Write end-to-end tests in plain English with an open-source agent framework
e2e is an open-source testing framework that combines AI agents with normal end-to-end tests: you describe what the user should do in plain English instead of manually scripting every click.
Source
@Goura_vk on X · 2026-10-16
Written in our own words. Credit to the original author. Link checked 2026-10-23.
What they did
e2e is an open-source testing framework that combines AI agents with normal end-to-end tests: you describe what the user should do in plain English instead of manually scripting every click.
Result (as claimed)
Tests read like user stories, so non-specialists can add coverage.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up e2e, AI agents. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Write end-to-end tests in plain English with an open-source agent framework What the original author did: e2e is an open-source testing framework that combines AI agents with normal end-to-end tests: you describe what the user should do in plain English instead of manually scripting every click. Reported result (as claimed by the author): Tests read like user stories, so non-specialists can add coverage. Source: https://x.com/Goura_vk/status/2110941210961678715 Tools they used: e2e, AI agents Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Write end-to-end tests in plain English with an open-source agent framework What the original author did: e2e is an open-source testing framework that combines AI agents with normal end-to-end tests: you describe what the user should do in plain English instead of manually scripting every click. Reported result (as claimed by the author): Tests read like user stories, so non-specialists can add coverage. Source: https://x.com/Goura_vk/status/2110941210961678715 Tools they used: e2e, AI agents Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Write end-to-end tests in plain English with an open-source agent framework What the original author did: e2e is an open-source testing framework that combines AI agents with normal end-to-end tests: you describe what the user should do in plain English instead of manually scripting every click. Reported result (as claimed by the author): Tests read like user stories, so non-specialists can add coverage. Source: https://x.com/Goura_vk/status/2110941210961678715 Tools they used: e2e, AI agents Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
How to test your app with AI agents before you ship · How to run multiple coding agents together
Related use cases
Run end-to-end tests on Windows desktop apps in parallel with recordings
QA Wolf can now run end-to-end tests for Windows desktop apps, 100% parallel, live streamed and recorded, using the same APIs it uses for web and mobile tests.
Have Claude write both a VM and a separate proof generator from the same spec
For a JavaCard VM he had Claude implement the VM from the spec and separately a proof generator from the spec, so a bug would have to exist in both to slip through, and verified them with ESBMC.
Ask Claude whether your tests have actually caught bugs
Cory House asked Claude: "Look through my past sessions. How many times did a test catch a bug?" Claude found 5 recent instances where a test caught a bug.
Make Claude Code write a handoff and reset itself at 50% context
His open-source Claude Code plugin watches the session; when context reaches a set level (he uses 50%) it writes its own handoff doc, clears itself and continues from that doc.