Skip to main content

One post tagged with "ai assistant"

View All Tags

Analytics is Changing (Again)

· 3 min read

AI has revolutionized how we write code; now it's reshaping how data teams can work.

Data + Compute + LLMs = Analytics at the Speed of Thought

The way we interact with data changes constantly; we only need to look at the last few years to see that we are seeing a shift as part of the "Great Decoupling” – a broader movement toward zero-infrastructure.

By adding Serverless Compute – via cloud functions or the browser – to formats like Apache Parquet and engines such as DuckDB, we unlock blazing fast analytics without clusters or VMs. Now AI is entering the mix, and we think this is the perfect timing to put all the pieces together.

We don’t think analysts, data engineers & scientists are going anywhere. We believe that “AI won’t replace you, a human using AI will”. AI amplifies the creativity and speed of the people already doing the work.

Here’s how we think the future of analytics looks like:

  • Data context limits hallucination: Having LLMs know exactly about the structure and content of your data means AI is much less likely to hallucinate.
  • Code execution as validation: AI code editors help write code, but can’t actually run it. At Fused we’re building on top of our real time execution engine, so errors in code are spotted and fixed much faster, all in the same workflow.
  • Human analysts to guide the work: LLMs can write every possible query imaginable to parse a dataset, or make whichever chart you want. Answering the questions becomes easier, so asking the right questions becomes more valuable.

Three ways working with AI is changing analytics

So... What is Vibe Analytics?

A few months ago Andrej Karpathy coined the term Vibe Coding: letting LLMs loose and just give in to whatever code suggestion comes around, to quickly get a prototype of a new project, specifically for web development.

We’ve since seen the term Vibe Analytics starting to pop up around, applying a similar approach but to analytics: leveraging LLMs to make it easier and faster to create analysis, make dashboards and share them to the rest of the team.

There are a few core differences though:

  • Analytics have to be based on real data: This is where having data-aware LLMs becomes so much more important.
  • Integrated with your tools: Unlike building web apps, analytics workflows require access to data and compute. Files need to be read & analysed by AI directly. Doing this properly isn’t only about making an AI Code Editor and pushing the code up once it’s written.
  • Human guidance throughout: LLMs are incredibly knowledgeable but have no self awareness of what they actually are doing. It’s still important to have proper analysts & engineers to guide the work.
Vibe CodingVibe Analytics
ContextNone, starting from scratchRooted in existing data
OutputCode, experimentsLive insights, dashboards, APIs based on real datasets
GuidanceFast loops via UIHuman-in-the-loop workflows
PurposeRapidly creating app prototypesQuickly answering complex data questions

Come Build With Us!

Help us build the future of data analytics. Reach out to us directly (hello@fused.io) or see our open positions.


We did take inspiration from Andrej Karpathy's recent Software is Changing (Again) talk at AI Startup School, as you may have noticed from the title.