you: load orders from Postgres, dedupe by id, stream to the warehouse agent building...
postgres_prod
dedupe(id)
warehouse
Describe a pipeline in plain English, or wire it up visually. An AI agent builds, tests, and deploys it on Apache Spark and Kafka. From idea to running pipeline in minutes, not sprints.
No credit card. Bring your own model keys.
Studio turns plain language into real, version controlled pipeline code that runs on distributed infrastructure. You stay in control of every step.
Type what you want, or drag nodes on the visual builder. Both stay in sync.
Pipelines compile to Spark and Kafka jobs. Production infrastructure, not a sandbox.
OpenAI, Anthropic, Gemini, Groq, or local Ollama. No lock in, no per seat AI tax.
# generated by the agent, editable by you source postgres_prod { table = "public.orders" mode = "cdc" # change data capture } transform dedupe { by = ["id"] keep = "latest" } sink warehouse { engine = spark to = "analytics.orders" }
Agents are non-deterministic. We treat that as an engineering problem, and it shapes everything we ship.
N agents race the same task in isolated git worktrees. You review the diffs and merge the winner. Git is your undo.
A ThinkingMemory backbone recalls schemas, decisions, and outcomes into every run, so agents build on what they already know.
Before any irreversible action, a forward check simulates the result. Destructive commands are rejected, even in full-auto mode.
Studio is the platform. These are the layers underneath it, free and open for the community.
Parallel agent fleets and persistent memory for coding and data engineering, in your terminal. Free, bring your own keys.
A memory database for agents. Intent goes in, the right context comes out, packed to a token budget.
A typed, compiled language where tables, streams, and models are native types.
Real analyses, built and executed by agents in Bonacci Studio, published with the data.
Pricing data across 12 providers and three years, analyzed end to end by an agent in Studio.
read the analysis →Four public datasets, three occupation coding schemes, one crosswalk, built in Studio.
read the analysis →25 months of GitHub, arXiv, and Hugging Face activity. The agent wrote and ran the PySpark.
read the analysis →No slides, no recording. We open Studio with you, describe a pipeline in plain language, and ship it to Spark while you watch.
Plain English. Source, transform, destination.
Generates the pipeline, runs it against sample data.
Running on Spark and Kafka, rows landing in the warehouse.