@flaurida11

Co-founder @QAWolfHQ, Previously @Bridgewater, @cityblockhealth. Doing my best every day 🐺

 Seattle, WA
qawolf.com/
Joined October 2019
  • Tweets140
  • Following163
  • Followers119
6Media
Laura Cressman retweeted
Chris Brown
@almostcmbOct 20
Today we announce @InspiredCap Fund IV. $450m more to back rational optimists shaping the intelligence age. The next decade will be unlike anything we've ever seen. Buckle up!
Alexa von Tobel, CFP
@alexavontobelOct 20
Today, our team is excited to announce @InspiredCap Fund IV, $450M in new capital to back early-stage founders. There has never been a moment in history when more is possible. It takes just one person with exceptional ambition to take on the world’s problems and change billions of lives for the better.
36
2
1
202
9,086
Asking Claude the hard questions. It's trying to thread the needle between making it sound easy (for Claude Code's sake) and hard (for Salesforce's sake)
15
Claude is learning to hedge its deadlines
17
We've come full circle
12
"Let me take a pass" translation: "Let me prompt my Claude." "Left some comments" translation: "I prompted my Claude to review."
1
30
Getting tons of AI generated cold emails these days, but the strange thing is they all pretty much beg me to unsubscribe at the end. Why is that? 😅
30
Claude/Codex are the new browser, and software products need to fit into this new paradigm.
Jon Perl
@jonperlOct 12
Dogfooding our MCP showed me how broken our UX was inside a coding agent. That led us to agent-first design: the UI comes to your agent's browser pane.
1
1
27
AWS meant you didn't need a server farm to ship. AI means you don't need a 50-person eng team.
33
Laura Cressman retweeted
QA Wolf
@QAWolfHQOct 6
2/ Deploys rose 31% between Q1 2025 and Q3 2026. About half of that rise came in the last two quarters.
1
1
1
79
Laura Cressman retweeted
QA Wolf
@QAWolfHQOct 6
1/ Does shipping faster with AI mean shipping more bugs? We looked at 50,000+ deploys over 21 months to find out...
2
4
1
5
308
Laura Cressman retweeted
Jon Perl
@jonperlSep 30
web and real phones streamed to the browser. you don't need to watch the tests live. but if you want to you can. it's little things like this that make a product experience magical
QA Wolf
@QAWolfHQSep 30
Now! Watch test runs live and in living color. When test runs get stuck they hold up your release. Before today, if you wanted to know why a test was hanging, you had to wait for the recording and logs. Now you (or our agent) can jump in and intervene. qawolf.com/changelog/live-st…
3
4
177
Laura Cressman retweeted
Erzhan Torokulov
@erzhtorSep 30

Black box testing, a black box no more: Live streaming test runs

Article · @erzhtor
5
4
363
Laura Cressman retweeted
Jon Perl
@jonperlOct 1
not just tests, even our ai chats get a computer. here is why:
atchyut
@_theonly1meOct 1
A new model launches every other week. GPT-6.1 Sol, Gemini 4 Argon, Claude Opus 5.5, each new release beating the last on some benchmark. But on its own, even the smartest model can only tell you how to fix a broken test. To actually fix it, it needs somewhere to work: your code, a browser to open your app, and a way to run the test and see it pass, that’s the sandbox. QA Wolf AI’s is warm in milliseconds, with a real file system, a git clone of your test suite and a live browser you can watch. When the task is big, it spins up 50 more sandboxes, each with its own browser and branch. Here’s how we built it: qawolf.com/blog/every-ai-age…

Why Every QA Wolf AI Agent Gets Its Own Computer | QA Wolf

Agent sessions don't behave like cloud jobs. How we rebuilt our infrastructure so every QA Wolf AI agent gets its own machine with a real filesystem, shell and browser.

qawolf.com
3
3
189
Laura Cressman retweeted
QA Wolf
@QAWolfHQOct 1
Welcome to self-driving QA 🚗 Your agent builds a feature ⬇️ Calls QA Wolf to test it ⬇️ QA Wolf bulk automates Playwright & Appium tests ⬇️ Tests run in parallel ⬇️ Verified bugs are shared with your agent ⬇️ Agent fixes ⬇️ Re-test & ship Start here: docs.qawolf.com/
1
4
3
6
363
Laura Cressman retweeted
QA Wolf
@QAWolfHQSep 30
Now! Watch test runs live and in living color. When test runs get stuck they hold up your release. Before today, if you wanted to know why a test was hanging, you had to wait for the recording and logs. Now you (or our agent) can jump in and intervene. qawolf.com/changelog/live-st…
1
2
2
344
Laura Cressman retweeted
Jon Perl
@jonperlSep 29
Everything you can do in the UI works via MCP and always will be (via a shared contract with the API)
QA Wolf
@QAWolfHQSep 29
Our MCP server is live for Codex, Claude Code, or the coding agent of your choice. Now when your coding agent says the PR is done and bug free, you can get a second set of eyes to run through your end-to-end test suite. docs.qawolf.com/quick-start

Quick start - QA Wolf Docs

Connect QA Wolf to your coding agent and create your first end-to-end test.

docs.qawolf.com
3
2
176
Laura Cressman retweeted
QA Wolf
@QAWolfHQSep 29
Our MCP server is live for Codex, Claude Code, or the coding agent of your choice. Now when your coding agent says the PR is done and bug free, you can get a second set of eyes to run through your end-to-end test suite. docs.qawolf.com/quick-start

Quick start - QA Wolf Docs

Connect QA Wolf to your coding agent and create your first end-to-end test.

docs.qawolf.com
6
3
3
8
933
Laura Cressman retweeted
QA Wolf
@QAWolfHQSep 24
Oh yeah! The other day, @golenull and the team added semantic assertions for Playwright to QA Wolf. They’re ideal for testing genAI apps, where the response can change but the meaning stays the same. And showing a lot of potential to cut down on flakes. Built with Jev from @typesafeai . More from Goran 👇
Goran Gajić
@golenullSep 24
Still figuring out what all we can do with Jev. One of the first places we’re putting it to work: giving Playwright tests a little judgment. ai.expect checks meaning. ai.act can take a different route through the UI. The rest of the test stays deterministic. Wrote it up qawolf.com/blog/semantic-ass…

Semantic assertions: Using Jev to make rigid tests flex | QA Wolf

E2E tests need to be deterministic, but not every variation is a failure. Here's how QA Wolf uses Jev to let wording and routes vary while Playwright enforces the requirements that can't.

qawolf.com
3
7
227
Load more