Exemplary AIEnterprise
For creatorsDemoBook a demo
Agentic analytics

Ask in a sentence. Get a dashboard you can defend in the meeting.

Everyone in the business gets an analyst. Ask in plain language and get back a governed answer, a dashboard, and a report that runs every Monday. The query runs inside the warehouse you already govern, under credentials you issue.

Talk to usHow it deploys inside your network
Queries your warehouse in placeIt shows its workingApproved before it shipsRuns on your infrastructure
Analytics/AskDraft
Op
Which regions missed target last quarter, and by how much?
Which regions missed target last quarter,and by how much?
Query planMeasuresum(revenue)Measuresum(target)DimensionregionDimensionquarterFilterquarter is Q3

Runs inSnowflakeunder credentials you issue

Regional performanceComposing dashboard
Revenue vs target-4.8%down 2.1 pts
Regions under target3 of 5was 1 of 5
Revenue against target
target
NorthSouthEastWestCentral
  • At or above target
  • Under target
Gap to target
  • West-1.42M
  • South-0.95M
  • Central-0.30M
Draft. A preview is required before anyone else sees it.Illustrative data
The backlog

Four reasons the answer lands after the decision.

None of these is a modelling problem. They are the reasons a question takes three weeks to become a number, in an organisation that has already bought the tools.

Every question is a ticket

Someone in operations wants a number. It joins a queue behind eleven other numbers, ordered by whoever asked most recently. The analytics team is not slow; it is a shared service with one door.

The data is in nine systems

The ERP, the CRM, the warehouse, and a spreadsheet three people maintain. The join that answers the question crosses four of them, so it gets done by hand, once, and never quite the same way twice.

Two dashboards, two numbers

Both are labelled revenue. Neither says which definition it used. The meeting spends its first ten minutes deciding which chart to believe, and the next ten deciding to check with the analyst.

The decision does not wait

The pricing call is made on Thursday. The analysis arrives the following Wednesday and confirms what the room had already settled on. Nobody reads past the first page.

Question to report

It shows its working, then waits to be approved.

This is the part that decides whether an executive trusts a number a model produced. Every step is visible before the next one runs, and nothing is published until a person says so.

Analytics/Regional performanceIllustrative data
QuestionPlanAnswerReviewScheduled
Op

Which regions missed target last quarter, and by how much?

Asked in a chat, by the person who wanted the answer.

No SQL. No modelling ticket. No request form.

1. Someone asks in plain language.

  1. Someone asks in plain language.

    No SQL, no modelling ticket, no request form. A question typed the way it would be asked out loud, by whoever needs the answer.

    Analytics/Regional performanceIllustrative data
    QuestionPlanAnswerReviewScheduled
    Op

    Which regions missed target last quarter, and by how much?

    Asked in a chat, by the person who wanted the answer.

    No SQL. No modelling ticket. No request form.

  2. The agent writes a query plan, not SQL.

    It emits a structured spec: measures, dimensions, filters. A compiler produces the SQL, every operator is type-checked against its field, and a plan can only reference an existing measure. What that cannot catch is a valid plan answering a slightly different question. So you read the plan before the chart.

    Analytics/Regional performanceIllustrative data
    QuestionPlanAnswerReviewScheduled
    Query plan
    Measuressum(revenue)sum(target)
    Dimensionsregionquarter
    Filtersquarter is Q3status is closed

    Compiled to one query, run in your warehouse. Every operator is type-checked against its field.

    contains is not a valid operator on a numeric field

  3. The answer arrives with its working attached.

    The number, and the definition behind it: which measure, at which grain, with which rows excluded and why. Checking the answer means reading the plan, not reverse-engineering a query.

    Analytics/Regional performanceIllustrative data
    QuestionPlanAnswerReviewScheduled
    RegionRevenueGap
    West2.85M-1.42M
    South4.10M-0.95M
    Central3.60M-0.30M
    How this was computed
    • Measure: sum(revenue) against sum(target)
    • Grain: one row per region, per quarter
    • Excluded: 214 cancelled orders
  4. The dashboard is a draft until someone approves it.

    Plans move from draft to reviewing to finalized, and the preview gate is required before finalization. Each version stays tied to the conversation that asked for it, so the question and the artefact never come apart.

    Analytics/Regional performanceIllustrative data
    QuestionPlanAnswerReviewScheduled
    DraftReviewingFinalized
    KPI rowRevenue against targetGap to targetDetail

    Version 3, tied to this conversation

    Preview required before finalization

    ApproveRequest changes
  5. Then it runs on a schedule, where the team already works.

    The approved dashboard becomes a recurring report, delivered into the tools people are already in. A watcher raises the figures that moved instead of waiting to be read.

    Analytics/Regional performanceIllustrative data
    QuestionPlanAnswerReviewScheduled
    Every Monday, 07:00
    Delivered asTeam channelPDFDOCX

    Watcher Raise any region more than 5% under target

    Recent runs
    • Mon 07:00Delivered1 raised
    • Mon 07:00Deliverednothing raised

Five frames from the same walkthrough. Values are illustrative; the states are the product.

Your data

Nothing is copied to answer a question.

Query the warehouse where your data already lives, and keep governed tables of your own for the data that has no home. A plan compiles the same way against both, and the same engine permissions both.

One query plansum(revenue)regionquarter is Q3
compiles to
The warehouse you already governin place
SnowflakeBigQueryDatabricksPostgres

The query runs there, under credentials you issue. Nothing is copied out to answer it.

Governed tables of your ownyour tenant
Imported tablesRows an agent writes

For the data with no home, and for the numbers an agent is allowed to change.

One plan, two destinations, one permission model. Import is an on-ramp, not the way in.

Revenue operations/ContractsIllustrative data
GridGalleryKanbanCalendarForm
ContractTextRegionSelectRenewsDateValueRollupMarginFormulaOwnerEmailPII
CTR-4821North12 Mar1.24M38%••••••Hidden from this agent by field policy
CTR-4830South02 Apr0.86M31%••••••Hidden from this agent by field policy
CTR-4844West19 Apr2.10M44%••••••Hidden from this agent by field policy
CTR-4851North30 Apr0.42M27%••••••Hidden from this agent by field policy

Rollup summed from the line items table

Formula parsed, not executed

Hidden from this agent by field policy

Row historyValue 1.18M → 1.24MRenewals agentfrom the conversation that asked
01

It reads your warehouse in place

Connect Snowflake, BigQuery, Databricks or Postgres and the plan compiles to a query that runs there, under credentials you issue. Nothing is copied to answer it, so retention, entitlements and the regulator still have one copy of the data to describe.

  • Credentials you issue, scoped to the tables you name
  • Where the source already filters rows, that filter still applies
02

A Postgres table, not a spreadsheet

For the data that never reached the warehouse: the tracker a team runs its week on, the reconciliation somebody keeps in a sheet. Twenty-six field types, rollups over related tables, formulas parsed rather than executed, five views over the same rows. An agent can write here; every write is attributable.

  • Rollups sum a related table, so a total is derived rather than typed
  • Every row change is recorded field by field, with the actor and the conversation behind it
03

Import is for the spreadsheet on a laptop

On import, every numeric field gets sum, average, minimum and maximum, and every date becomes a five-level hierarchy, year down to day. Drilldown works on the first afternoon, not after a modelling project. It is the on-ramp for data nobody ever modelled, not for the fact table you already govern.

  • Measures are generated, then yours to rename, hide or redefine
  • The date hierarchy is what makes a chart drillable without setup
04

One definition of revenue, and the plan has to use it

A measure is defined once, by the person who owns it, and every plan that touches revenue resolves to that definition. The agent cannot invent a measure. Definitions carry an owner and a version, so when a number moves you can see whose change moved it.

  • Written instructions teach it your vocabulary; they do not define your metrics
  • Sensitivity classes on every field, and a redacted field never reaches model context
See where the data comes from
Dashboards

One question, five angles, one review.

The orchestrator explores overview, trend, comparison, distribution and detail in one turn, and hands you one set to accept or reject. You keep what earns a place; the rest is discarded, not saved. Nothing gets published by being generated.

Build me a view of regional performance for the Thursday review.

Dashboard orchestratorOne turn. Five angles, explored at the same time.
  1. Overviewdraft
    KPI row, revenue against target
  2. Trendsdraft
    Trendline by month, moving average
  3. Comparisonsdraft
    Region against region, waterfall
  4. Distributiondraft
    Boxplot, treemap by segment
  5. Detaildraft
    Grid view, drillable to the row
One reviewKept, and publishedDiscarded, not saved

Five angles, one review, one dashboard kept. Nothing survives by default.

Ask a follow-up of a chart

Point at a widget and ask why. The follow-up runs against the same query plan that drew it, so the answer and the picture cannot quietly drift apart.

The chart is the question, not a screenshot of one.

Drilldown you did not have to build

Year to quarter to month to week to day, derived from your dates when the table was imported. Click a column and the level below it is already there.

No hierarchy modelling, no cube.

It picks the chart, and you can overrule it

A trend gets a line, a breakdown a bar, a flow a sankey. The chart follows what the plan returned, not a picker you have to learn.

Composed for the question that was asked.

Reports and watchers

On Monday at seven, the report writes itself.

A finalized dashboard becomes a recurring run. It goes where the team already works, and a watcher raises the things that moved rather than waiting to be opened.

  1. Monday 07:00

    The run fires on its own

    The same query plan the dashboard was approved on, pointed at this morning. Nobody has to remember it is Monday.

  2. Recomputed

    The numbers are re-queried, not copied

    A scheduled run re-executes the plan against live tables. A stale screenshot with a fresh date on it is how a report loses a room.

  3. Composed

    It comes out as a document

    Report, proposal, memo, one-pager or letter, on your letterhead, exported to PDF and DOCX. Charts where a chart helps and prose where it does not, because a board pack is not a dashboard.

  4. Delivered

    Into the tools people are already in

    It lands in the place the team already spends its day, instead of waiting for someone to remember another tool. Access still follows the permissions the dashboard had.

  5. Watched

    And the exceptions raise themselves

    Set a threshold on a measure. When a run crosses it, the run says so. The report you actually open is the one where something happened.

Governed

The same permission model for your people and your agents.

An agent is not a service account holding a wide key. It is evaluated by the engine that evaluates your people, with groups and roles from your directory. On top of your entitlements, not in place of them.

Field-level, in each direction

Read and write are separate allow-lists. An agent permitted to read a column is not thereby permitted to change it, and neither list is inferred from a role name.

Row filters, and an intersection mode

Scope a caller to the rows it is entitled to. Where several policies apply at once, intersection mode grants only what all of them agree on, which is the setting a regulator asks about.

One evaluator, whoever is asking

A person and an agent hit the same decision. There is no second, looser path for machine callers to audit separately, because there is no second path.

Explain this permission

Ask why a caller can or cannot reach a field and get a structured answer back. Access reviews stop being a conversation about what somebody believes the policy does.

SOC 2 Type II and ISO 27001 certified, with the report and the statement of applicability available under NDA. HIPAA and GDPR obligations are met by the deployment itself: the data never leaves your perimeter, so none of it is ours to process.

SOC 2 Type IIAICPA
HIPAACompliant
GDPRReady
ISO 27001Certified
See how access and policy are governed
The platform, measured

It measures itself, too.

The same instinct pointed inward. Tokens by model and by agent, queue depth and wait, storage by location, attributed to the thing that spent it.

100%of spend attributable to an agent
9dimensions to slice by
24×7queue health monitoring
0telemetry leaving your network

From who asked to what it cost

Every token, traced through the model that served it.

AgentsModelsTotalSupport deskRecords lookupPolicy researchFinance reviewOnboardingFast generalLong contextEmbeddingVision / OCR
1.24Mtokens this period
  • Fast general
  • Long context
  • Embedding
  • Vision / OCR
Illustrative data

Tokens by agent

The attribution that matters most: spend against the thing that spent it.

Average queue wait

Plotted on its own scale. Seconds and slot counts share an x-axis but never a y-axis.

Usage telemetry is operational data about the platform: tokens, queues and storage, attributed to the agent that spent them. It is aggregated inside your network beside the agents that produced it, and none of it is a record of what any individual asked.

Swap the deployment behind a model
At a glance

What it is made of.

The SOC 2 report, the ISO 27001 statement of applicability and the deployment architecture are available under NDA, along with a reference call on request.

Ask
Plain language, in chat or on a dashboard
Query
A structured semantic spec, compiled to SQL
Sources
Snowflake, BigQuery, Databricks and Postgres, queried in place
Guardrail
Filter operators type-checked against their field
Semantics
Measures and a five-level date hierarchy, on import
Metrics
Owned, versioned, and the only thing a plan may reference
Fields
26 types, plus formulas, rollups and lookups
Views
Grid, gallery, kanban, calendar and form
Charts
25 types, including sankey, treemap, funnel and heatmap
Widgets
20 templates, and KPI cards with delta and trend
Review
Draft, reviewing, finalized, behind a required preview
Identity
SAML and OIDC, with groups synced from your directory
Permissions
Field allow-lists, row filters, intersection mode
History
Append-only, field-level, tied to the conversation
Documents
Report, memo, one-pager and letter, to PDF and DOCX
Scheduling
Recurring runs, with watchers on a measure
Deployment
On-premise, private cloud or air-gapped
Common questions

What data leaders ask first.

See Exemplary AI in action

Book a demo and we'll show you purpose-built agents grounded in your own knowledge — deployed on your infrastructure.

Book a demo
Exemplary AIEnterprise

Agentic AI for the enterprise — installed inside your network.

  • Sovereign deployment
  • Purpose-agnostic agents
Book a demo

Build

  • Agents
  • Model Hub
  • Knowledge Graph
  • File store

Connect

  • Integrations
  • Chatbots
  • Browser Extension

Govern

  • Management
  • Groups
  • Analytics

Company

  • About Us
  • Exemplary for creators
  • Book a demo

Use cases

By industry
  • Healthcare
  • Government
  • Financial services
  • Legal
  • Media
By department
  • Customer Support
  • IT & Engineering
  • Human Resources
  • Finance & Procurement
  • Compliance & Risk

© 2026 Exemplary AI. All rights reserved.

  • SOC 2 Type II
  • HIPAA
  • GDPR-ready
  • ISO 27001