QA agents that test your product like real customers: describe tests in plain English and get replays, screenshots and reproduction steps for failures.
Wren by Seldon: stop babysitting end to end tests
1 / 3Overview
What is Seldon?
Behavioral QA agents that use your product like customers do
Seldon builds behavioral QA agents that use your product like customers do. Its QA product, Wren, finds the tests you never thought to write: describe how Wren should behave in plain English and its agents walk full flows — going back to change an address mid-checkout, retrying after a failed payment — then report failures with replays and reproduction steps. Your first 10 test runs are free.
- Define tests in plain English, no scripts
- Agents explore like real users, beyond scripted paths
- Failures include screenshots, video replays, logs and reproduction steps
- Scheduled regression runs before every release
- SSO, CI/CD, Slack, Jira, Linear and MCP integrations
Wren costs $3 per completed test run, with model usage and browser execution included and no seat fees. Seldon also offers Finch for product research and Rook for government simulation.
Platforms and languages
Seldon Availability
Platforms
Languages
Capabilities
Seldon Key Features
Tests in plain English
Describe the task, expected behavior and constraints in plain English — no test scripts to write.
Behavioral exploration
Agents use your product like real customers, exploring paths beyond your scripted tests.
Evidence-rich bug reports
Failures come with screenshots, video replays, logs, network requests and steps to reproduce.
Automatic regression
Re-run test suites on a schedule to catch regressions before release.
Enterprise-ready
SSO, dedicated environments, CI/CD, Slack, Jira, Linear and MCP integrations.
Best for
Who uses Seldon?
Software, product, engineering and QA teams
Find bugs they never thought to write tests for, with evidence for every failure
Plans and access
Seldon Pricing
Freemium
First 10 test runs free; then $3 per completed run, no seat fees.
Common questions
Seldon FAQs
How is a Wren test run billed?
One test case executed once in one browser and environment counts as one run — $3. A suite of 10 cases run once counts as 10 runs, or $30.
What does $3 per run include?
Model usage and browser execution, plus the evidence collected — screenshots, replays and logs. There are no separate token fees or seat fees.
Can I try Wren first?
Yes. Your first 10 completed test runs are free — one allowance per workspace — so you can sign up, create a workspace and run real tests before paying.
Reviews
See what the community thinks and share your experience.
—
Based on 0 ratings
Rating distribution
Community reviews
No reviews
No written reviews yet.
