Manouk Draisma's profile on Product Hunt

About

Hey Product Hunters! 👋 I'm co-founder of LangWatch.ai - build up from the painpoint of having limited control over LLM apps. We've build the end-to-end evaluation framework for AI engineering teams. Not just obervability or evals, but finding that right eval for your Agents. The past 10+ years I have been working in the start-up tech space, and what a crazy ride it has been... 🤯 Started 10 years ago at a Start-up, which went IPO within the first years I worked there. Building teams, partnerships, connecting with users and customers is what I love. 🤝 ❤️ In the meantime, I will add value where ever possible and support new product launches. Connect with me here and also on LinkedIn! ✌️

Work

Founder & Leadership at LangWatch

Links

LangWatch

Badges

Buddy System

Plugged in 🔌

Gemologist

Top 5 Launch

View all badges

Maker History

LangWatchAI Agent Testing, Observing & Evaluation

🎉

Joined Product HuntOctober 28th, 2023

Forums

•

5d ago

Which session burned your budget? Claude Code usage tracker by LangWatch

Hey everyone!
Launching a new feature of LangWatch today on ProductHunt, developer focussed but not just dev's anymore, so also curious what each of you think.
You know what Claude Code costs per seat. But do you know which sessions burned the budget, which model did the work, or whether your cache paid off? LangWatch now tracks every Claude Code session: tokens, costs, cache hits, bash commands, MCP tool calls, file edits, and full terminal replays. Works with Claude Code, Codex, Gemini CLI, and opencode.
If you want to support us, feel free to do so

You can find us under "LangWatch" on the launching page!

•

1yr ago

I build the world's first AI Agent Testing platform to run Agent simulations.

Hey Product Hunt

Manouk here, I m the co-founder of LangWatch, and today we re incredibly excited to launch LangWatch Scenario, the first platform built for systematic AI agent testing.

Over the last 6months, we ve seen a massive shift: teams are moving from simple LLM calls to full-blown autonomous agents, handling customer support, financial analysis, compliance, and more. But testing these agents is still stuck in the past.

•

1yr ago

LangWatch Scenario - Agent Simulations - Agentic testing for agentic codebases

As AI agents grow more complex, reasoning, using tools, and making decisions, traditional evals fall short. LangWatch Scenario simulates real-world interactions to test agent behavior. It’s like unit testing, but for AI agents.