Turn production traffic into unit & integration tests. 10 lines of code. Backed by Y Combinator.
San Francisco, CA
Joined October 2023
- Tweets246
- Following15
- Followers268
- Likes561
Tusk retweeted
love when the audience asks thoughtful questions, s/o to @patricia_dugan for hosting last week’s Agents & APIs meetup
pictured: @sohilkshirsagar telling war stories and showing how we repro traffic
Tusk retweeted
Super cool learning @sohilkshirsagar’s backstory and what he and @marcel7an are building at @usetusk @ the @getpostman Agents and APIs meetup tn!
Tusk retweeted
Sharing about execution boundaries for agents here next week.
If you love thinking deeply about agent infra, come say hi!
growing up i've organized nightclub events, duolingo streak parties, and even a music festival
now i'm hosting a meetup series for the people building infra for coding agents. first event is Thu, May 7 in SF featuring:
- @aditabrm at @reductoai
- @MelkeyDev at @vercel
- @juecd__ at @usekernel
- @jyt4n at @usetusk
Tusk retweeted
Hey thats me!
Come hang out while I tell you how were building everything you will ever need for your agent
growing up i've organized nightclub events, duolingo streak parties, and even a music festival
now i'm hosting a meetup series for the people building infra for coding agents. first event is Thu, May 7 in SF featuring:
- @aditabrm at @reductoai
- @MelkeyDev at @vercel
- @juecd__ at @usekernel
- @jyt4n at @usetusk
Tusk retweeted
growing up i've organized nightclub events, duolingo streak parties, and even a music festival
now i'm hosting a meetup series for the people building infra for coding agents. first event is Thu, May 7 in SF featuring:
- @aditabrm at @reductoai
- @MelkeyDev at @vercel
- @juecd__ at @usekernel
- @jyt4n at @usetusk
Tusk retweeted
AI is transforming software development, but more code means more pull requests, more edge cases, and more QA pressure on engineering teams.
Tusk, a Y Combinator startup, catches bugs that slip past both AI agents and humans using AI-enabled tests based on real production traffic. Built on Amazon Bedrock, Tusk flags issues before code merge so teams can focus on building great products.
Tusk retweeted
🌉 April 30 - Agents & APIs SF Developer Meetup
✨ Ben Warren @bwarrn, Founder, @mesa_dot_dev
✨ Ben Backus @BenBackus4, SWE, @greptile
✨ Nihar Kumara, Sr. SWE, Postman!
✨ Sohil Kshirsagar, Co-Founder & CTO, @usetusk
Space is limited! Register 👉 luma.com/agents-AI-apis-apri…
Tusk retweeted
We all have learned that testing is crucial before pushing to production.
Tusk (YC W24) generates tests based on your codebase, catching all edge cases too, and prevents regressions.
Using E2B persistent environment for that too.
Catch all the other fast-growing startups in SF! 🌉
Tusk retweeted
So excited to have @usetusk (and @marcel7an ) in our Auth0 for Startups program! They're building an all-in-one testing platform that automatically creates and maintains unit and API tests from your live traffic. Check out their interview below 🎬
AI is helping teams ship 10x more code. Testing hasn’t caught up.
@usetusk is fixing that by turning production traffic into automated tests.
Featuring @marcel7an + how @auth0 secures it all 👇
Truly groundbreaking technology
Tusk retweeted
catching bugs locally is a skill issue
so we made one. no more waiting on CI to see if you've broken features your users rely on
>replays production traffic as tests against your diff
>reads API response deviations
>flags regressions
>fixes code
>re-runs tests
>iterate until passing
Tusk retweeted
this past quarter, the number of tests we created for users grew 50.4% MoM
wild part is this month's count is close to the total created in the 3 months before. background agents have achieved lift off
Tusk retweeted
Your tests/specs are only as good as your input.
And there's no better input than production traces. Your coding agents need to see how real users actually hit your API.
This means giving the agent every request/response body and database call, instead of old mocks that long drifted from reality.
Here's how we record production traffic and pipe the traces to your coding agent. You can replay as tests and diff API responses against real user behavior.
