Insight
Data Foundations Setup
A small cloud data warehouse in BigQuery or Postgres with up to 4 business tools synced daily, 10 cleaned reporting tables and…
Insight
AI BI Assistant
Ask your existing BI dashboard a question in plain language and get the number explained, not just displayed.
You already pay for a BI dashboard, but people still message the one person who understands it. This assistant sits alongside the dashboard you use, such as Looker Studio, and answers plain-language questions about what it shows. It traces each number back to the query behind it, so managers understand the figure, not just see it. Connections are read-only.
- Managers get dashboard numbers explained in plain language
- Every number traced back to the query behind it
- Works alongside the BI dashboard you already pay for
$6,900
20–30 working days
Optional maintenance $345/mo
What it is
AI BI Assistant sits alongside the BI dashboard you already use, such as Looker Studio, and answers plain-language questions about what it shows, tracing a number back to the query behind it. Connections are read-only by default, and scheduled summaries can go to email or Slack.
Why businesses buy it
Dashboards are only useful when people understand them. Too often a number looks wrong, nobody knows how it is calculated, and the question lands on an analyst who is already busy. That slows decisions and erodes trust in the data. This assistant explains the dashboard on request and shows the query behind every figure, so people act with confidence. The written scope sets the sources, metrics and testing against your history before you order.
Problems this solves
People see a dashboard number but cannot tell where it comes from
The assistant sits alongside the BI dashboard you already use, such as Looker Studio. It answers plain-language questions about what the dashboard shows and traces a number back to its query.
Managers ask analysts to explain dashboards they already have
Up to twenty-five metrics or recurring questions are defined with you. Managers ask the assistant first, and analysts step in only when a question goes beyond them.
Dashboards go unread because nobody opens them each week
Scheduled summaries can go to email or Slack, bringing the key numbers to people. Up to five alerts can flag a metric when it moves outside a level you set.
A good fit if
You already have a dashboard in a tool such as Looker Studio, but people keep asking someone to explain what it means.
Managers ask 'why did this number change' more often than they open the dashboard itself.
You already keep data in tools such as Google Sheets, BigQuery, PostgreSQL or Google Analytics 4, and can grant read-only access.
You want every explanation to reference the actual query or source behind the dashboard, not a guess.
Not the right fit if
You do not have a BI dashboard yet and want fresh answers built from your raw data. See AI Data Analyst Agent, which answers questions directly from your sources.
You want a brand new dashboard built, not help understanding an existing one. See AI Business Intelligence Dashboard, which builds a full dashboard from scratch.
Your analysts want to write their own queries faster. See AI SQL Assistant, which turns a question into SQL against your schema.
You need alerts on specific thresholds rather than explanations. See AI KPI Monitor, which watches defined KPIs and alerts on breaches.
How it works
- You tell us which dashboard and which tables or sheets sit behind it, and we connect to those same read-only sources.
- A manager asks a question about the dashboard in plain language, such as 'why did the churn tile jump this month?'
- The assistant traces the number back through the query or source, and explains the change in a short written answer.
- Answers are checked against 3 months of your historical data before launch, so the explanations match what the dashboard actually shows.
- If a question needs a metric the dashboard does not track, the assistant says so instead of inventing a number.
- Recurring explanations, such as a weekly summary of the dashboard's biggest movers, can be scheduled to your inbox or Slack.
What you provide within 72 hours
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
- Access to the dashboard tool you already use, such as Looker Studio, and read-only access to the data behind it.
- Your own definitions of the key metrics shown on the dashboard.
- At least 3 months of historical data, so explanations can be checked before launch.
- The list of people who should receive scheduled explanations, and the channel to use.
- Admin access and API keys for every connected system, shared by adding our team as a user or creating a key you control, never by email.
- Your business information (company basics, hours and brand voice), shared during intake.
- One decision-maker who can confirm the metric definitions are correct.
- An API key for your own AI model account (for example OpenAI or Google Gemini), created for this build with a spending limit.
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Intake confirmed and the dashboard's key metrics agreed.
Weeks 1–2
Read-only connections built to the sources behind your dashboard.
Week 3
Recurring explanations and alert thresholds configured.
Weeks 3–4
Answers tested against 3 months of your historical data.
Week 4
Your review and two rounds of changes.
Go-live
Live, handover report sent, 30 days of support starts.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $6,900 |
| Express | 15–25 working days | $8,100 |
| Rush | 10–20 working days | $9,300 |
What you receive at handover
- The AI BI assistant, working alongside your existing BI dashboard
- Read-only connections to up to three data sources
- Definitions for up to twenty-five metrics, one scheduled summary or report and up to five alerts
- A test report checking results against three months of your historical data
- An admin guide and the written handover report
- 30 days of post-launch support
Expected benefits and how to measure them
- Can make your existing dashboards easier to understand
- Helps managers trust numbers they can trace
- Brings key metrics to people who rarely open the dashboard
- Dashboard questions to analysts
- Count 'what does this mean' requests to analysts per month, before and after launch.
- Summary engagement
- Check opens or replies to scheduled summaries in email or Slack each week.
- Dashboard visits
- Use your BI tool's usage report. Compare visits for the month before launch with the month after.
Before you start: Pull current dashboard usage from your BI tool. Count explanation requests reaching analysts for a few weeks.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
The build itself is a one-time payment, shown before you buy. Running the assistant costs roughly $20 to $150 a month in your own accounts, covering AI model usage and hosting or scheduler fees, on top of whatever you already pay for your BI dashboard tool.
AI usage during the build and testing is billed to your own accounts too, so the provider relationship stays in your name.
Ask about running costsCustom requirements
If your dashboard pulls from more than 3 sources, or you want it explained in a second language, add a note at checkout for a written Change Quote. Your order still runs on its original delivery date. Larger or bespoke projects go through the Custom AI request form instead.
Request a custom versionKeep it running
We recommend monthly maintenance for this build. It covers monitoring, fixes and monthly change hours for new metrics, extra recurring questions or changes after a dashboard redesign. The allowance scales with the build, and bigger changes go through a Change Quote. It starts after the included support period and can be cancelled any month.
$345/mo (5% of the build price a month, includes 3 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | A BI tool add-on charges per seat for its own AI feature | An agency quotes per training session or workshop | Ours is one fixed price, shown before you buy |
| Delivery | A BI vendor's AI feature can take months to reach your plan tier | An agency workshop is usually booked weeks out | Ours has a fixed delivery time shown before you buy, with faster options |
| Explanations | A BI tool's built-in AI often works only inside that one product | An agency explains the dashboard once, in a meeting | Ours answers on demand, with the source traced every time |
| Scope | A BI vendor's AI feature scope changes with every plan update | An agency agrees scope during discovery | Ours is written on the Scope Card before purchase |
Questions about this product
What does the AI BI Assistant price include?
One fixed price, agreed before work starts, covers up to three read-only data sources behind your dashboard, up to 25 defined metrics, one delivery channel and checks against three months of your history. Faster delivery options are shown in the price panel before you order, and there are no other build fees.
Does the AI BI Assistant work with my existing dashboard tool?
Usually, yes. It connects to the same read-only sources that feed dashboards built in Looker Studio and similar tools, plus Google Sheets, BigQuery, PostgreSQL, MySQL or Snowflake. Tell us your dashboard tool during intake, and we confirm the connection during the first ten working days of the build.
How long does the AI BI Assistant take to launch?
The standard, Express and Rush delivery times are all shown in the price panel before you order, and the clock starts once your intake is complete. Delays only happen when access or metric definitions arrive late, which moves delivery by three working days per day of delay.
What happens when the AI BI Assistant cannot explain a number?
It says so rather than guessing. If a question needs a metric your dashboard does not track, or falls outside the connected sources, the assistant tells the person who asked instead of inventing an explanation. New metrics can be added through monthly maintenance or a Change Quote.
How much does the AI BI Assistant cost to run each month?
Roughly $20 to $150 a month in your own accounts, covering AI model usage and hosting or scheduler fees, in addition to whatever you already pay for your dashboard tool. The exact figure depends on how many questions are asked and how many sources stay connected.
Can the AI BI Assistant cover a second dashboard later?
Yes, as an add-on. A second dashboard or a fourth data source is quoted through a written Change Quote based on your request. Small changes to the existing metric set fit inside the monthly change hours that come with maintenance instead.
Who owns the explanations the AI BI Assistant gives?
You do. The connections, prompts and metric definitions run in your own accounts, alongside your existing dashboard tool. If maintenance lapses, the assistant keeps answering; you lose the monthly monitoring and included change hours, not the build itself. While it runs, those hours cover new metrics, extra recurring questions or changes after a dashboard redesign.
Stop being the person who explains the dashboard.
Order the AI BI Assistant and it starts explaining your existing dashboard in plain language. The scope above is what you get, in writing, before you pay.
Works well with
Insight
Business KPI Dashboard Build
One business dashboard in Looker Studio or Power BI with up to 3 pages, 20 KPIs and 3 data sources, refreshed on…
Insight
AI Data Analyst Agent for Hotels & Hospitality
Answers plain-language questions against your data and produces charts and summaries, adapted for Hotels & Hospitality businesses that need quick answers on…