Point it at your data
Connect a Databricks SQL warehouse or a PostgreSQL database, browse the catalog, and pick the entities that belong in a dataset. A session works over the datasets you choose — nothing wider.
An experiment from Halo Powered Labs
Halo BI Assistant
Questions in. Insights out.
A desktop app that answers business questions over your own warehouse — by planning the analysis, writing the SQL, running it, and explaining what came back. Every number traces to a query you can read.
Databricks SQL
PostgreSQL
macOS & Windows
Runs on your machine
BI tools make you build the question. This one answers it — and shows its work.
You ask in plain language. The assistant maps the question onto the real entities and columns in your data, runs read-only SQL until it has the answer, and replies with the numbers, the comparison, and a short takeaway — citing the tables it used. When the data doesn't cover what you asked, it says so instead of filling the gap.
Grounded
Every factual claim comes from SQL executed in the conversation — never from what the model already believes.
Tailorable
Visuals are conversation participants. Ask for a change; the chart updates, versioned, revertible.
Local
One installer. The app, its API and its database all run on your machine — no service to stand up.
How it works
From a question to an answer you can defend.
One loop per question. Each step is visible in the app, so a reviewer can follow the reasoning from the sentence you typed down to the rows that produced the number.
Ask in business language
The assistant resolves the question against real schemas and sample values. When the metric itself is undefined — "best", "top", "performed well" — it asks one short question with concrete options drawn from your data, rather than guessing.
It writes and runs the SQL
Read-only queries, chained as far as the analysis needs, favouring aggregations so results come back small and meaningful. You see the SQL, the row counts, and a sample of the rows behind every answer.
Answer, then visual
The reply carries the numbers, the ranking, the takeaway and the entities it used. Ask for a chart and it builds one from that answer's own rows — then keeps tailoring it as you talk, with every version kept.
What's inside
The parts that make the answers trustworthy.
Most of the app is not the chat box. It's the machinery that keeps an answer honest when the schema is messy and the business vocabulary is not in the column names.
Curated knowledge
Glossary terms, standing instructions and default filters you author once. They outrank whatever the model would infer from a column name, and the assistant names which filters it applied.
Interactive visuals
Charts you refine by conversation. Each visual is versioned, revertible, and exports as a self-contained page with the question, the analysis, the SQL and the data.
Data provenance
Every visual and answer carries the query that produced it, how many rows came back, and the first rows themselves — collapsible, but always there.
Deep analysis
For the bigger questions: the assistant plans several angles of attack, investigates each one, and synthesises the findings into a written report saved to the session.
Verified queries
Promote SQL you trust into a reusable, known-good answer, so the next person asking the same question gets the same numbers.
Evaluations
Run a question set against the agent, grade the results, and compare runs over time — so a prompt change that quietly breaks an answer shows up as a regression.
Sessions with memory
Each session keeps its own transcript, memory thread and workspace, so follow-up questions build on the analysis instead of restarting it.
Bring your own model
Point it at OpenAI or at LenAI, Halo's internal OpenAI-compatible gateway. The key is stored encrypted on your machine and tested from the settings screen.
Single-app delivery
The installer ships the interface and its API together. Launch the app and everything it needs starts with it — no runtime to install, no server to operate.
Get the app
Download Halo BI Assistant.
Installers are built per platform. Pick the one that matches your machine — on a Mac, Apple silicon is arm64 and Intel is x64.
On first launch, open Settings and add your model provider key and a data connection. macOS builds are not notarised yet — if Gatekeeper blocks the app, open it once via right-click → Open.
Where your data goes
It runs where you run it.
The assistant is a desktop app, not a hosted service. Your warehouse credentials, your sessions and your answers stay on the machine that installed it.
Data sources
Databricks SQL warehouses and PostgreSQL databases, queried read-only.
Storage
Sessions, datasets, knowledge and settings live in a local database in the app's own user-data directory.
Leaves the machine
Queries go to the warehouse you connected; prompts go to the model provider you configured. Nothing else.
Credentials
Model provider keys are stored encrypted locally and never rendered back into the interface.
Platforms
macOS (Apple silicon and Intel) and Windows x64.
Status
An active Labs experiment — shipping often, and built alongside the teams using it.
Have a question your dashboard can't answer?
That's the one we want. Bring it to the bench and we'll come back with a working answer — and the evidence behind it.
Talk to the Labs