Front Line
AI Customer Support Agent
Resolves customer questions across chat and email using your knowledge base and hands off complex cases.
Extensions
Analytics Dashboard Add-on
One dashboard shows how your AI product is performing, so you stop guessing from scattered logs.
Your AI product records a lot, but scattered logs do not tell you whether it is working. This add-on turns what it already records, such as volumes, outcomes and handoffs, into one dashboard your team can filter. Every measure is defined in writing and checked against raw records, so the numbers can be trusted in meetings and decisions.
- Shows your AI product's performance in one filtered view
- Defines every measure in writing so nobody argues counts
- Checks dashboard figures against the raw records
$2,500
10–20 working days
What it is
The Analytics Dashboard Add-on adds a performance dashboard to an AI product you already run, or are buying now. It turns what the product already records, such as volumes, outcomes and handoffs, into charts and tables your team can filter. Each figure is checked against raw records.
Why businesses buy it
Without clear numbers, it is hard to tell whether your AI product is paying for itself, where it struggles and what to improve next. Teams end up exporting logs and building spreadsheets that disagree with each other. A dashboard built from the product's own records, with agreed definitions, gives everyone the same view. The written scope fixes the measures, filters and checks before the build, so you get a dashboard you can rely on rather than an open-ended analytics project.
Problems this solves
You cannot easily see what the AI product is doing day to day
This add-on turns what the product already records, such as volumes, outcomes and handoffs, into charts and tables. Your team can open one dashboard instead of digging through logs.
Reports are built by hand from raw exports and take hours
The dashboard updates from the product's own records, and your team can filter it themselves. The manual export-and-chart routine is no longer needed for these figures.
People doubt the numbers because nobody checked how they were made
Each figure on the dashboard is checked against the raw records before handover. The test report shows those checks, and the documentation explains how each figure is calculated.
A good fit if
Your product is live, and nobody can say quickly how many conversations, calls or tasks it handled last month.
You want to see outcomes, such as resolved, booked or handed off, without exporting logs.
Managers want to filter by date, channel or type without asking someone technical.
You can agree a short list of measures that matter to you.
Not the right fit if
You want a written summary sent to leadership on a schedule. Executive Reporting Pack does that for less.
You need one specific report in a set format. Custom Report Template adds one report.
You want to trace each step and tool call to debug an agent. AI Agent Observability is built for that.
You want support-wide analytics across contact drivers and resolution times. AI Support Analytics covers the whole support operation.
How it works
- Measures are agreed. We list what the product already records and choose the measures you care about.
- Data is prepared. The product's records are shaped so each measure is counted the same way every time.
- The dashboard is built, with charts, tables and filters such as date range, channel and outcome.
- Numbers are checked. We compare the dashboard against the product's raw records for a test period.
- Access is set. The people you name can view it, and you review it with one revision round.
- Handoff. Documentation explains each measure, plus a test report, handoff note and a short written walkthrough.
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.
- The order reference of the product the dashboard covers
- The questions you want the dashboard to answer
- Who should be able to view it
- Access to any system holding the product's records, shared securely in the way we agree at intake
- One person who signs off the measures
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Questions, viewers and data sources listed
Week 1
Measures and definitions agreed
Week 2
Data prepared and dashboard built
Week 2
Figures checked against raw records
Week 2
Your review and one revision round
Go-live
Dashboard live, measure definitions documented
| Option | Delivery time | Price |
|---|---|---|
| Standard | 10–20 working days | $2,500 |
What you receive at handover
- A performance dashboard for your existing product, with filters
- Charts and tables built from the product's own records
- Updated documentation explaining each figure and how it is calculated
- A test report showing figures checked against raw records
- A handoff note and a short written walkthrough
Expected benefits and how to measure them
- Makes it easier to spot changes in volume or outcomes early
- Can save time spent building reports by hand
- Helps the team agree on one set of numbers
- Reporting time
- Ask whoever builds reports to note their monthly hours before launch and again two months after.
- Dashboard use
- Check how many team members open the dashboard each week, if your tool shows views.
- Issues spotted from the dashboard
- Keep a simple log of problems the team noticed on the dashboard and acted on each month.
Before you start: Note how you currently report on the product, who does it, and how long it takes. Keep a copy of your latest manual report for comparison.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
Any hosting or reporting tool the dashboard runs on is billed to your own accounts, as agreed at intake. We charge once for the build and nothing per viewer or per refresh.
Ask about running costsCustom requirements
Combining data from systems the product does not touch, forecasting, or more than one dashboard are beyond this add-on. Note them at checkout for a written Change Quote. Larger or bespoke projects go through the Custom AI request form instead.
Request a custom versionKeep it running
The dashboard is covered by the parent product's maintenance, which grows in line with the add-on's price. A new chart or a changed definition uses its monthly change hours.
Adds $125/mo to maintenance
Covered by the main product's maintenance, which grows by this amount.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | A BI tool bills monthly per viewer | An agency quotes dashboard work by the hour | Ours is one fixed price, shown before you buy |
| Definitions | You decide how to count things | Agreed during the project | Ours writes each measure's definition down |
| Accuracy | Trusted as shown | Depends on the brief | Ours is checked against raw records |
| Delivery | Self-build | Set per project | Ours has a fixed delivery time shown before you buy, with faster options |
Questions about this product
What will the analytics dashboard show?
The measures agreed at intake, drawn from what your product already records. Depending on the product, that might be volumes by day, outcomes such as resolved or booked, handoff rates, or response times. If a measure needs data the product does not keep, we say so before building.
How do I know the dashboard numbers are right?
Before launch we compare the dashboard against the product's raw records for a test period and share the results in the test report. Each measure also has a written definition, so everyone reading it counts the same thing the same way.
Why does the dashboard cost more than a report template?
Because it is a live view with filters, prepared data and written definitions, not one fixed format. Preparing the data and checking every measure against raw records takes more work than filling a template. Both have one fixed price per delivery speed, shown before you pay, so you can compare them side by side.
Can the dashboard include data from other systems?
Only data the product already touches. Blending in figures from systems it does not use, such as your accounts package, is a larger job and goes through a Change Quote. For a dashboard across many sources, AI Business Intelligence Dashboard is the fuller product.
Who can open the analytics dashboard add-on?
The people you name at intake. Access is set up for them during the build, and you can add or remove viewers later through the parent product's maintenance. If you need different views for different roles, the Role-Based Access Control add-on adds that.
Is the analytics dashboard updated in real time?
It refreshes on the schedule agreed at intake, which depends on how the parent product stores its records. Second-by-second updates are rarely needed for performance questions, so we agree a refresh rate that answers them without extra running cost. The agreed refresh rate is written into the documentation.
Know what your AI product did last month without opening a single log.
Add the Analytics Dashboard Add-on and see your product's agreed measures in one filtered view, each one defined in writing and checked against raw records.
Works well with
Inbound
AI Voice Receptionist
Answers calls, handles common questions, takes messages and transfers callers.
Lead Generation
AI Lead Qualification Agent
Qualifies inbound leads with a short conversation and scores them against your criteria.