and focus on what matters.
We started to create a homemade experimentation platform because we were frustrated by the features of mainstream A/B testing tools. However, developing and maintaining such a project requires a dedicated team with many resources. Thanks to Statsig, we could stop our project's maintenance. Analyzing an experiment is very fast. We can manually break down metrics and do group-by / filters operation within the user interface.
Statsig helps us move in the right direction. We are able to see which features are improving our UX and which ones not so much, so we as a company can spend our limited resources where it matters most.
Statsig is a powerful driver of data-driven development
Working with the Statsig team feels like we’re working with a team within our own company
The team is top-notch and incredibly responsive/helpful. They are very agile, execution-oriented, and genuinely care/listen to users/customers.
Statsig lets us measure the effectiveness of product increments by releasing with A/B tests first. We can use custom metrics to measure the impact of new features and they even help you estimate how long it will take to reach significance given historical data. It's a powerful yet easy-to-use platform.
Excited to bring Statsig to Whatnot! We finally found a product that moves just as fast as we do and have been super impressed with how closely our teams collaborate.
Statsig allows us to run continous sequential A/B tests that require numerous metric criterias. It would be daunting to do it by hand.
I love the features statsig has to offer and how easy it makes it for engineers and product to work together to enable features behind flags!
Statsig is lightyears ahead of other feature gating and experimentation tools on the market. It's clearly built by people who've done this before at scale!
If I go to Statsig, I see a bunch of experiments and a bunch of tags being created. So you can really see that people are starting to use it for everything that they're doing. Any new feature that they are launching, any new experiment that they are launching, they're using Statsig.
Statsig allows us to run A/B experiments on our product. We use it to ensure variants are shipped evenly to the right user cohort. We also use it to understand whether a variant performs better than others.
Statsig is my most recommended product for PMs
We have been very unsure about certain language/copy on our website, Statsig helped us quickly land on the right choices. Rather than getting caught up in meetings debating what is best, our users made the decision because of Statsig.
While using Statsig, some features we wanted were missing regarding metrics, but the team was very responsive via Slack to answer questions and later on deliver the requested features. As the Statsig product matures, it seems like the team is quickly building out more and more features.
Statsig is a game changer!
Statsig takes away all the pre-work of doing experiments. It's really easy to setup, also it does all the analysis. I and most data scientists know the pain of doing this work manually. Statsig takes away all the hard work of doing experimentation, and also does the nice part of seeing what's increasing or decreasing.
Statsig is user friendly, which is missing from most of the experimentation tools out there like Split. We are using Statsig for feature management, segment management, and logging user patterns.
Statsig has been a game changer for how we combine product development and A/B testing. It's made it a breeze to implement experiments with complex targeting logic and feel confident that we're getting back trusted results. It’s the first commercially available A/B testing tool that feels like it was built by people who really get product experimentation.
The main reasons we chose Statsig were: it had the best UI that was easiest to understand, its flexibility of API integrations so that it could work across all our product platforms, and the background of the team.
As we searched for a partner to help us with our growth efforts, we needed someone who could provide fast results and insights for us to be able to quickly iterate, which is why we decided to go with Statsig.
After evaluating alternatives, we chose Statsig because of its incredibly low cost of entry, ease of implementation, and the exciting idea that the same tool we use for feature flags can also be extended into A/B testing and other customization. With very minimal effort, we had Statsig code implemented and were granularly managing the staged rollout of one of our new features. We've had no issues, and I'm excited to continue using it for feature flagging and growing into using it for A/B testing and the even more robust statistical analysis functionality Statsig already has and is continuing to develop.
Unless you have >5 engineers + 1 Tech Lead with experimentation expertise + 1 year to roll your own experimentation, you're more likely better off using Statsig.
Great data visualizations: Confidence intervals are so often misunderstood, having them visualized is wonderful.
My team has been using Statsig for over a year now and we find it's such an easy way to run A/B tests. It's efficient for both product and eng and super simple to ship the winning version.
I've got to say - I'm very very impressed with Statsig's responsiveness to questions and issues we've raised. Gives me a lot of confidence that this is going to be great partnership.
Statsig simplifies the process of creating and managing access to new in-development features.
Allows measuring incremental changes to our product through A/B tests. Previously we were using firebase experiments, which had a limitation of running separate experiments for iOS and Android and required us to combine results manually. Statsig helps us run them as a single experiment and provides powerful metrics to easily measure impact.
The more features or improvements we can test, the better our product becomes. Statsig has helped us go live with tests at a very quick rate and allows us to monitor the results.
Statsig helps us with the ingestion of events and numerical data from BigQuery to run experiments that cover numerous functions within a healthcare organisation.
The fact that Statsig offers feature gating for free is huge - this is something competitors charge thousands of dollars for. There's no reason not to use Statsig!
We plan to use Statsig for any new major feature releases. The beauty is that the tool allows us to both run experiments, but also track the impact of feature releases.
Statsig is the best option for startups!
Having a culture of experimentation and good tools that can be used widely by cross functional teams is business-critical now. You simply will not survive as a technology company without them. Statsig was the only offering that we felt could meet our needs across both feature management and experimentation. The support we’ve had from their team so far has also been a huge value add.
Statsig enables our entire product development team to easily understand the results of hypothesis tests without a data scientist/analyst needing to interpret, negates the danger of peeking, and makes it easy to double click on interesting results. It makes our process faster, more trustworthy, more collaborative, and more thorough.
Our primary uses for Statsig have been marketing funnels and game feature optimization. We have seen a measurable improvement to our product KPIs.
Statsig helped to optimize our games for higher retention and revenue.
Feature flags are just the beginning!
Statsig manages my organization's feature flags. It’s very easy to define a feature flag that depends on certain properties. Also, it was very easy to show other users how to use it.
An excellent experimentation platform!
Nearly every time I log into Statsig, there are new features to play with
We needed to quickly turn off some features for a portion of our userbase. Statsig was by far the quickest way to make that happen. We almost always feature flag new features through statsig now to get better data around the efficacy of said features.
Feature gates and experiments are quick to set up and run. There is a lot of customization that can be done in both to be able to create any needed features/tests. We are able to set up quickly test new features and ensure we are not hurting our current app and making improvements before releasing the new feature to everyone.
Setting up experiments is straightforward. The advanced options are powerful, and we defined experiments with custom exclusion criteria and mutually exclusive tests. The results view sums up everything essential to decide the best variant to ship. The real-time debugging panel is a friendly tool for ensuring everything is set up correctly.
Tavour helps fill your fridge with unique, craft beers you can’t find locally. We chose to partner with Statsig because it gives Tavour best in class feature flag management combined with unparalleled A/B testing.
As a data scientist who uses Statsig primarily for setting up and analyzing product experiments, the platform makes experimentation straightforward. The UX is clear for both technical and non-technical users, and it's easy to set up and understand metrics of interest. I like the ability to tag critical metrics and add these groups to any relevant experiment.
Statsig integrates with our events to tell us which AB Test runs best, and you can apply the winner directly to your production site in a few clicks!
I’ve been really impressed with Statsig. Some people in our company questioned the results of a test, so I asked Statsig to do an A/A test to make sure the control groups were balanced. It turns out they were already doing that in the background and could see how many metrics were false positives at a 95% confidence interval.
We're innovating at a rapid pace at Tempo, and we need an experimentation platform that is both robust and moves at our speed. Statsig's nimble and responsive team, combined with their simple-yet-powerful platform, make them a natural fit for us.
The ease of use and analysis is unmatched by existing solutions.
Statsig makes experimentation easy!
Statsig's product focus is exactly what my company wanted when we looked for a new experimentation platform. The features make sense and almost all of them add value for my company.
We need to roll out some features to customers slowly, and we are using Statsig to test the parts first in the testing environment and then to a small percentage of the users to ensure everything is fine. Statsig is helping in controlling the rollout of the features and as a quick shut-down in case of failure.
Statsig provides a experimentation platform, allowing us to roll out new features behind gates. Aata visualization and reporting can be easily understood across different stakeholders.
Try Statsig Today
Easy to start, simple to collaborate. It's for your whole team!
What our customers say about us
“Statsig gives Tavour best in class feature flag management combined with unparalleled A/B testing.”
Tavour
Philip Vaughn
Founder
“Statsig has enabled us to quickly understand the impact of the features we ship.”
Headspace
Shannon Priem
Lead PM
“It has been a game changer to automate the manual lift typical to running experiments.”
Brex
Karandeep Anand
CPO