Intent-driven tests as code
Describe a journey in plain English and blop turns it into a `.blop.ts` test that reads as intent rather than a selector script. The test lives in your repo and can be reviewed like other code.
blop
Claimblop is a QA agent that writes browser tests as code in your repo, runs them in CI, clusters repeated failures, and can open PRs to fix broken tests.
QA agent that keeps tests as code
Blop is a QA agent for teams that want browser tests to live as code in their repository instead of in a vendor dashboard. You describe a journey in plain English, and the agent runs a real browser through it to create and maintain a test artifact you own.
The product runs those tests in your CI, posts structured results back to the pull request that triggered them, and clusters repeated failures so recurring breakages are easier to track. When UI changes break a test, Blop can open a pull request with a fix and verification step, keeping the workflow centered on reviewable diffs.
What blop does
Browser runs backed by Playwright
The agent drives a real browser through the flow over Playwright, so the test outcome reflects an actual user path rather than a hidden dashboard state.
CI-native execution
Blop runs tests in your CI using your existing GitHub Actions runners, so the workflow fits into the pipeline you already operate.
Failure clustering
Repeated failures are grouped into clusters so the same broken selector or UI change does not appear as dozens of separate rows across runs.
Agent-authored repair PRs
When a failure is eligible, the agent can open a pull request that fixes the test and verifies it green before review. Auto-fix is described as early access.
Synthetic monitoring
Any test can also be scheduled as a recurring probe against production, with uptime, p95 duration, and journey completion shown as signals.
Where blop fits
Turn product journeys into code
Teams can describe a checkout, signup, or other user journey in plain English and get a browser test that can be versioned and reviewed alongside product changes.
Triage repeated failures
When the same selector breakage or UI regression shows up repeatedly, failure clustering turns many similar results into one issue to investigate.
Repair tests through pull requests
If a UI change breaks a test, the agent can inspect the trace, console output, and diff, then open a pull request with a scoped repair and verification run.
Fit into an existing CI workflow
Teams that already use GitHub Actions can run tests through their current CI runners instead of hosting a separate execution environment.
Monitor critical journeys
Any test can be scheduled as a recurring production probe to watch uptime, journey completion, and p95 duration for important user flows.
Pros and Cons
Pros
- Tests are stored in the repository as code, not as hidden dashboard state.
- Runs integrate with existing GitHub Actions runners, so there is no separate runner to host.
- Repeated failures are clustered, which reduces noise from the same issue appearing across multiple runs.
- The product can post structured results back to pull requests, keeping review context in the code review flow.
- A recurring test can double as a synthetic check with uptime and p95 duration signals.
Cons
- Auto-fix is in early access, so the repair workflow is not yet a fully general release feature.
- Playwright is the only runtime called out as first-class today, with other framework adapters planned rather than available now.
- Self-hosting the full control plane is on the roadmap, not yet shippable.
FAQ
Where do my tests live?
Tests live in your repository as `.blop.ts` files. They are version-controlled, code-reviewed, and editable or deletable by your team.
Is there a free trial?
Yes. Every plan starts with a 7 day free trial, and the trial includes full access to the features in the plan you choose. No credit card is required to start.
Do I need to host my own runners?
Blop runs through your existing GitHub Actions runners, either cloud or self-hosted. The control plane does not execute tests itself.
Does it only work with Playwright?
Blop is Playwright-first today. The result payload is a versioned contract, and the site says adapters for other frameworks are planned next.
How does the agent fix failing tests?
When a run fails, the agent inspects the failure, trace, and diff, then can open a pull request with a scoped fix and verification build. Auto-fix is in early access and nothing merges without approval.
Quick Facts
- Category
- Developer Tool
- Primary use
- Browser testing and QA automation
- Execution model
- Runs in your CI with GitHub Actions runners
- Test format
- .blop.ts files in your repo
- Framework
- Playwright-first
- Pricing
- Per-user plans with a 7 day free trial
blop Alternatives
Orca
Orca is an Agent Development Environment for shipping with coding agents, running multiple CLI agents in parallel across isolated worktrees, with desktop and mobile workflows.
AI Magicx
AI Magicx is a unified AI workspace for chat, image, video, voice, music, email and developer tasks, helping teams and creators manage multiple models in one place.
Paper
Paper is a design tool that connects canvas, code, and AI agents so teams can create, share, and ship work in one workflow. Includes desktop app and MCP access.
RLAMA
RLAMA is a local AI platform for building RAG systems and intelligent agents on macOS, Linux, and Windows, with HTTP API support.
Kastra
Kastra authorization infrastructure for AI systems checks prompts, tool calls, shell commands, API requests, and browser actions before execution.
AakarDev AI
AakarDev AI helps teams manage AI provider access, project setups, logs, and analytics in one dashboard with BYOK support.