Launching today

Bonacci Studio

Launching today

Agentic, Visual Data Engineering and Data Science Platform

5 followers

Agentic, Visual Data Engineering and Data Science Platform

5 followers

Visit website

Most AI data tools stop at generating a snippet you still have to run yourself. Bonacci Studio's agent has real tool access: it connects to your database, inspects schemas, writes PySpark or SQL, executes it on Spark, streams logs back, and debugs its own failures. Also included: a visual drag-and-drop DAG builder, Kafka streaming, Apache Camel API integration, RAG knowledge bases, and native MCP support. Bring your own model - Claude, GPT, Gemini, Groq, or fully local via Ollama

Free Options

Launch tags:Developer Tools•Artificial Intelligence•Data & Analytics

Launch Team

Blocks.aiThe Control Plane & Network Layer For AI Agents

Promoted

Maker

📌

Hey Product Hunt 👋 I've spent years building data pipelines, and the same thing kept happening: I'd ask an LLM for help, get a beautiful PySpark script, and then spend the next 40 minutes finding out it hallucinated three column names that don't exist in my schema. The model wasn't the problem. The model just couldn't see anything. So I built Bonacci Studio around one idea: give the agent real access, not a description of reality. When you ask it to build a daily revenue rollup, it doesn't guess - it calls inspect_schema("orders"), gets back 14 real columns and 2.4M rows, writes the PySpark against what's actually there, runs it on Spark, and streams the logs into your browser. If it fails, it reads its own stack trace and fixes it. What's in it: • Agentic engine - DB tools, SSH tools, code-gen, all in a real tool-calling loop • Visual DAG builder - drag-and-drop for when you'd rather not type • Three engines under the hood - Spark (batch), Kafka (streaming), Camel (APIs) • Native MCP - client and server, so the agent extends to any MCP tool, and your other agents can drive Studio • Bring your own model - Claude, GPT, Gemini, Groq, or fully local with Ollama • RAG knowledge bases so the agent knows your internal docs, not just your schema It's built on Apache Spark, Kafka and Camel - proven infrastructure for data heavy loads. The name derived from 'Fibonacci'. Pipelines grow the way nature does, one connection building on the last. Free tier is real, not a trial - bring your own model key, connect a source and a target, and actually run pipelines. No card. $29/mo if you want scheduling and more room. I'm here all day and genuinely want the honest feedback.

Report

1d ago

The agent debugging its own failures is honestly such a nice touch. One thing though, would be great if you could save and version the generated PySpark or SQL as actual files in a connected Git repo right from the studio, basically turning the agent runs into proper commit history you can review or roll back later.

Report

2h ago

Blocks.aiThe Control Plane & Network Layer For AI Agents

Promoted

Maker

📌

Report

1d ago

Report

2h ago