Databricks AI/BI Dashboards vs Mitzu: KPI Dashboards on Databricks, and the Why Behind Them

Databricks AI/BI Dashboards and Mitzu both put KPI dashboards on your Databricks data. AI/BI turns tables and SQL datasets on your lakehouse into charts, and Genie answers questions by writing SQL. Mitzu is an analytics platform on your data warehouse for BI, product analytics and experiment analysis, where the data team governs the metrics and everyone uses them through dashboards, an AI agent, Slack and their own AI assistants.

For a weekly revenue, orders and margin dashboard, the two are direct alternatives: both chart it, both share it and both let you ask about it in plain English. The difference shows up when that number moves and someone asks where do new users drop off before paying, which channel converts best, and how much revenue do those customers bring? This comparison covers KPI reporting first, then walks through that question in both tools, with tables for what is the same, what is different, how the AI works, and where each one fits. It is written for data teams choosing a BI layer on Databricks, and for the product, growth, sales and marketing people who will use it.

What is Databricks AI/BI?

Databricks describes AI/BI as "a new type of business intelligence product" for self-service data analysis. It has two parts. AI/BI Dashboards are built from datasets (tables, views or custom SQL queries) with a library of more than 20 visualization types, global, page and widget filters, cross-filtering, drill-through, schedules, email and Slack subscriptions, and embedding. Genie is the conversational part: you ask a question in plain English, and Genie writes and runs a SQL query against the tables an author has added to a Genie space. For open-ended questions, its Agent mode drafts a research plan and runs several queries.

It is a strong choice for KPI reporting over tables an analyst has already modeled, including reporting where there is no customer behind the row: general ledger and P&L, inventory, cloud and warehouse cost, SLAs. It needs no separate BI license or data extract, and it inherits Unity Catalog permissions. If your question can be answered by grouping and summing columns in a table, AI/BI Dashboards will chart it well.

What is Mitzu?

Mitzu is an analytics platform on your data warehouse for BI, product analytics and experiment analysis, where the data team governs the metrics and everyone uses them through dashboards, an AI agent, Slack and their own AI assistants. It covers KPI reporting on metrics such as net revenue, orders, average order value and margin, and the funnels, journeys and experiments that explain them, without anyone writing SQL. It needs one thing up front: business and event data already in your warehouse, such as order and revenue tables and product, sales or marketing events from Segment, Snowplow, RudderStack, Firebase, GA4, Stripe or your own pipeline. Mitzu connects to a Databricks SQL warehouse on AWS, Azure or GCP and queries the tables in place.

At setup, the Configuration Agent scans your warehouse, finds event and dimension tables, and builds a semantic layer of events, properties and customer attributes. Mitzu drafts metric definitions from your warehouse and dbt models, and the data team reviews and owns them. From then on, everyone works on those definitions: KPI dashboards, funnels, retention, segmentation, journeys and A/B test analysis. They can build them by clicking or ask the Analytics Agent, in the app, in Slack, or from any MCP-connected assistant, and scheduled agents can review a dashboard and email the team when something moves.

Where Databricks AI/BI and Mitzu overlap?

For KPI dashboards and self-service reporting, the two are direct alternatives. Both are warehouse-native in the plain sense: the data stays in Databricks and the queries run on your SQL warehouse.

The core difference: a KPI chart vs the analysis behind it

On the KPI dashboard itself, both tools do the same job. The gap opens one question later, when a number moves and someone asks which step, which channel or which users. A classic BI tool has no idea what a user, a visitor or a journey is. It knows tables, columns and aggregations. That is not a shortcoming; it is what makes BI general enough for ledgers, inventory and cost reporting. It does mean the journey work has to happen somewhere else first, usually in SQL that an analyst writes. Mitzu computes it from events on the same governed metrics, so the revenue on the dashboard and the revenue in the funnel are the same number. For the general case, see the difference between analytics and product analytics.

You can see this in the AI/BI documentation. Its funnel chart takes a step column and a value column, and the example shows already-counted stages (10,000 visited, 4,000 signed up). Its cohort chart expects pre-computed retention values, and its Sankey diagram takes stage columns and a value. These are good charts. But the hard questions (in what order, within how many days, counted per user or per account, and who dropped off) are answered in the SQL that produced the numbers, not in the chart.

Revenue, orders and marketing conversion on the same metrics

In Mitzu, KPI reporting and journey analysis share one set of definitions. The data team defines metrics such as net revenue, orders, average order value and margin once on fact and dimension tables, and the same metrics appear on KPI dashboards, in agent answers and in A/B test results. Where a row also has a user, visitor or account behind it, Mitzu can follow it through the journey. An order, a payment, a subscription renewal, a page visit with a UTM campaign and a demo request are all events with a subject.

Order value, discount and plan are event properties. Country, segment and acquisition channel are customer attributes from a dimension table.

On top of counts and unique users, Mitzu aggregates any numeric property with sum, average, median, min, max or a percentile from P75 to P99. That turns order and payment events into revenue, average order value and revenue per customer. Retention on a purchase event gives repeat purchase rate, and summing its price property gives retained revenue month over month. A funnel from a campaign visit to a payment, summing the payment amount, gives the revenue those visitors brought in.

Time-to-convert measures (average, median or any percentile) answer how long the first order takes.

AI capabilities compared

Both products put AI at the front. The difference is in what the AI produces. Genie's language model writes SQL, which a reviewer then checks. Mitzu's Analytics Agent never writes SQL: it assembles an analysis specification (funnel steps, conversion window, breakdown, measure), and a deterministic query engine turns it into SQL. The same specification always produces the same SQL, which is what makes the rest of the answer reviewable.

Reviewing a Mitzu AI answer end to end

Once AI writes the charts, the question that matters is whether you can trust them. For a product or marketing manager, the answer cannot be “read the 80-line SQL query.” What they can check is the logic: which events, in what order, over which window, broken down by what. In Mitzu, every link between the question and the number is visible:

Genie gives a reviewer real tools too. Each Genie response has a “Show code” view of the generated SQL, an Analysis section explaining how Genie read the question, a Trusted label when the answer used a query or function an editor added, and buttons to give feedback or request review. Databricks is also candid that Genie, like other LLMs, can be non-deterministic and should be reviewed carefully. The review still ends in SQL: the window, the step order and the attribution a PM wants to check only exist inside a query the LLM wrote for this run.

Here is what the trail looks like for a real question in Mitzu's demo SaaS project: Where do new users drop off between sign-up and their first subscription, and which acquisition channel converts best?

Expanding the funnel step shows exactly what was built: four events in order, a breakdown by the campaign property on the first step, and the conversion measure. The written answer also states its assumptions. Here it pointed out that the campaign is recorded on page_visit, not on the sign-up event. It also flagged that the result used 10% sampling and that some channels had only single-digit conversions.

Self-service: who can change the question?

Self-service is not about who can look at a dashboard. Both tools do that well. It is about who can change the question when the first answer raises a second one: a 7-day window instead of 30, trial users only, revenue instead of conversion, broken down by plan instead of channel.

In AI/BI Dashboards, the logic lives in the dataset. Creating a dashboard needs the Databricks SQL entitlement and CAN USE access on a SQL warehouse, and datasets are SQL queries or tables. Viewers can filter, cross-filter and change any parameters the author exposed, such as the length of a conversion window. Authors can also add calculated fields without touching the dataset query.

A change the author did not anticipate, like a new step, a different step order or counting per account instead of per user, means editing SQL, or asking Genie and reviewing the new SQL it writes. For most PMs and marketers, that means a request to the data team.

In Mitzu, every agent answer has an Open Insight link. It opens the same funnel in the no-code builder, with the agent still alongside. Steps, filters, breakdowns, “Convert within 30 days”, “Analyze uniques by User” and the sampling rate are controls on the left. Anyone can change them and the engine regenerates the SQL. They can also ask the agent to do it.

One journey question, three ways

Take the question from the review example: Where do new users drop off between sign-up and their first subscription, and which acquisition channel converts best?

In Mitzu's demo project, the answer also flagged that the paid and seasonal campaigns converted no trials to paid in the window, and suggested the next questions to ask. A follow-up question (“show this as a journey, including where users drop off”) returned a Sankey with an explicit drop-off node after each step. A third (“how much subscription revenue did each campaign bring in?”) only needs a different measure on the same funnel.

Which questions go where?

When to use Databricks AI/BI, Mitzu, or both?

Setting up Mitzu on Databricks

1. Connect a Databricks SQL warehouse (serverless or Pro recommended) with its host, HTTP path and catalog. See the Databricks connection guide.
2. Let the Configuration Agent scan your warehouse. It recognizes common Segment, Snowplow, Firebase and GA4 schemas and maps users, accounts and dimension tables. Order and payment tables join the same way.
3. Review the semantic layer and the metric definitions Mitzu drafts, such as net revenue and orders: event names, descriptions and which properties are visible.
4. Invite teammates and set who can see what. Plans include editor seats and unlimited events, with no per-event pricing.

For KPI reporting, see BI and warehouse metrics. For a longer walkthrough, read Mitzu and Databricks in practice, or compare options in the top Databricks tools for product analytics.

FAQ

What are the limitations of a Databricks dashboard?

AI/BI dashboards chart datasets. Authors can add calculated fields without editing the dataset query and expose parameters, such as a window length, that viewers change at runtime. Journey logic the author has not built in (funnel step order, per-user conversion windows, retention cohorts, paths) still has to be written in the dataset SQL first. Viewers can filter and change exposed parameters, but not the logic behind them.

For a KPI dashboard over modeled tables these limits rarely matter; they show up when someone asks why a number moved.

Is Databricks AI/BI a customer journey analytics tool?

No. Databricks describes AI/BI as a business intelligence product. It can show journey metrics once they are computed, and it has funnel, cohort and Sankey charts, but these chart values from a dataset rather than following users through their events.

Can Mitzu analyze sales, orders and revenue?

Yes. The data team defines metrics such as net revenue, orders, average order value and margin once on fact and dimension tables, and they power KPI dashboards and agent answers. Where a user, visitor or account is behind the row, the same metrics also break down by customer attribute or campaign and feed funnels and retention, such as repeat purchase rate and revenue per customer. Teams with heavy ledger-level finance reporting often keep a BI tool for that.

Can I review how Mitzu's AI reached an answer?

Yes, end to end. You can approve the plan before it runs, expand every step the agent took with its inputs, read the analysis specification, open the SQL the deterministic engine generated, list the users behind any number, and open the insight in the no-code builder to change it.

Can Databricks AI/BI Dashboards build a funnel?

It can display one. The funnel chart takes a step column and a value column, so the counts per step, the step order and any conversion window have to be calculated in the SQL dataset. Mitzu calculates the funnel itself from event data, with the window and order as settings.

Does Mitzu replace Databricks AI/BI?

For KPI dashboards and self-service reporting, many teams use Mitzu instead, and get product analytics, experiment analysis and the agent on the same governed metrics. Teams with heavy pixel-perfect or financial reporting, such as the general ledger and P&L, often keep AI/BI for that, since it is already part of Databricks.

Does Mitzu copy data out of Databricks?

No. Mitzu runs its queries on your Databricks SQL warehouse and reads event tables in place. The AI agent only receives aggregated results and metadata, not raw rows, and your data is not used for model training.

How is Mitzu different from Databricks Genie?

Genie's LLM writes SQL against the tables in a Genie space. Mitzu's agent never writes SQL. It builds a funnel, retention, segmentation or journey specification, and a deterministic engine generates the SQL. That is why every Mitzu answer can be reviewed end to end and opens as an editable insight.