How to Ask an AI Analyst About Your Business Data
Why simple business questions take so long to answer
Most owners and managers have the same handful of questions every week: what changed in sales, who owes us money, how much cash we have, which stock is not moving, which deals are stuck. The data to answer them is already in the ERP, but getting the answer means running several reports, exporting them and comparing columns by hand.
The person who can do that analysis is usually busy, so the question waits until month-end or never gets asked. When it is answered, the explanation lives in an email or a meeting, and nobody can see which numbers it was based on.
An AI analyst that reads the business data directly, explains it in plain words and shows the exact rows behind each figure turns those weekly questions into a few seconds of reading, without exporting anything.
Why this happens
- Questions need several reports combined.
- Exports are copied into spreadsheets to compare.
- Only one person knows how to read the numbers.
- Explanations are not linked to the figures behind them.
- Follow-up questions start the work again from scratch.
Biznsbook addresses this through Ask the analyst conversations, briefs you run with one click, figures linked to their source rows, Ask panels on module dashboards in AI Analyst, reading your own company data with each figure linked to its source row.
None of this needs more data: the business records are already in the system. What is missing is a quick, trustworthy way to ask about them and see the rows behind each answer.
Step-by-step: Ask an AI Analyst About Your Business Data
Written for owners, finance managers and team leads using Biznsbook AI Analyst on their own company data.
- Check the add-on and your role. AI Analyst is an add-on at $10 per company per month. You need the AI Analyst User role, and your company must have turned analysis on in AI Analyst → Settings with an approved AI model.
- Open the Ask page. Go to AI Analyst → Ask, or use Ask the analyst on the Automation dashboard.
- Write the question in plain words. For example "What changed in sales last week?" or "Who owes us the most?". Leave Data to read on Choose from my question, or pick the area yourself.
- Click Ask and read the answer. The answer takes 10 to 30 seconds. It has a summary, findings with their figures, what to do, and what the analyst could not see.
- Open Show the data. Under the answer, Show the data lists every table the analyst read, with numbered rows, so you can check any figure against its source row.
- Ask a follow-up. Ask "And last month?" in the same conversation. The analyst remembers the last three answers, but every figure is still checked against fresh data.
- Save repeat questions as briefs. For questions you ask every week, create a brief in AI Analyst → Briefs and click Run now whenever you want a fresh answer.
Review results after the first full monthly cycle. Adjust roles, mappings, or approvals where the same exception repeats.
Setup and screen steps are in the AI Analyst guide inside Biznsbook. This page focuses on the business question; the AI Analyst page summarises the add-on.
Common mistakes to avoid
- Mistake 1: Questions need several reports combined. Repeating this each month usually shows up first in decisions made on numbers nobody checked.
- Mistake 2: Exports are copied into spreadsheets to compare. Repeating this each month usually shows up first in decisions made on numbers nobody checked.
- Mistake 3: Only one person knows how to read the numbers. Repeating this each month usually shows up first in decisions made on numbers nobody checked.
- Mistake 4: Explanations are not linked to the figures behind them. Repeating this each month usually shows up first in decisions made on numbers nobody checked.
- Mistake 5: Follow-up questions start the work again from scratch. Repeating this each month usually shows up first in decisions made on numbers nobody checked.
Each of these leaves managers acting on numbers nobody checked. Ask about the data where it lives, and read the source rows before acting on a figure.
Best practices that hold up as you scale
- Check the add-on and your role — AI Analyst is an add-on at $10 per company per month.
- Open the Ask page — Go to AI Analyst → Ask, or use Ask the analyst on the Automation dashboard.
- Write the question in plain words — For example "What changed in sales last week?" or "Who owes us the most?".
- Click Ask and read the answer — The answer takes 10 to 30 seconds.
- Open Show the data — Under the answer, Show the data lists every table the analyst read, with numbered rows, so you can check any figure against its source row.
Ask specific questions, read The data it used before acting, and save the questions you repeat as briefs.
How Biznsbook supports this workflow
Ask the analyst conversations is part of Biznsbook AI Analyst and reads the same business records the rest of Biznsbook uses, under the asking person's rights, with every figure checked against the data before the answer is shown.
briefs you run with one click is part of Biznsbook AI Analyst and reads the same business records the rest of Biznsbook uses, under the asking person's rights, with every figure checked against the data before the answer is shown.
figures linked to their source rows is part of Biznsbook AI Analyst and reads the same business records the rest of Biznsbook uses, under the asking person's rights, with every figure checked against the data before the answer is shown.
Ask panels on module dashboards is part of Biznsbook AI Analyst and reads the same business records the rest of Biznsbook uses, under the asking person's rights, with every figure checked against the data before the answer is shown.
AI Analyst is an add-on ($10 per company per month) and needs no other module; each analysis area needs its module, scheduled analysis also needs Business Automation, and your company pays its own AI provider for tokens.
Suggested implementation timeline
- Day 1: Add an approved AI model and API key in AI Analyst → Settings, tick the kinds of data allowed and turn analysis on.
- Week 1: Give the AI Analyst User role to two or three people and try Ask the analyst conversations on real questions.
- Week 2: Open The data it used on each answer and check the figures you plan to act on.
- Month 1: Save the questions people repeat as briefs, and schedule the weekly ones if you use Business Automation.
- Ongoing: Making questions part of the weekly routine.
How the analyst decides what data to read
When Data to read is left on Choose from my question, the analyst picks the area that fits the question, such as a sales review for "What changed in sales last week?" or receivables for "Who owes us the most?". If you already know the area, pick it yourself and the answer is built from that data only.
Whatever the area, the analyst reads only what you may already see in Biznsbook: your module permissions plus data classes such as Customers, Finance or Margins. Margins, HR, Payroll and Personal data each need their own right, so an answer never shows cost prices or salaries to someone who could not open them in the app.
If the data needed for part of the question is not available to you, or the module is not licensed, the answer says so under What the analyst could not see instead of guessing. That section is worth reading: it tells you whether a missing right or a missing module is limiting the answer.
Metrics to track monthly
- Questions asked per week and by whom
- Analyses refused or failed, and why
- Recommendations acted on
- Tokens and cost per month in Runs
Start with three metrics; trend direction matters more than a single point-in-time snapshot.
Manual analysis vs Biznsbook AI Analyst
Compare common manual analysis with Biznsbook Ask the analyst conversations and the related AI Analyst capabilities.
| Capability | Manual / Spreadsheet | Biznsbook |
|---|---|---|
| Getting an answer | ❌ Run reports and compare exports | ✅ Ask in plain words, answer in 10 to 30 seconds |
| Why it changed | ❌ Worked out by whoever has time | ✅ Findings explain what changed and why it matters |
| Checking the numbers | ❌ Trace back through the spreadsheet | ✅ Every figure linked to its source row |
| Follow-up questions | ❌ Start the analysis again | ✅ Same conversation remembers the last three answers |
| Who sees what | ❌ Whoever receives the file | ✅ Only data the asking person may see |
| Repeat questions | ❌ Rebuilt every week | ✅ Saved as a brief and run with one click |
Making questions part of the weekly routine
Pick three questions the business should answer every week, for example sales change, who owes the most and stock not moving. Save each as a brief, run them every Monday and read What to do first. When the same recommendation keeps appearing, act on it and ask again next week to see whether the figure moved.
Write down which questions each role asks every week and who acts on the answer.
Frequently asked questions
What kinds of questions can I ask?
Questions about your own company's data: sales, receivables and collections, cash and payables, stock health, the CRM pipeline, field service jobs, finance health, inventory cover and dead stock, the CRM funnel, bookings and no-shows, and labour coverage and cost. Each area needs its module.
Are my conversations private?
Yes. Nobody else sees your conversations, including administrators. Each question is still recorded in Runs.
How many questions can I ask?
A conversation holds up to 20 questions, and you can ask about 6 questions a minute. A company can run 50 analyses in 24 hours.
Why was my question refused?
The analyst answers only questions about your own company's data. It refuses questions about other companies, requests to change its rules and requests for code.
Can I ask from a module dashboard?
Yes. The Accounting, Inventory, CRM, Field Service, Booking (Today) and Labour Analytics pages have an Ask the AI Analyst box with example questions. The answer opens as a new conversation on the Ask page.
Does it change anything in Biznsbook?
No. It reads and explains; it never changes your data.
How this differs by industry
Retail
Shop owners ask which store or category drove last week's change in sales and which slow lines are tying up cash on the shelf.
Wholesale & distribution
Distributors ask which customers owe the most and are past their terms, and which supplier bills fall due before the next big receipt.
Manufacturing
Manufacturers ask which finished goods have the most days of cover and which open deals in the CRM pipeline will need production soon.