Free Trial
Added on Nov 11,2026
Wren by Seldon is an AI-powered QA testing tool that runs end to end browser tests from plain-English descriptions using agents guided by behavioural models.
Instead of scripting each browser action, you describe the test in a sentence or two, including where to start and what a successful result looks like. Wren then runs your tests in parallel.
Seldon's behavioural models guide what each agent tries next. Agents choose their next step based on what they see, so if a button gives no feedback an agent might retry or look elsewhere, much like a real customer. This means one workflow can reveal test cases you never thought to write, such as going back to change an address halfway through checkout or retrying a failed payment.
Key features include plain-English test definitions, parallel test runs, recorded runs shown step by step, evidence for every failure, and the steps needed to reproduce a bug.
Pricing: your first 10 completed runs are free and shared across your workspace. After that, each completed test run costs $3, which includes model usage, browser execution, findings and recorded evidence, with no separate token charges and no seat fees. Runs that fail because of an agent or platform failure are not charged. Volume pricing and enterprise agreements are available for larger teams. Prices are in USD.
It is suited to engineers and QA teams who want to find out what a release broke without maintaining scripted browser tests, and can be run alongside an existing test suite.
By the PowerfulAI.tools Editorial Team · Updated 11 November 2026 · Researched with AI assistance and checked against the official Seldon Wren website · How we review tools
Each completed test run costs $3, and the first 10 completed runs per workspace are free; volume and enterprise pricing is through sales.
Pricing checked against the official Seldon Wren website in November 2026. Prices can change, so confirm before you buy.
QA and engineering teams who want plain-English browser tests that explore beyond their scripted suite and return reproducible bug reports.
One test case executed once in one browser and environment is one run, and re-running it counts again. A completed test that finds a bug still counts, but runs that fail because of an agent or platform error are not charged.
Seldon lists SOC 2, GDPR, HIPAA and ISO 27001.
Yes. The pricing page also lists Finch for usability and product research and Rook for national security wargaming, both on custom pricing.
Popular alternatives to Seldon Wren include Pollinations, NemoClaw and Agnes AI. Compare their pricing and what each is best for below.
| Tool | Pricing | Best for |
|---|---|---|
| Pollinations | Freemium | Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app... |
| NemoClaw | Free | Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control... |
| Agnes AI | Freemium | Developers building AI-powered apps who want access to several models through one API. |
| OrcaRouter | Freemium | Developers and teams who want to balance AI quality and cost across many models. |
| DiagramGPT | Free | Developers and students who need to sketch system designs and workflows quickly by describing them in words. |
Own Seldon Wren? Add this badge to your website.
Leave a review for the community
No Review Found
