Загрузка видео...

Не удалось загрузить видео

На главную

Here is my experimental agent QA walking idea. Agents walking and testing Omarchy with little direction other than "You are the theme tester" (its much more extensive than that, but this is X, no room for such nonsense).

111,896 просмотров • 14 дней назад •via X (Twitter)

Комментарии: 34

Фото профиля Viber · fireply.ai
Viber · fireply.ai14 дней назад

four agents poking at omarchy at once, that's a saturday afternoon rig honestly

Фото профиля ThePrimeagen
ThePrimeagen14 дней назад

i technically have 30, but it gets really hard to know what the heck is going on when I do that :)

Фото профиля Kamil
Kamil14 дней назад

Microsoft has been shipping this QA strategy for years They just call it Windows Insider 🤣

Фото профиля Brian Oliver
Brian Oliver14 дней назад

You bastard! You are taking peoples jobs using AI to test Omarchy.

Фото профиля Mihai Marinescu
Mihai Marinescu14 дней назад

the agents when they find out omarchy has a light theme

Фото профиля Daniel Morris
Daniel Morris14 дней назад

Hi Prime, does this run locally or in the cloud?

Фото профиля ThePrimeagen
ThePrimeagen14 дней назад

yes

Фото профиля Maxim Titarenko
Maxim Titarenko14 дней назад

The failure mode I've hit with loosely-prompted QA agents is confident false positives - one of mine reported "all done" on a batch of tests that turned out simulated, not actually run. Now I require pasted raw test-runner output, never a self-reported pass.

Фото профиля Aashish Ranjan Singh
Aashish Ranjan Singh14 дней назад

If you ever try something similar on the side of mobile (emulator/connected physical devices) then do share them as well. I currently feel that QA self healing automations are better on desktop but fail in case of mobile development, since mobile is bottlenecked by adb (considering android) limitations. Plus testing them in stage networks where we need to configure proxy is real pain in the a**. I am myself working on its end to end QA automation

Фото профиля woooltina
woooltina14 дней назад

my agents only test my patience 😭

Фото профиля Morphexe
Morphexe14 дней назад

I love how AI pilled you have become :p

Фото профиля Guy
Guy14 дней назад

"you are the theme tester" and the agent files a bug that just says "too much purple". honestly fair

Фото профиля macfee
macfee14 дней назад

The role instead of a checklist is the interesting bit. A script only checks what you already expect; a wandering theme tester stumbles into the rest.

Фото профиля Mirko Rüther
Mirko Rüther14 дней назад

Cool! Are you doing dev livestreams while working on omarchy QA? Enjoyed the ones you did in early September on this topic :-)

Фото профиля meehai
meehai14 дней назад

So the OS has an "MCP"-like API, allowing an agent to do I/O like a user would do with a mouse and a keyboard? And the agents are using that to test various user journeys?

Фото профиля marsel
marsel14 дней назад

that's awesome. I am building a design tool (like figma) optimized for omarchy (with mcp) that can also design themes, so that would be perfect for QA😍

Фото профиля Mauricio Acosta
Mauricio Acosta14 дней назад

share the prompt porfavor

Фото профиля Davit yan
Davit yan14 дней назад

This is cool 👀 Does it follow a set of predefined steps, or does the agent come up with its own test scenarios every run?

Фото профиля Arbaz
Arbaz14 дней назад

does the theme tester actually have taste or does it just say every theme looks great

Фото профиля faizan.
faizan.14 дней назад

agent as QA tester is the NPC mode we didn't know we needed

Фото профиля The MEEPING Man
The MEEPING Man14 дней назад

the agents are walking before i am

Фото профиля Nathan
Nathan14 дней назад

Nice i had my agent write a fuzz testing thing for mine

Фото профиля foundrceo
foundrceo14 дней назад

giving an agent a vague role and letting it wander is a better bug finder than most scripted tests. humans stop looking where they already expect things to work

Фото профиля Jeff Bruchado
Jeff Bruchado14 дней назад

a low contrast theme and a broken one look a lot alike to the theme tester, so most of the work is teaching it which ugly is on purpose

Фото профиля Digital Foundation
Digital Foundation14 дней назад

Day three and it only wants to test Tokyo Night

Фото профиля larry
larry14 дней назад

how does it decide a theme's broken, screenshot diffs or the model eyeballing it

Фото профиля Anis Ahmed Chohan
Anis Ahmed Chohan14 дней назад

This is X pretty pictures and videos only please...

Фото профиля Solomon
Solomon14 дней назад

That's Hendrickson's exploratory testing charter: explore [target] with [resources] to discover [information]. Now the testers never get bored.

Фото профиля Jeremy W
Jeremy W14 дней назад

We're all building the same thing 😭😂😭😂

Фото профиля Xander
Xander14 дней назад

you gave an ai agent a desktop and told it to explore. that's not qa anymore, that's putting a raccoon in an office and observing the damage

Фото профиля Marius Miclau
Marius Miclau14 дней назад

what does it report back , screenshots of broken themes or actual bug notes ?

Фото профиля Om Londhe
Om Londhe14 дней назад

theme testing is a good stress case because the bugs are visual. no stack trace to latch onto, the agent has to actually look at the screen

Фото профиля John
John14 дней назад

letting it just wander the app finds stuff scripted tests never would

Фото профиля seridarivus 🇷🇴
seridarivus 🇷🇴14 дней назад

Giving each agent one narrow role like theme tester is the clever part. A generalist QA agent reports everything; a specialist that only cares about themes catches the contrast bug a human stops seeing after day two.

Похожие видео