Sourcetable, a startup behind a ‘self-driving spreadsheet’ tool, wants to replicate the vibe coding trend for data analysts
The startup wants to take on the industry giants behind Excel and Sheets


Sourcetable, a startup developing what it’s dubbed the world’s first ‘self-driving spreadsheet’, has raised $4.3 million in funding to transform data analysis.
The seed funding round was led by Bee Partners, with participation from a host of leading industry figures including Hugging Face co-founder Julien Chaumond.
Sourcetable’s autonomous spreadsheet uses AI to streamline and simplify data analysis activities for users. Using natural language prompts, users can give the tool instructions - either through voice commands or keyboard - to edit or carry out multi-step activities.
The firm’s aim is to create a “vibing” experience when using spreadsheets, similar to the emerging “vibe coding” trend in software development, in which devs use AI tools to generate code rather than writing manually.
"AI is the biggest platform shift since the browser, with a bigger opportunity for disruption. Sourcetable is building the AI spreadsheet for the next billion users, be they human or AI," says Eoin McMillan, CEO & Co-founder of Sourcetable.
"As AI makes analysis easier, everybody will become an analyst. Sourcetable's AI automation ushers in a new era of productivity and human cognition."
How Sourcetable’s spreadsheet tech works
Sourcetable said its autopilot mode can complete a “wide range of complex tasks” that would typically require advanced spreadsheet expertise.
Get the ITPro daily newsletter
Sign up today and you will receive a free copy of our Future Focus 2025 report - the leading guidance on AI, cybersecurity and other IT challenges as per 700+ senior executives
This includes creating and editing financial models, generating spreadsheet templates, building pivot tables, and cleaning and enriching data.
The in-built AI model can understand the context of data without requiring users to pre-select ranges, the firm said, or interpret multiple ranges across different tables.
While the tool will seek human clarification when instructions are unclear, it otherwise functions as an autonomous assistant for users working in spreadsheets.
Sourcetable revealed that users will be able to draw upon a wide range of models when using the tool, and the AI will autonomously select or combine the optimal models for specific tasks.
“This agility allows Sourcetable to integrate the latest breakthroughs from OpenAI, Anthropic, Groq, Meta (Llama), Nvidia, Prior Labs, DeepSeek, and Hugging Face on the day of release, ensuring users always have access to cutting-edge AI capabilities,” the company said in a statement.
Sourcetable wants to shake up data analysis
Sourcetable was founded by San Francisco-based entrepreneurs, Eoin McMillan and Andrew Grosser, both of whom have extensive experience in machine learning and AI from previous startup ventures.
This technical background has enabled the team to ‘leapfrog’ AI tools offered by leading platforms such as Excel and Sheets, the firm claims.
The platform was originally built for technical users such as data scientists, Python programmers, and SQL analysts.
“For decades, we’ve been stuck in a world with those who know Excel, and those who don’t. Not anymore. Today’s AI supercycle demands that all of our interfaces transform to become useful for both humans and machines, and they all demand a new data architecture,” said Michael Berolzheimer, managing partner at Bee Ventures.
“Eoin, Andrew and the Sourcetable team have done it. Now anyone, human or agent, can benefit from accurate, reliable data analysis, underpinned by the all important spreadsheet.”
MORE FROM ITPRO
- This startup wants to simplify AI adoption through a single “orchestration” platform
- Password management startup Passbolt secures $8 million to shake up credential security
- CyberArk eyes identity security gains with $175 million startup acquisition

Ross Kelly is ITPro's News & Analysis Editor, responsible for leading the brand's news output and in-depth reporting on the latest stories from across the business technology landscape. Ross was previously a Staff Writer, during which time he developed a keen interest in cyber security, business leadership, and emerging technologies.
He graduated from Edinburgh Napier University in 2016 with a BA (Hons) in Journalism, and joined ITPro in 2022 after four years working in technology conference research.
For news pitches, you can contact Ross at ross.kelly@futurenet.com, or on Twitter and LinkedIn.
-
What is polymorphic malware?
Explainer Polymorphic malware constantly changes its code to avoid detection, making it a top cybersecurity threat that demands advanced, behavior-based defenses
-
Outgoing Kaseya CEO teases "this is just the beginning" for the company
Opinion We spoke to Fred Voccola who remains a key figurehead at the firm as it enters its next chapter...
-
Microsoft says workers should believe the hype with AI tools: Researchers found Copilot users saved three hours per week sifting through emails, gained more focus time, and completed collaborative tasks 20% faster
News Using AI tools paid dividends for some workers, but alternative research shows it could create problems for others down the line.
-
AI-first partnerships: Unlocking scalable growth for business
Industry Insights Channel partners play a vital role in facilitating AI adoption, but there's more to offering support than simple integration
-
Reinventing Procurement: From Cost Center to Innovation Driver
whitepaper
-
Digital Optimisation Paves the Way to Strategic Supplier Management
whitepaper
-
Google Cloud is leaning on all its strengths to support enterprise AI
Analysis Google Cloud made a big statement at its annual conference last week, staking its claim as the go-to provider for enterprise AI adoption.
-
Meta executive denies hyping up Llama 4 benchmark scores – but what can users expect from the new models?
News A senior figure at Meta has denied claims that the tech giant boosted performance metrics for its new Llama 4 AI model range following rumors online.
-
Fake it till you make it: 79% of tech workers pretend to know more about AI than they do – and executives are the worst offenders
News Tech industry workers are exaggerating their AI knowledge and skills capabilities, and executives are among the worst offenders, new research shows.
-
DeepSeek and Anthropic have a long way to go to catch ChatGPT: OpenAI's flagship chatbot is still far and away the most popular AI tool in offices globally
News ChatGPT remains the most popular AI tool among office workers globally, research shows, despite a rising number of competitor options available to users.