Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Can't overstate how cool self-testing is in Agent 3. Here's a shot of Replit running end-to-end UI tests on a whiteboard app. It tests out the different tools, the undo button, and even sends a chat.

matt palmer

42,474 subscribers

63,239 views • 11 months ago •via X (Twitter)

Science & Technology Education Comedy

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Stop writing tests. Start describing them. KaneAI converts natural language into end-to-end tests in seconds. ✔ JIRA / PDF / video uploads ✔ Self-healing UI tests ✔ GitHub PR-based test creation ✔ API & backend validation Modern testing, powered by GenAI Give it a try : Follow #AITesting #KaneAI #DevOps #QualityEngineering

Stop writing tests. Start describing them. KaneAI converts natural language into end-to-end tests in seconds. ✔ JIRA / PDF / video uploads ✔ Self-healing UI tests ✔ GitHub PR-based test creation ✔ API & backend validation Modern testing, powered by GenAI Give it a try : Follow #AITesting #KaneAI #DevOps #QualityEngineering

Marry claire

25,653 views • 6 months ago

Introducing CodeCapy: the only PR bot that actually tests your code - an open-source GitHub app that generates end-to-end UI tests based on code changes and executes tests autonomously in isolated Scrapybara Ubuntu desktops. Try CodeCapy for your repos with the link below!

Introducing CodeCapy: the only PR bot that actually tests your code - an open-source GitHub app that generates end-to-end UI tests based on code changes and executes tests autonomously in isolated Scrapybara Ubuntu desktops. Try CodeCapy for your repos with the link below!

Scrapybara

18,272 views • 1 year ago

Here's everything you need to know about Replit in 60 seconds ⭐️ → Plain English prompts turned into real working software → End-to-end workflow from UI to deployment → Real-time team collaboration with just a link → Parallel AI agents building different parts of your app at once

Here's everything you need to know about Replit in 60 seconds ⭐️ → Plain English prompts turned into real working software → End-to-end workflow from UI to deployment → Real-time team collaboration with just a link → Parallel AI agents building different parts of your app at once

Replit ⠕

13,548 views • 2 months ago

Docket (Docket) is building AI agents for QA testing — enabling teams to write end-to-end tests in plain English. Congrats on the launch, nh and Boris Skurikhin!

Docket (Docket) is building AI agents for QA testing — enabling teams to write end-to-end tests in plain English. Congrats on the launch, nh and Boris Skurikhin!

Y Combinator

25,848 views • 1 year ago

Websites now self-improve! Our AI agent (trained on thousands of tests) comes up with website variations and then launches A/B tests. When tests reach stat sig, we use the data collected to improve your model and repeat the process. Try it:

Websites now self-improve! Our AI agent (trained on thousands of tests) comes up with website variations and then launches A/B tests. When tests reach stat sig, we use the data collected to improve your model and repeat the process. Try it:

Fab

6,793,216 views • 1 year ago

This is the dream of anyone who has ever tested a website. Writing automated tests for a UI is one of the hardest things ever. Here is how to write and run tests for your web pages 100x faster (it also supports iOS and Android apps).

This is the dream of anyone who has ever tested a website. Writing automated tests for a UI is one of the hardest things ever. Here is how to write and run tests for your web pages 100x faster (it also supports iOS and Android apps).

Santiago

31,529 views • 13 days ago

1) Full end-to-end AI software automation is near. At Nexus, we have the goal of achieving full end-to-end automation of our software production system by end of year. We are experimenting with this via a fast iteration closed-loop self-improving system. I think it's quite interesting, so I want to share publicly as I haven't seen too many engineering teams talk publicly about findings like this yet. In our tests, each autonomous improvement cycle has the following structure: - 1. Pre-planning: High-level architectural goals - 2. Planning: Medium-level planning and spec authoring, including specs for all tests, benchmarks, regression tests, etc. - 3. Execution: Full end-to-end agentic implementation cycle spanning 1-2hrs of autonomous work. This is the bulk of the productive session where the actual code is written, tested, and progressed. - 4. Evaluation: Complete running of tests, benchmarks, telemetry and profiling of the post-execution state system - 5. Retrospective: Thorough retrospective of the end-to-end run, including telemetry of the agent itself, such as cost, tokens used, times context limits were hit, etc. - 6. Self-improvement: Reasoning based on execution metrics and meta-level metrics about the agentic system itself The view below shows a 3D visualization of 29 generations of a self-improving codebase authored by our E2E automation system

1) Full end-to-end AI software automation is near. At Nexus, we have the goal of achieving full end-to-end automation of our software production system by end of year. We are experimenting with this via a fast iteration closed-loop self-improving system. I think it's quite interesting, so I want to share publicly as I haven't seen too many engineering teams talk publicly about findings like this yet. In our tests, each autonomous improvement cycle has the following structure: - 1. Pre-planning: High-level architectural goals - 2. Planning: Medium-level planning and spec authoring, including specs for all tests, benchmarks, regression tests, etc. - 3. Execution: Full end-to-end agentic implementation cycle spanning 1-2hrs of autonomous work. This is the bulk of the productive session where the actual code is written, tested, and progressed. - 4. Evaluation: Complete running of tests, benchmarks, telemetry and profiling of the post-execution state system - 5. Retrospective: Thorough retrospective of the end-to-end run, including telemetry of the agent itself, such as cost, tokens used, times context limits were hit, etc. - 6. Self-improvement: Reasoning based on execution metrics and meta-level metrics about the agentic system itself The view below shows a 3D visualization of 29 generations of a self-improving codebase authored by our E2E automation system

Daniel Marin | nexus.xyz

42,408 views • 3 months ago

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

Yohei

211,889 views • 1 year ago

How to Use KaneAI — Best Gen AI Native (FULL GUIDE) 🔥” QA Engineers & DevOps: Stop wasting 80% of your time on manual tests. KaneAI converts natural language into executable End to End tests instantly: ✅ Upload JIRA issues, PDFs, or videos → Auto-generate test cases ✅ Self-healing locators for resilient Ul tests ✅ Analyze GitHub PRs to create/update tests automatically ✅ Seamless API calls, database queries, and backend validation Transform your testing workflow today - create, debug, and evolve tests in plain English. No coding required. Ship faster with confidence! Give it a try : #AITesting #KaneAI #DevOps #QualityEngineering

How to Use KaneAI — Best Gen AI Native (FULL GUIDE) 🔥” QA Engineers & DevOps: Stop wasting 80% of your time on manual tests. KaneAI converts natural language into executable End to End tests instantly: ✅ Upload JIRA issues, PDFs, or videos → Auto-generate test cases ✅ Self-healing locators for resilient Ul tests ✅ Analyze GitHub PRs to create/update tests automatically ✅ Seamless API calls, database queries, and backend validation Transform your testing workflow today - create, debug, and evolve tests in plain English. No coding required. Ship faster with confidence! Give it a try : #AITesting #KaneAI #DevOps #QualityEngineering

Erina | AI Tools & News

45,902 views • 6 months ago

Need a beautiful design for your next Replit app? Head to 21st⁠.dev and: - Find a design - Copy the prompt into Replit Agent - Iterate and add Replit’s built-in tools and databases - Deploy your app to the public - Profit Share what you build and tag us!

Need a beautiful design for your next Replit app? Head to 21st⁠.dev and: - Find a design - Copy the prompt into Replit Agent - Iterate and add Replit’s built-in tools and databases - Deploy your app to the public - Profit Share what you build and tag us!

Replit ⠕

50,651 views • 1 year ago

INSANE: Grok 3 + Replit Agent is a Superpower!! Using the pair, I built an AI agent that reviews my Pull Requests Here's the flow: • Grok 3 generates PR-reviewing agent code using Composio + LlamaIndex • Replit Agent automatically crafts the front-end interface • Get a ready-to-run workflow where you paste the url to your PR, and the agent generates a code review instantly with suggestions. Built with Grok Replit ⠕ Agent Powered by LlamaIndex 🦙 Groq Inc repl link:

INSANE: Grok 3 + Replit Agent is a Superpower!! Using the pair, I built an AI agent that reviews my Pull Requests Here's the flow: • Grok 3 generates PR-reviewing agent code using Composio + LlamaIndex • Replit Agent automatically crafts the front-end interface • Get a ready-to-run workflow where you paste the url to your PR, and the agent generates a code review instantly with suggestions. Built with Grok Replit ⠕ Agent Powered by LlamaIndex 🦙 Groq Inc repl link:

Karan Vaidya

1,684,869 views • 1 year ago

🚀 Less managing, more creating. Building app usually means: • Hours lost debugging • Constantly juggling tools • Non-stop AI hand-holding Replit’s new Agent 3 changes that entirely → ⁠ We just tried out Agent 3, and it’s impressive! ⁠ It’s not another ordinary AI coding assistant. It’s a full-on collaborator that: • Runs autonomously for up to 200 minutes, building your app from start to finish. • Tests its own work in a real browser and fixes bugs automatically, saving hours of manual debugging. • Lets you build other agents and automations (think Slack bots, Telegram reminders, email summaries). ⁠ Here's why Agent 3 is different: Unlike traditional AI tools where you constantly babysit and prompt, Agent 3 understands your idea and takes charge, freeing you to focus on creativity, strategy, or simply grabbing coffee while your app builds itself. And to show how easy it is, we built a complete waitlist app in less than an hour, from idea to almost finished product. No babysitting. No endless tweaking. ⁠ Replit ⠕ is calling this “Autonomy for All,” and after seeing Agent 3 in action, it’s easy to see how it can bring millions more creators online. ✅ Faster builds ✅ Less frustration ✅ More polished, reliable apps With Agent 3, app-building really does feel less like wrestling with software and more like collaborating with a teammate. ⁠ Try Replit Agent 3 yourself today…👆 Get $10 credit when you purchase Replit Core using our link above!

🚀 Less managing, more creating. Building app usually means: • Hours lost debugging • Constantly juggling tools • Non-stop AI hand-holding Replit’s new Agent 3 changes that entirely → ⁠ We just tried out Agent 3, and it’s impressive! ⁠ It’s not another ordinary AI coding assistant. It’s a full-on collaborator that: • Runs autonomously for up to 200 minutes, building your app from start to finish. • Tests its own work in a real browser and fixes bugs automatically, saving hours of manual debugging. • Lets you build other agents and automations (think Slack bots, Telegram reminders, email summaries). ⁠ Here's why Agent 3 is different: Unlike traditional AI tools where you constantly babysit and prompt, Agent 3 understands your idea and takes charge, freeing you to focus on creativity, strategy, or simply grabbing coffee while your app builds itself. And to show how easy it is, we built a complete waitlist app in less than an hour, from idea to almost finished product. No babysitting. No endless tweaking. ⁠ Replit ⠕ is calling this “Autonomy for All,” and after seeing Agent 3 in action, it’s easy to see how it can bring millions more creators online. ✅ Faster builds ✅ Less frustration ✅ More polished, reliable apps With Agent 3, app-building really does feel less like wrestling with software and more like collaborating with a teammate. ⁠ Try Replit Agent 3 yourself today…👆 Get $10 credit when you purchase Replit Core using our link above!

There's An AI For That

40,330 views • 11 months ago

built and deployed an AI Ad Analysis Tool on my vibe marketing resource site today... steps: 1) I've managed $150m+ in campaigns so used my knowledge to have Manus build out a super detailed scope using weights for various factors 2) loaded the scope into Replit and it basically one shotted the app! it uses reasoning models from OpenAI 3) went back and forth with Replit agent to update the overall design and UX 4) now we have tools, super cool. did some testing and everything is working with beehiiv Give it a try and lmk what you think... THIS IS VIBE MARKETING. Stack: - Replit - Manus - OpenAI - Beehive

built and deployed an AI Ad Analysis Tool on my vibe marketing resource site today... steps: 1) I've managed $150m+ in campaigns so used my knowledge to have Manus build out a super detailed scope using weights for various factors 2) loaded the scope into Replit and it basically one shotted the app! it uses reasoning models from OpenAI 3) went back and forth with Replit agent to update the overall design and UX 4) now we have tools, super cool. did some testing and everything is working with beehiiv Give it a try and lmk what you think... THIS IS VIBE MARKETING. Stack: - Replit - Manus - OpenAI - Beehive

The Boring Marketer

17,832 views • 1 year ago

✂️ Introducing: Shortest! Shortest is an open-source AI-powered testing framework that allows developers to write end-to-end tests in plain English, as simple as: shortest(“user can sign up and create a $5 product”) More tests = fewer regressions as AI writes and ships code.

✂️ Introducing: Shortest! Shortest is an open-source AI-powered testing framework that allows developers to write end-to-end tests in plain English, as simple as: shortest(“user can sign up and create a $5 product”) More tests = fewer regressions as AI writes and ships code.

Sahil Lavingia

722,572 views • 1 year ago

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇

Manny Bernabe

32,109 views • 6 months ago

Can AI agents really manage other agents? Most of us can't even get one AI agent to really work well. But it works in Replit ⠕ v3. For real. And it's so cool. I had it do a 2.75 hour autonomous security audit. One agent managing other AI agents. Here's how it worked:🧵

Can AI agents really manage other agents? Most of us can't even get one AI agent to really work well. But it works in Replit ⠕ v3. For real. And it's so cool. I had it do a 2.75 hour autonomous security audit. One agent managing other AI agents. Here's how it worked:🧵

Jason ✨👾SaaStr.Ai✨ Lemkin

14,102 views • 10 months ago

Sanji shares his Higgsfield Supercomputer playbook to run marketing end-to-end. He lets the agent analyze his niche, find the winning formula, generate 100+ variations, and run A/B tests at scale, with the agent learning from every run. How do you use Supercomputer for scaling?

Sanji shares his Higgsfield Supercomputer playbook to run marketing end-to-end. He lets the agent analyze his niche, find the winning formula, generate 100+ variations, and run A/B tests at scale, with the agent learning from every run. How do you use Supercomputer for scaling?

Higgsfield AI 🧩

115,336 views • 2 months ago

AI CHECKUP? STEP INSIDE THE FUTURE OF “WTF” HEALTHCARE CarePod is an AI-powered clinic in a box: 86 tests, zero humans. You walk in, it hands you the tools, you follow instructions, and boom - blood draws, body scans, even genetic tests, DIY-style. Data gets zapped to a remote doctor who sends feedback in minutes. Because who needs a waiting room when you’ve got a vending machine that checks your heart? Source: theshivrajdube on IG

AI CHECKUP? STEP INSIDE THE FUTURE OF “WTF” HEALTHCARE CarePod is an AI-powered clinic in a box: 86 tests, zero humans. You walk in, it hands you the tools, you follow instructions, and boom - blood draws, body scans, even genetic tests, DIY-style. Data gets zapped to a remote doctor who sends feedback in minutes. Because who needs a waiting room when you’ve got a vending machine that checks your heart? Source: theshivrajdube on IG

Mario Nawfal

39,542 views • 1 year ago

claude code now writes its own test plan and runs it on a live iphone. i didn't write the tests. i didn't run the tests. i didn't even open the app. it caught the bug too.

claude code now writes its own test plan and runs it on a live iphone. i didn't write the tests. i didn't run the tests. i didn't even open the app. it caught the bug too.

Landseer Enga

30,714 views • 3 months ago