Never let a signup go cold again.
Turn emails into revenue with Brew. No credit card, free credits to try.
Turn emails into revenue with Brew. No credit card, free credits to try.
growthbook.io · newsletter
Explore this email design and adapt it to your own brand. Review the copy, links, and offer before sending.
GrowthBook logo
Hi there,
Our largest release to date, GrowthBook 4.4, is here!
This release introduces capabilities that help product teams move fast while maintaining control across the entire experimentation and feature flagging lifecycle.
Highlights include automated ramp schedules with approval controls for safer rollouts, a fully programmable experiment lifecycle, and an AI Data Analyst for self-serve analytics.
Version 4.4 is available immediately to both our cloud and self-hosted users.
Read on for highlights or get the details at GrowthBook's blog.
Read Blog
Experimentation: An API-first lifecycle
With GrowthBook 4.4, you can run the full experiment lifecycle programmatically, working with agents at every step from setup to decision. The REST API was rebuilt on Zod-driven endpoints, making the experiment lifecycle a fully programmable workflow.
Agents can set up and launch experiments from templates that encode your organization's standards: statistical methods, metric selection, guardrails. An agent can pull the pre-launch checklist to verify metrics, variations, and targeting, plus any manual checks before launch.
Observe experiments at the scale of your program, making a single API call to return estimated completion times, metric direction, and any guardrail issues for every experiment at once.
Reports are now a first-class API resource. An agent can build a persistent analysis, read results against your decision criteria, and conclude the experiment by setting the winner and analysis summary in one call.
Watch the demo video below on how you can execute the full end-to-end experiment workflow using Claude Code and GrowthBook.
Play
AI Data Analyst (beta)
The AI Data Analyst is a conversational AI assistant for Product Analytics. Ask a question in plain language, like “What’s our DAU trend by country” and get back charts and insights built with tooling specific to GrowthBook’s metrics, fact tables, and data sources. Product managers, marketers, and others can self-serve their questions without writing SQL or filing tickets with the data team.
It's in beta, and we want to hear how you're using it. Ask it real questions, try out your actual workflows, and tell us where the friction is.
Explorations
GrowthBook’s Explorer lets you create charts (Explorations) from your warehouse data through a visual interface. Select your metric, dimensions, and date range to generate a chart that you can share or save. Or run the same exploration over the API and get the chart data back, plus a deep link to open it in GrowthBook.
Product Analytics over MCP and API
Every exploration is now addressable through the MCP server and REST API. Queries run the same way whether they come from a person clicking through the UI or an automated workflow calling the endpoint.
Bandits without sticky bucketing
Multi-armed bandits fit when you want continuous learning and traffic reallocation without the time cost of a full A/B test. They are now easier to set up, no longer requiring sticky bucketing. We expect that teams building AI-powered products will use them extensively.
Release plans with ramp schedules
Targeted releases now include automated, time-based rollouts with fine-grained controls and optional approval steps. With monitored ramp schedules, you can attach guardrail metrics and automatically hold, advance, or roll back releases. With reusable templates, teams codify standard rollout shapes they want to apply to new features quickly.
Revisions and approval controls
Approval flows are built directly into the flag change lifecycle, with REST coverage (in beta) for revisions, reviews, and approvals. The same guardrails apply whether the change comes from a teammate or an automated process.
Automated stale flag cleanup
This release adds an endpoint for stale flag detection, which lets an AI agent run an entire cleanup process. An agent or tool can pull stale flags by API, provide a reviewable list, then find and clean up flag references in your codebase as you decide what to remove. Automating the cleanup process removes a major source of compounding debt, especially for large enterprise teams.
If you're using GrowthBook cloud, you already have the latest version. Self-hosted users can update with these instructions. To upgrade from Pro to enterprise, please contact us.
A big thanks to all of our users who reported bugs, shared feedback, and contributed ideas to this release on GitHub or Slack. We're excited to see what you build.
– The GrowthBook Team
Manage Subscriptions
©2026 GrowthBook
1950 West Corporate Way, Suite 34560
Anaheim, CA 92801
United States
Unsubscribe
