Ask your data a question. Get a chart back in seconds.
Business teams depend on analysts or engineers for even simple data questions — "what were our top products last month?" — creating delays and bottlenecks that slow down decisions.
A natural-language analytics platform: ask a question in plain English, the system generates SQL with a confidence score, executes it, and streams back a chart and summary in seconds.
View the source — Text2Insight on GitHub
View Source ↗User Question -> LLM SQL Generation (confidence-scored) -> DuckDB Execution -> Chart + Summary (streamed via SSE)
Self-reported from my own testing, not a third-party audit.
For simple business AI implementations — chatbot, FAQ assistant, basic knowledge base.
Workflow automation, AI agent, API/Telegram/email integrations.
RAG, NL2SQL, business analytics, document intelligence, advanced agents.
For larger or more complex requirements — scoped on a call.
Directional, not a fixed quote — real scope depends on your data and integrations.
Around 90%+ on standard queries in my own testing — self-reported, not a third-party audit. Complex multi-table joins are harder than simple aggregations, which is why every query gets a confidence score, not a blind execute.
Built on DuckDB for the reference implementation, but the same NL2SQL pattern adapts to Postgres, MySQL, or a CSV/warehouse export depending on where your data actually lives.
Yes — the system streams back a chart and a plain-English summary together, so you get the "what happened" alongside the "why it matters."
Tell me what you're trying to solve — I'll tell you honestly whether this is the right fit.