Why Is AI Suddenly Good at Numbers?
AI can now do maths, not because it is getting better at predicting the next number, like it predicts text, but because it's become a reasoning layer that knows when to use tools.
The architecture shift
The AIs we’re talking to isn't doing everything itself anymore. They’ve become a reasoning layer that:
Understands our request
Decides which tools will give us the best result
Executes that tool (calculator, code writing, search engine…)
Interprets the output with domain expertise
When we ask it to analyse data, it doesn't generate text as a response. It writes code, a Python script, and runs it. When you ask it to count characters, it doesn't estimate, it calls a calculator. When you need current information, it searches the web.
AI as a Data Analyst
All mainstream AI tools now work this way. In today’s video I pasted in my newsletter stats, asked for analysis, and we see the AI:
Read the data and create a CSV file
Write a Python loop to calculate weighted averages
Generate graphs using code (not an image model)
Return insights combining the numbers with marketing expertise
The LLM orchestrates. The tools execute. We get deep, accurate results.
A simpler example
Later in my video, I show how I needed to count characters in my LinkedIn profile text. I pasted it into Perplexity and asked for the word count.
First, it searched for online character-count tools and returned 147 characters.
Then I edited my text and pasted again. This time, it wrote a two-line Python script: using the text length function. And returned an accurate 134 characters.
Same task, two different tool choices—both accurate.
I didn’t tell it how to do it, it decided itself.
It’s time to start using AI for Data Analytics
Gone are the days that AI wasn’t reliable with numbers.
It is very accurate. And it's easier than you might think.
Paste your data into ChatGPT, Claude, Perplexity or Copilot.
Ask for analysis.
The AI will write the code, run the calculations, generate visualisations, and explain what the numbers mean in your context.
You don't need to learn Python or Excel formulas. You don't need to hire an analyst for simple tasks. The AI handles the technical work while you focus on the insights.
But wait, there’s more!
The best data analyst ever, are those who understand our domain knowledge.
AI is just that. We now have access to a data analyst and domain expertise in one workflow.
Newsletter stats? Data analysis + marketing insight.
Financial data? Analytics + accounting knowledge.
Medical records? Data processing + clinical context.
What you need to do with this
I suggest that when your AI uses tools, you actually look inside, like I do in my video.
You don't need to understand all the details.
But you do need awareness of what it's doing. Just like asking a staff member: how did you reach this conclusion? How did you calculate this? Did you do mental maths or use Excel? Where did you research?
If I ask a question that I expect to require code and it doesn't run any, I ask: how did you calculate this?
Often I find it made a wrong assumptions or didn’t quite get what I meant.
Looking at what the AI does builds critical thinking. It helps you understand its process, be better reviewers and catch wrong assumptions, and stay aware of emerging capabilities.
It is also a great way to stay aware of emerging capabilities, which means you'll know when to push AI harder, when to question its methods, and when it's unlocked something you couldn't do before.
So, what data can you throw at your AI tool to test its analytics capabilities?
—-
Inbal Rodnay
Guiding Firms in Adopting AI and Automation
Keynote speaker | AI Workshops | Executive briefings | Consulting CIO
Want to receive these updates straight to your inbox? Click here: www.inbal.com.au/join
When you are ready, here is how Inbal can help:
Bring your entire team on the AI journey in just 30 days. This program is designed to give your team a solid foundation in using generative AI in responsible and impactful ways. Inbal helps you choose your AI tools, create an AI policy and train your team.
Want the confidence to set strategy and lead but don't have time to keep up with all the changes in tech?
Tailored for your needs, Inbal will works with you through one-on-one sessions to develop your technology literacy and keeps you up to date.
For CEOs, partners and business leaders. Everything you need to know about AI without the noise. Inbal shares the state of AI, recommends tools, and answers your questions about strategy, implementation and safe use.
Only what's real, no hype, no noise.
This is a one-off session for your entire leadership team.
