automating testing @getlark (YC S25). prev @stripe. climb with me calendly.com/founders-uselar…

Joined August 2025
15 Photos and videos
Hands down best way to handle agentic memory
1
12
Am I the only one who thinks Claude Opus 4.8 hasn't really improved over 4.7 wrt coding tasks?
16
Jack Brown retweeted
May 27
Lark is sponsoring AI Dev Summit this week. If you’re here, come say hi. We’d love to chat about faster releases, fewer regressions, and AI-powered testing.
2
4
94
Nationalize utility companies
Nearly 50,000 people in the Lake Tahoe area have been told that their utility will stop providing power to them, because it's redirecting that power to data centers. NV Energy, the Nevada utility that has supplied most of Lake Tahoe’s electricity for decades, says that next year it will stop servicing homes in the area, and instead direct that electricity to the growing demand from Nevada data centers. Northern Nevada is one of the fastest-growing data-center corridors in the country. fortune.com/2026/05/12/lake-…
Community note
NV Energy is ending a wholesale supply contract with Liberty Utilities (the actual retail provider) in May 2027. Liberty is actively seeking replacement power sources and has stated, 'This does not mean the power is shutting off.' sfgate.com/tahoe/article/… calmatters.org/economy/2026/0…
14
tag this person
12
Jack Brown retweeted
May 5
E2E tests shouldn’t break every time your UI evolves. Today, one of Lark’s own E2E tests failed after we shipped a UI change. Lark summarized the failure, identified it as a test issue rather than an app bug, and repaired the test automatically. The test has been passing consistently since.
2
3
106
Okay keep it together @ClaudeDevs
1
20
Okay actually idek how to pronounce this
9
AI solving a 60-year-old math problem is impressive. what's more impressive is that most teams can't get their AI to reliably fill out a form. the gap between research demos and production workflows is still enormous.
24
the test suite that takes 45 minutes to run is the one nobody fixes broken tests in. speed is a feature, and in CI it's the only feature that affects whether engineers actually trust the output.
33
Who else is using openclaw to do their taxes?
1
32
still the best tax strategy tbh
14
Jack Brown retweeted
Over 100 QA reports generated since launch. We’re seeing real issues uncovered across SDKs, APIs, and dashboards—helping teams catch and fix problems before users report them. Fast, structured, reproducible.
We just shipped QA Reports. Deploy AI agents to test your product, uncover issues, and get back a structured report with reproducible test cases. We ran it on the Vercel Sandboxes API. It mapped test areas, executed flows, and surfaced real issues in minutes. Try it: getlark.ai Example report (Vercel Sandboxes API): tests.getlark.ai/a/kiwi/qa-r…
2
6
136
Jack Brown retweeted
OpenAI just added support for popular sandbox providers in their Agents SDK — using a “harness separate from compute” model. At @getlark, we take a different approach: “harness in compute.” We want agents to behave more like local Claude or Codex — fully embedded, with everything running inside the compute environment. That’s why we open-sourced runtimeuse.com — an agent-agnostic framework for running long-lived agents in any sandbox. Works with @e2b, @daytonaio, @vercel, @modal, and more.
Build long-running agents with more control over agent execution. New capabilities in the Agents SDK: • Run agents in controlled sandboxes • Inspect and customize the open-source harness • Control when memories are created and where they’re stored
1
6
215
Jack Brown retweeted
Apr 15
Create Linear issues automatically when tests fail or bugs are discovered. Catch bugs → create issues → fix faster. No missed failures. No manual triage.
2
2
113
Jack Brown retweeted
We just shipped QA Reports. Deploy AI agents to test your product, uncover issues, and get back a structured report with reproducible test cases. We ran it on the Vercel Sandboxes API. It mapped test areas, executed flows, and surfaced real issues in minutes. Try it: getlark.ai Example report (Vercel Sandboxes API): tests.getlark.ai/a/kiwi/qa-r…
2
2
9
360
The leaked claude code src has a real comment about optimizing launch timing for "sustained Twitter buzz" while being "gentler on soul-gen load"
1
55
We just launched Repairs at Lark. Ship a UI change. End-to-end tests break. Lark's QA agents automatically fix them. No more test maintenance bottlenecks. Just turn on auto-repairs and keep shipping. Try it → getlark.ai
3
3
210
Jack Brown retweeted
fuck this administration it does not matter your feelings on immigration at all, this is not how our legal system is intended to work
ICE detain mother at airport—traveling with young daughter. First reported kidnapping at airport since Trump ordered ICE agents to report—refuse to show ID. "I don't know who you are!" witness yells. "You could be someone kidnapping her!" Agent continue to refuse to show ID until bystanders agree they should call police to report a kidnapping. Incident occurred at the San Francisco International Airport Gate E2 on March 22, 2026, at 10pm. #DemsUnited
45
33
703
52,484
Jack Brown retweeted
Jimmy Carter had to sell his peanut farm...
1
1
178