Ship AI that works, not AI that "feels right"
🛠 Prototype high-quality prompts and Agents from our UI or your codebase.
✅ Test & Evaluate LLM outputs through a dataset of scenarios.
🚀 Deploy AI features confidently with our SDK.
📊 Monitor & Optimize your AI with automated tracking & insights.
💡 Collaborate with your team for better AI-driven products.
No more guesswork—just better AI, faster. 🔗
This is the 2nd launch from Basalt. View more
Basalt Agents
Basalt, #1 AI observability tool for teams, is launching its brand new Agent Builder : prototype, test, and deploy complex AI flows composed of multiple prompts, and run them through a dataset of scenarios.
Free Options
Launch Team / Built With
Blocks
Guys ! so happy to have you back on Product Hunt, the platform has powered up so much congrats !
Basalt
@vicgrss thanks Vic !!
Triforce Todos
This looks amazing, François! 👀 How does the evaluation part work across different models?
UI Bakery
Great launch! How does Basalt prevent overfitting on the evaluation dataset — e.g. if prompts start optimizing too much to test cases and lose generality?
Basalt
@vladimir_lugovsky great question !! To avoid overfitting, we recommend creating a dynamic dataset, meaning that you continuously enrich it with new test cases from your logs (something you can do from Basalt or programmatically) !
Happy to discover the product! No more excel sheets for evals ;))
Basalt
@steffanb exactly !! Thanks :)
Congrats on the launch! Curious if there's any example workflow with multimodal (video, speech) results?
This looks solid! The evaluation-first approach is exactly what's needed. Curious how you handle workflows that need human approval gates between steps, not just eval metrics, but hard stops for review before continuing?