LangWatch @LangWatchAI

Open Source LLM Ops & Evaluations Platform https://t.co/CrsnEmal2g ➡️ DSPy Optimizations ➡️ Scenario Agent Simulations langwatch.ai Joined April 2024

Tweets

120
Followers

583
Following

209
Likes

163

LangWatch @LangWatchAI

19 hours ago

In agent demos, everything’s smooth. In prod? You get messy inputs, long chains, weird edge cases — that’s when things snap. We treat agents like code → write scenario tests first, simulate full workflows, then iterate until green. Think TDD, but for LLMs. More on how we do it…

0 0 0 49 0

LangWatch @LangWatchAI

4 days ago

“Do I really need evals?” The real q: how do you know your AI agents will behave in prod? Prototypes don’t need them. Scaling products do. That’s why we built Agent Simulations; Unit tests for AI. The only way to know if you can ship reliably. OSS: github.com/langwatch/scen…

0 1 1 54 0

LangWatch @LangWatchAI

4 weeks ago

We’re hosting a Meetup in our office in Amsterdam on Sept 18 all about agentic AI. 👀 👀 👀 Talks from: • @_rchaves_ (CTO, LangWatch) → Beyond Unit Tests: why agent simulations are redefining AI agent testing. • Deepak Grewal (Kong) → Agentic AI -> powering the next wave…

0 0 2 110 0

Download Image

Kong Inc. @thekonginc

a month ago

In Amsterdam and want to spend an evening networking and learning all about agentic AI? Come to our @Meetup with @LangWatchAI on September 18th! RSVP to save your spot > bit.ly/3JyBwgY

0 2 1 370 0

Download Image

LangWatch @LangWatchAI

2 months ago

The gap between model release hype and production reality is always bigger than it looks. OpenAI’s new GPT-5 headlines focus on the measurable: fewer hallucinations, better reasoning, faster responses. All great gains. But the real story? How it works in your workflows, with…

0 0 0 162 0

LangWatch @LangWatchAI

2 months ago

Start tracing AI SDK 5 with LangWatch today: docs.langwatch.ai/integration/ty…

AI SDK @aisdk

2 months ago

Start tracing AI SDK 5 with LangWatch today: docs.langwatch.ai/integration/ty…

66 144 1K 273K 627

Download Image

0 0 8 476 2

Rogerio Chaves @_rchaves_

2 months ago

We've won second place in the Power of Europe Hackathon in Amsterdam with this one ;) more on it soon!

Kilo Code @kilocode

2 months ago

We've won second place in the Power of Europe Hackathon in Amsterdam with this one ;) more on it soon!

1 1 3 718 1

Download Image

0 1 6 473 0

Kilo Code @kilocode

2 months ago

First up - built with Kilo Code is an MCP tool that visually tests real applications with computer use and scenarios powered by @LangWatchAI

1 1 3 718 1

Download Image

Rogerio Chaves @_rchaves_

2 months ago

Here is how to test Voice Agents, using Scenario simulations 👇

2 3 6 648 6

Download Image

Rogerio Chaves @_rchaves_

2 months ago

notes on agent testing discussion with the team

0 3 11 609 4

Download Image

Rogerio Chaves @_rchaves_

3 months ago

always so satisfying to watch a DSPy optimization happening

3 4 95 8K 83

Download Image

Rogerio Chaves @_rchaves_

3 months ago

First impressions of Grok 4 ✅ it passes all the Scenario agent simulation tests on the 13 different agent frameworks in create-agent-app ❌ probably because of the reasoning, but facing quite high latency using it as an agent 🤔 on our vibe coding test, the website it designs…

1 2 14 1K 0

Download Image

LangWatch @LangWatchAI

3 months ago

Now you can ship AI agents faster with developer-first testing. LangWatch Scenario allows you to test your agents like you test your code. That’s because: ❌Manual testing doesn't scale. ❌"Vibe checking" isn't systematic. ❌Hope isn't a strategy. That's why we’re building…