Seldon
Seldon's Wren runs plain-English end-to-end tests with behavioral AI agents that explore your app like real customers, finding failures your scripts miss and recording steps to reproduce each one. First 10 runs free, then $3 per completed run.
About Seldon
Wren by Seldon: behavioral QA testing
Wren runs end-to-end tests that you describe in plain English. Seldon's behavioral agents carry out each test in parallel, choose their next step from what they see, and explore paths your scripted suite may miss. Every failure comes with a recorded replay and steps to reproduce.
How it works
- Write: describe the task, where to start and what success looks like
- Run: agents execute tests in parallel and react to the page, for example retrying a button that gives no feedback
- Find: review recorded runs step by step with evidence for every failure
What it catches
- Broken layouts, failed API calls and incorrect totals
- Edge cases outside written test cases, such as duplicate items after a repeated click
Pricing
First 10 completed runs free per workspace, then $3 per completed test run. Model usage, browser execution and evidence included; no seat fees or token charges. Failed runs caused by the platform are not charged. Enterprise volume pricing available.
About Seldon
Seldon (Blok Intelligence Inc.) is an applied research lab modeling human behavior. Its products are Finch (usability testing), Wren (QA testing) and Rook (national security). Blok raised a $7.5M seed round led by MaC Venture Capital in 2025.
Value & Audience
Value Proposition
Replace brittle browser scripts with one- or two-sentence test descriptions, and let behavior-driven agents discover the edge cases real customers hit, with a recorded replay for every failure.
Problem Solved
Scripted end-to-end tests are slow to write, break easily and only check the paths someone thought to script, so bugs in unexpected customer behavior reach production.
Use Cases
Social & Links
Loading ratings...
Loading comments...
Gallery
Feedback & Roadmap
Seldon FAQ
Common questions about Seldon's features, pricing, and use cases
Is Seldon free to use?
No. Seldon is a paid product, starting at Wren - $3 per completed test run - first 10 completed runs free per workspace; model usage, browser execution and evidence included; no seat fees. Plans listed: Wren - $3 per completed test run - first 10 completed runs free per workspace; model usage, browser execution and evidence included; no seat fees; Wren Enterprise - Custom - volume pricing and enterprise agreements.
What are some alternatives to Seldon?
Popular Testing & QA alternatives to Seldon include TheySaid, BotGauge and heal.dev.
Seldon appears in
You May Also Like
View all alternatives to Seldon
TheySaid
TheySaid is a user-testing platform that runs usability tests with synthetic AI testers or real people and delivers findings and fix prompts inside tools like Claude Code, Cursor and Jira.
View Product
BotGauge
BotGauge is an AI agent reliability platform that red-teams agents with adaptive attacks, traces every run, turns failures into evaluations and policies, and monitors agents in production; the company also runs an AI-led managed QA service.
View Product
heal.dev
heal.dev is an AI agent that runs an application in a production-like sandbox to find bugs, performance regressions and runtime security issues. Each defect it files comes with a failing test that reproduces it.
View Product
Testifly
Testifly is an autonomous AI QA service for web apps: you give it a URL, and it discovers your real user flows, turns them into end-to-end tests, runs them on every deploy and on a schedule, heals them when the UI changes, and explains failures with root-cause analysis and session video.
View ProductOne email a week
TechLogHub tracks 813 tools and 592 open-source projects. Get the week's new launches, release roundups and open-source picks — nothing else.
Get the TechLogHub digest
One email a week: new and trending developer tools, fresh comparisons, and what shipped. Unsubscribe in one click.