The analytics agent that doesn't write SQL
Ask about revenue, a funnel, retention or an A/B test in plain English. Mitzu's agent composes each analysis against the semantic layer your data team governs — and a deterministic query engine generates the SQL on your warehouse, so the same question gets the same answer.
What is an analytics agent?
An analytics agent is an AI system that answers business questions by planning and running analyses on your data, then returning the answer with the evidence behind it. A dashboard answers the question it was built for; a chatbot that turns one sentence into one SQL query is a translation layer. An agent takes the follow-up question and investigates from several angles before it answers.
Mitzu's analytics agent answers questions, explains why metrics moved and runs deep dives on your governed metrics. It builds analysis specifications that a deterministic engine turns into SQL, so the same question gets the same answer. It runs on the data already in Snowflake, BigQuery, Databricks, Redshift, ClickHouse and other warehouses, and needs one there: events, revenue and CRM tables in one place are what let it answer across them.
Read the full definition, the main architectures and what makes an agent trustworthy.
The agent composes the analysis. The engine writes the SQL.
Mitzu's Analytics Agent does not write SQL. It composes analysis specifications — funnels, retention, segmentations — against a semantic layer specialised for product analytics, and a deterministic query engine turns each specification into SQL that runs in your data warehouse. That is why funnel, retention, and cohort methodology stays correct instead of depending on a model getting the SQL right.
The agent interprets the question
It maps your words to real events, properties, and cohorts in the semantic layer that the Configuration Agent built from your warehouse — filters are suggested from sampled values that actually exist, not invented.
It composes an analysis specification
A metric and its breakdown, a funnel's steps and conversion window, a retention cohort and its return event, an experiment and its metrics. The agent fills in these parameters. It never authors query text.
A deterministic engine generates the SQL
The same specification always produces the same SQL, executed in your warehouse. Funnel, retention, and cohort methodology lives in the engine, so the model cannot get it wrong — and the SQL is shown for your analysts to verify.
The same architecture powers the agent in the app, in Slack, and over MCP, on top of Mitzu's warehouse-native architecture — read the full mechanism reference at docs.mitzu.io: how the agent works.
Analytics agent vs dashboards, text-to-SQL and BI chatbots
| Dimension | Static dashboards | Text-to-SQL and BI chatbots | Agents inside a product analytics tool | Mitzu's analytics agent |
|---|---|---|---|---|
| Who writes the SQL | An analyst, once per chart | The language model, on every question | The vendor's query engine, over its own event store | A deterministic engine, from the agent's analysis specification |
| Same question, same answer | Yes, for the questions the chart was built for | Not guaranteed: the query can change between runs | Yes, inside the tool | Yes: same specification, same SQL |
| Follow-up and “why” questions | A new request to the data team | One query per question; the investigation is up to you | Yes, on the data the vendor ingested | Root cause, impact analysis and deep dives |
| Funnel and retention methodology | Hand-built for each chart | Written freehand; conversion windows and cohort bucketing are easy to get wrong | Built in | Built into the engine |
| Data it can reach | The modelled tables behind each dashboard | The warehouse it is attached to | Events sent to the vendor; billing, CRM and support data sit elsewhere | Everything in your warehouse: events, revenue, CRM and experiment exposures, joined |
| Metric definitions | In the BI model | A semantic layer you write and maintain, or none | The vendor's own | Governed by your data team and shared with every dashboard |
| Where people use it | The BI tool | A warehouse console or chat window | Inside the vendor's app | The Mitzu app, Slack, and MCP clients such as Claude and ChatGPT |
The longer version, with a checklist for evaluating tools in a pilot: analytics agents vs text-to-SQL and BI chatbots.
Where teams use an analytics agent
Product teams
“Why did week-2 retention drop after the v2.3 release?”
Diagnose funnel drop-offs, cohort behaviour and activation friction without waiting for an ad-hoc query.
Marketing and growth
“Did the email campaign move conversion?”
Connect campaigns and channels to product outcomes and revenue, on the same definitions the rest of the company reports.
Leadership and operations
“Revenue dropped last week. Which funnel step, and which users?”
Go from a KPI to the funnel step and the users behind it in one question, because the KPI and the funnel share one set of definitions.
Data teams
Define net revenue once.
Keep governance while everyone self-serves: the agent, dashboards and Slack answers all use the metrics and permissions you set.
Get started in minutes, not weeks.
01/2 min
Connect your data warehouse
Agent config scans your warehouse and creates semantic layer.02/5 min
Create a semantic layer
No need to write YAML at all. The produced data catalog is designed specifically to work with product analytics.03/Instant
Ask anything
Our deterministic SQL engine makes sure there are no hallucinations.
Built for questions that demand deep diagnosis.
Did that release actually move conversion? Did the campaign change behaviour? Mitzu compares cohorts, finds correlations, and tells you whether that feature, campaign, or product change made a real difference.
Ask why a metric moved. Mitzu fans out across funnels, cohort breakdowns, and segment comparisons, running as many tool calls as the answer requires, and comes back with a synthesised finding.
Do users who complete onboarding in under 5 minutes retain better? Does hitting feature X in week one predict long-term engagement? Mitzu tests your assumptions against real cohort behaviour, and tells you whether the hypothesis holds.
Don't wait to ask the question. Mitzu monitors your warehouse and surfaces metric shifts, retention anomalies, and activation drops before anyone thinks to look. The insight finds you via email or Slack, before it becomes a problem.
Ask questions like you're talking to a colleague
Type the question the way you would ask an analyst. The agent picks the analysis, runs it on your warehouse and answers with the chart and the SQL behind it.
- Revenue, funnel, retention and A/B test questions in one conversation
- Filters come from values that exist in your data, not guesses
- Follow-up questions keep the context of the thread
- Every chart can go straight onto a shared dashboard
Mitzu AI Agent
What was our conversion rate last week?
Your conversion rate last week was 4.2%, up 0.5% from the previous week. The highest performing day was Thursday with 5.1%.
Why did it increase on Thursday?
Thursday's increase correlates with your email campaign launch. Users from the campaign had a 6.8% conversion rate.
A dashboard you have to remember to check is worse than one that watches itself
Scheduled agents run your questions on a cadence and email you only when the results meet a condition you set — a metric drop, a threshold crossed, a cohort behaving differently.
- Runs on the schedule you choose
- Alerts only when your condition is met
- Same semantic layer and deterministic engine as every other surface
- Findings arrive with the supporting charts
AI Insights
Auto-detected today
Conversion Spike Detected
Mobile conversions up 23% in the last 24 hours
Unusual Drop-off
Checkout abandonment increased on Safari browsers
Growth Opportunity
Users from LinkedIn convert 2x better than average
Trusted by leading companies









0
Lines of SQL written by the agent
1
Deterministic engine behind every answer
11
Warehouses queried in place
3
Surfaces: app, Slack, and MCP
Analytics agent FAQ
How is an analytics agent different from a BI chatbot or text-to-SQL?
What can an analytics agent do?
Can the agent answer funnel, retention, and cohort questions reliably?
How does Mitzu prevent hallucinated SQL?
Should we build our own analytics agent or buy one?
How do you measure whether an analytics agent is working?
Does an analytics agent replace data analysts?
Which warehouses does the analytics agent run against?
Can teams use the agent in Slack or their own AI assistant?
How do we try it, and how is it priced for multiple teams?
Go deeper on analytics agents
Guides on how analytics agents work, what separates trustworthy answers from plausible ones, and the reference documentation behind this page.
What is an analytics agent?
A definitional guide: how analytics agents work, the main architectures, and what makes one trustworthy.
Read the guideAnalytics agents vs text-to-SQL and BI chatbots
Why generic SQL generation falls short on funnels, retention, and cohort methodology.
Read the guideWhy an analytics agent needs a semantic layer
How a product-analytics semantic layer prevents hallucinated SQL and keeps answers reviewable.
Read the guideVendor-silo analytics agents vs warehouse-native
Why agents inside Amplitude or Mixpanel can't reach billing, CRM, and support data in your warehouse.
Read the guideDocs: how the Analytics Agent works
The architecture reference — analysis specifications, the deterministic query engine, and what the agent can and cannot do.
Read the guideDocs: warehouse-native architecture
What Mitzu queries, what it never copies, who pays for compute, and the read access it needs.
Read the guideTry the analytics agent on your own warehouse
Connect Snowflake, BigQuery, Databricks or another warehouse and ask your first question. The SQL behind every answer is there to check.



