Self-service AI analytics with
programmable semantic layer

Holistics helps data teams stand up self-service BI where the AI answers and the point-and-click answers actually match, because both read from metrics you define once.

Book a demo

Start free trial

See our customers

Self-service AI analytics

Analysts prepare curated datasets. Business users self-serve via AI or point-n-click interface.

Governed semantic model

Define metrics and logic in a centralized layer. Dashboards, AI answers, and explorations pull from the same source of truth.

Analytics as-code

Define everything as code, from models, metrics to dashboards. Check in with Git version control. Plug directly to your AI agents as context.

AI analytics

Ask hard questions, get reliable answers

Anyone can ask in plain language, from a quick metric to a multi-step cohort breakdown. Answers come from your governed definitions, so the numbers match your dashboards.

Hi — what would you like to explore?

Ask about revenue, customers, or why a number moved…

How has revenue trended this year?

Thinking…

Revenue is up 105% since January, from $38.2k to $78.4k. August was the outlier though — it dipped 11% versus July.

Monthly revenue, 2026 YTD Up 105% Jan to Dec, with a break in August

Revenue

Analyze decrease

I’ll break down July and August revenue by a few dimensions to see what drove the drop.

Revenue fell across every product category, each by roughly 11% — so no single product line is responsible.

Revenue by category, Aug vs Jul

JulyAugust

By region it is concentrated: APAC accounts for 82% of the drop — $5.4k of the $6.6k total.

Revenue by region, Aug vs Jul

JulyAugust

So this isn’t a category problem — it’s an APAC problem. That could mean fewer APAC customers, or the same customers spending less. Worth checking APAC customer activity next.

Is APAC losing customers, or just not gaining them?

Thinking…

One definition to pin down first:

90 days without an order

Thinking…

This is an acquisition problem, not churn. August gains fell to 1,240 36% against a 1,938 monthly average, while losses held at 310 avg 306 — the same as every other month.

APAC customer flow Gained vs lost · lost = 90 days without an order Open in Explorer

GainedLost

Ask a follow-up…

Revenue: $51.2k Month: Aug 2026

Exclude this data point

Filter

Analyze decrease

How long without an order counts as lost? Avg. APAC repeat-order gap is 47 days, so this sets the whole answer.

60 daysComfortable grace beyond the average gap

90 daysWide grace, safer against seasonal or slow-cycle buyers

Something elseSet your own window

Skip Confirm

Sales overview ···

Revenue, YTD$649.7kJan–Dec 2026

Avg. revenue growth, MoM+7.1%Across 11 months

Revenue, August$51.2k11% vs July

Monthly revenue, 2026 YTD Up 105% Jan to Dec, with a break in August

Revenue

Revenue by region, Aug vs Jul

JulyAugust

Add AI block

Tell AI what to write…

Gathering dashboard data…

Revenue is up 105% — but August broke the streak

Since January revenue has grown 105%, averaging 7.1% a month. August broke the run, falling 11% versus July.

📊 Key insight

January $38.2k → July $57.8k, then $51.2k in August 11%, recovered by September.
August: APAC drove 82% of the drop — 24.8k → 19.4k 22%; no other region gave up more than $0.6k.
APAC: not churn — losses flat at 310 avg 306. Gains fell to 1,240 36% against a 1,938 average.

🔔 Next steps

Why APAC stopped acquiring in August — two things to check:

Marketing — ad spend paused, or a campaign that lapsed in early August.
Market — regional seasonality, or a competitor pulling demand away.

Summarize this dashboardExplain the August dropHighlight key trends

Generate preview Cancel Save

Find out why, not just what happened

Revenue dipped in August. Ask why, and AI finds the region behind it, checks what you meant, and writes the finding up on a dashboard — one continuous conversation, no SQL.

AI summarizes any dashboard

AI reads the dashboard and adds a plain-English summary on top, flagging what changed and where to look next.

Ask user: Which metric do you want for “how did we do” across over the last few weeks

Please answer the question below

Thinking

Revenue/MRR by product Weekly revenue trend across products
New subscriptions by products Weekly new subs across products
Net subscriptions by products New minus churn by week
Active/paying subscriptions by product Current paying subs trend by week
Something else:

Ask anything about your data…

AI asks before it guesses

When a request is unclear, Holistics AI asks what you meant, offering the likely options to pick from or letting you type your own.

Guido Stark Head of Data, World Vision New Zealand

I'm seriously impressed with Holistics AI capabilities! It doesn't just fetch documentation, it understands the content and generates working solutions.

See Holistics AI in action

Watch it answer live, then trace every number back to the metric it came from.

Explore AI analytics

Self-service BI

Self-service exploration that breaks nothing

Explore without waiting on the data team

Business users slice, drill, and combine metrics on datasets your team curates, without SQL, tickets, or numbers that disagree with the dashboard next door.

Drill down and through

Break down by any dimension, then jump to the detail dashboard.

View underlying data

Click into any number to see the exact rows behind it.

Take action from any row

Open a CRM record, send a pre-filled email, or jump to another dashboard, right from your table.

Insan Ramadhan Data Team Manager, Qoala

The business user doesn't need to query anymore... they can just drag and drop metrics. This makes data more accessible across the business.

Put self-service in your users' hands

See what business users can answer on their own, and how curated datasets keep them on track.

Explore self-service BI

Semantic layer

One semantic layer under every answer

Define it once, and AI can trust it

Your metrics and logic live in one place your team controls, so Holistics AI answers from those definitions instead of guessing at raw tables.

The semantic layer is Holistics' biggest draw because I was able to build reusable models, dimensions, metrics, and then describe them as code.

Sterling Paramore Sr Staff Data Engineer, Mainspring Energy

ecommerce.aml

Model orders {
  table_name: 'ecommerce.orders'

  dimension status     { type: 'text' }
  dimension created_at { type: 'datetime' }

  measure revenue {
    type: 'number'
    definition: @aql sum(order_items.quantity * products.price) ;;
  }
}

// assemble models into a governed dataset
Dataset ecommerce {
  models: [orders, order_items, products, users]
  relationship(order_items.order_id > orders.id)
  relationship(order_items.product_id > products.id)
}

one definition · compiles to native SQL · governs every surface

A query language built for your semantic layer

Query it in AQL, where every metric is an object that composes like a function, so you build new metrics on top of existing ones instead of copy-pasting SQL.

I'd score AQL a 9 or 10, up there with the best tools I've used. We can define metrics based on other metrics, stacking them on top of each other, and still retain visibility into the raw data.

Ian McLaren Business Intelligence Engineer, DNSFilter

“What’s LTV by plan?”

metric revenue =
  sum(order_items.quantity * products.price)

metric arpu =
  safe_divide(revenue, count(users.id))   // builds on revenue

metric ltv =
  arpu * avg(users.lifespan_months)       // builds on arpu

each metric builds on the last · compiles to native SQL

Access your semantic layer from any AI

Query your metrics from Claude, ChatGPT, Cursor, or your own app over MCP and APIs. Every tool reads the same definitions, so the answers agree.

See connector

Go deeper on the semantic layer

See how defining a metric once keeps every dashboard, query, and AI answer in sync.

Explore the semantic layer

Analytics as-code

Manage BI the way you ship software

Define models, metrics, and dashboards as code in Git. Branch a change, open a pull request, and roll it back the moment something looks wrong.

Everything as code

Define everything in AML, from models to dashboards, so your analytics is text you can read, review, and reuse.

Version control

Full history on every change, with one-operation rollback when something breaks.

Branch, review, deploy

Real pull-request review on your business logic before it hits production.

Build your BI with coding agents

Point Claude Code, Codex, or Cursor at your BI codebase.

Or use our in-browser Development Copilot to build models, metrics, and dashboards.

secure.holistics.io/reports/revenue-dashboard

Live preview

Your dashboard will build here

claude · ~/analytics

⠋ Build Revenue dashboard (0m 00s · ↓ 0.0k tokens)

› esc to interrupt · ctrl+t to hide tasks

Bring your software workflow to BI

See a change go from a branch to a pull request to production, all in version control.

Explore analytics as-code

Embedded analytics

Embed analytics your customers trust

Ship white-labeled dashboards and self-service inside your own product, with per-tenant security enforced by the same layer that powers the rest of your analytics.

Embed analytics that feels native

White-label dashboards and portals that match your product's look and feel, from a single dashboard to a full self-serve mini-BI.

Because of the quality of your platform, it really feels native for our end users, and so they're very happy about it.

Rob Winters Head of Data, Lepaya

Ask AI, embedded

Let your customers ask questions in plain language inside your product, answered from the same metrics that power their dashboards.

Embed analytics in your product

See how product teams ship white-labeled dashboards and AI inside their own apps.

Explore embedded analytics

Everything else you'd expect, in the box

Deliver

Email & Slack schedules
Data alerts (webhook)
Export CSV / Excel / PDF
Shareable links

Govern & secure

Row & column permissions
SSO / SAML & SCIM
Audit logs
SOC 2 & GDPR

Connect

Snowflake · BigQuery
Databricks · Redshift
dbt Core & Cloud
and more

End-to-end semantics. That's the difference.

Every modern BI tool claims a semantic layer. But ask for a running total by segment, a rolling window by region, or a custom retention cohort, and most can’t express it. The moment you do, you’ve left the semantic layer behind back to table calculations, raw SQL, or “ask an analyst.”

And once you’re outside the semantic layer, governance breaks down and self-serve stops scaling.

Not all semantic layers are equal

Capability

Conventional BI

Holistics

Outcome

Composable metrics

Running totals, rolling windows, nested aggregations, period-over-period comparisons

Falls back to table calculations or raw SQL for complex logic

First-class composable metric definitions inside the semantic layer

✅ Self-service ✅ Governance

Business-centric self-service

Cohorts, funnels, retention curves, segmented breakdowns: analysis business users actually need

Advanced analysis requires analyst to build custom reports, or users bypass governance with raw SQL

1-click advanced analysis without leaving the semantic layer. Users stay within governed definitions.

✅ Self-service ✅ Governance

AI that reasons over semantics

Ask a follow-up question and get an answer that builds on the last one, not a fresh SQL query from scratch

Generates raw SQL. Context lost between questions; AI ignores governed definitions.

Reasons over semantic layer in AQL. Multi-turn context preserved; AI respects metric governance.

✅ Self-service ✅ Governance

Git version control

Who changed what, when, why, for every metric, model, and dashboard definition

UI-configured, no audit trail, definitions drift

Code-defined, Git-backed, code-reviewed. Full change history.

✅ Governance

Programmable semantic layer

Models, metrics, and dashboards defined as code: readable by humans, AI, and automation

Duplicated logic across dashboards, reports, exports

Define once, reuse everywhere: AI, dashboards, embedded analytics

✅ Governance

Sterling Paramore Sr Staff Data Engineer, Mainspring Energy

The semantic layer is Holistics' biggest draw because I was able to build reusable models, dimensions, metrics, and then describe them as code.

Data teams that made the switch

NASDAQ-listed. Autonomous vehicle tech. 1,000 end users.

We evaluated 41 BI tools, including mature companies, startups, open source solutions. During that process, I stumbled upon Holistics, tried it, and liked it a lot.

Read case study

Replaced Tableau and Looker. Data team of 3.

Working with Holistics is completely different from companies like Tableau or Looker. Your team moves fast, and I can see ideas turn into features in real time.

Read case study

Migrated from Looker Studio. Marketing AI platform.

Holistics has democratized the ability to get the right data at any given point and then visualize it in a very simple way.

Read case study

Holistics, built to help your business grow

Hands-on support

White-glove support from people who actually build the product.

From your first dashboard to scaling, the Holistics team is here to make you successful.

Learn more

The support has been great. We get updates, fixes, or even just helpful advice when it's not a technical issue. That level of responsiveness was a huge factor in our decision.

Even before we were paying customers, we felt important. That engagement, that sense that we matter, is one of the biggest reasons we chose Holistics.

Rob Winters Head of Data, Lepaya

Trusted by teams worldwide

Hear from data-driven teams who've transformed their workflows with Holistics.

We evaluated BI tools across the market. I went through an evaluation process, reviewing around 41 options, including mature companies, startups, open source solutions. During that process, I stumbled upon Holistics, tried it, and liked it.

Staff Data Scientist

Aurora (NASDAQ-listed)

Read full

Excellent BI tool for customers looking for a Looker alternative. Coming from a Looker background, I was very familiar with its concepts of analytics-as-code, and we have achieved everything we needed for reporting.

Alex H

Head of Data, Pinter

The metrics dataset component is really critical for companies that don't have a real data team to build everything all the time. In the work I do, I recommend Holistics to people all the time.

Pedram Navid

Consultant/Founder, West Marine Data

The ability for everyone to explore: Massive win. The one feedback we've had over and over again from the whole company is “Man, how did you guys go through your process? Because you choose such a great tool.”

Guido Stark

Head of Data, Optimal Workshop

Holistics is the next big BI Tool. It took me 2 hours to build the same report in Holistics that I took 16 hours to build in Tableau.

Stephen Motherwell

Chief of Product, Ordo

Holistics became an excellent choice to get us going in BI without the typical huge annual expense. We have built visualizations in Holistics that took it way beyond the 'out-of-the-box' tools.

Seth L

Chief of Product, Oxbridge Health

As an analytics engineer, I was looking for a tool that allowed me a lot of data modeling flexibility and reusability. With Analytics as code, Holistics does a great job of being able to define data models and relationships using code.

Sterling P

Chief of Product, Mainspring Energy

They are great. They are continuously improving the platform and releasing new features, so we know that what we don't have right now will be at some point :)

Marta Garrido

Head of Data, MyRealFood

See all case studies

Want to understand the complex landscape of data analytics?

Want a quick primer on the practice of modern data analytics? We wrote The Analytics Setup Guidebook to help you with that.

Get a soup-to-nuts overview of the broader data landscape in less than 200 pages. (Plus we drew all the pictures ourselves!)

Learn more

I'm shocked to be telling you this next sentence: I read a free ebook from a company and actually loved it.

Mark MacArdle

Data Engineer

Want to understand the complex landscape of data analytics?

In the press

Holistics has received positive reviews for its innovative data analytics approach, enabling businesses to make informed, data-driven decisions easily.