Univer: Feishu's former spreadsheet engineering lead is building AI spreadsheets for agents
Univer is turning spreadsheets into an AI tool. Led by Feishu's former head of spreadsheet development, the team is building an engine that can plug into any system. AI agents process the data on their own, and humans only sign off on the results. The approach puts Univer ahead of Excel Copilot and ChatGPT Agent.
AI-processed from 36Kr (36氪); edited by Hamidun News
Spreadsheets have long been the domain of manual labor, but AI is giving them a second life. Univer, a startup founded by Feishu's former head of spreadsheet development, wants to fundamentally change how people work with data by turning spreadsheets into an AI tool used not by humans but by AI agents.
Univer founder and CEO Liu Yang believes the future lies in automation: AI should import, clean, and analyze data on its own, then hand the user ready-made insights. Copilot's approach still has a human interacting with the tool. Univer instead offers a fully automated solution in which AI makes the decisions and the human approves them.
The key to this vision is Univer's own spreadsheet engine, built from scratch. It can extract dependency graphs between formulas, which makes the information easier for AI to understand. Univer also uses an SDK architecture, so its spreadsheets can be embedded into existing workflows without forcing users to switch between applications.
Univer is already posting impressive results. On the global SpreadsheetBench leaderboard, the company outperformed Excel Copilot and ChatGPT Agent. Univer's product, "表答" (Capalyze), lets users automatically collect and analyze data from multiple sources and turn it into structured spreadsheets.
The implications for the industry and users are significant. AI-powered spreadsheets have the potential to revolutionize data analysis, making it faster, more efficient, and more accessible. Businesses can use AI agents to automate data processing, freeing employees to focus on strategic decision-making. The rise of AI-native spreadsheets could also lead to new applications and services built on the power of structured data.
Still, AI spreadsheets face obstacles on the road to widespread adoption. The AI algorithms need to be accurate and reliable, and data security and privacy issues have to be resolved. Users will also need training and time to adapt to new ways of working with spreadsheets.
Univer stands at the start of a new era in working with data. By turning spreadsheets into an AI tool, the company opens up new possibilities for automation, analysis, and decision-making. Much work remains, but the potential of AI spreadsheets is enormous, and they could radically change how we work with information in the future.
- Nov 1, 2026OpenAI Rewrites GPT Behavior Rules: Five Values and a Chain of Command
- Nov 1, 2026Google admits AI Mode cuts search revenue, shares fall 15%
- Oct 31, 2026Author puts his script before an AI jury: the verdict cost 850 thousand tokens
- Oct 31, 2026Anthropic: Fold Subagents Back Into a Single Loop — One Customer's Tasks Ran Twice as Fast
Build & Ship Production AI Agents Without Boilerplate Code
Start your free 72-hour trial at Hamidun Academy (academy.hamidun.com) — interactive lessons on Claude Code & Cursor, live Tech Radar, and production agent templates.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.