Question for people building AI tools around data.

I’ve been experimenting with letting AI analyse business spreadsheets directly (Excel / Google Sheets), instead of requiring people to move data into BI tools.

and spreadsheets are obviously messy, making high accuracy quite hard.

• multiple tables stacked in the same sheet
• section headers
• summary blocks mixed with raw data
• inconsistent column structures

Do you guys think people actually want AI to analyze spreadsheets directly for things like: – customer analytics – sales trends – partner performance – product breakdowns

Or do most teams still prefer pushing data into structured dashboards / BI tools first?

Curious if anyone here has tried building AI on top of spreadsheets or seen this problem before.

Big update: finally something concrete to try!! (Claude Code MCP)

I’ve been tightening Sovant around a single idea: **Governed memory for AI systems. **

That means memory that is:

• explicit (written intentionally, not auto-captured)
• scoped (per repo/project)
• inspectable and editable
• with a clear lifecycle (create, update, delete)

To make this easy to experience without building an app, I’ve just shipped a Claude Code MCP integration.

If you use Claude Code, you can install a small local MCP adapter that lets Claude:

• write memory to Sovant
• recall memory later (scoped to your repo)
• update or delete memory

The MCP runs locally. Memory is stored in Sovant (cloud) using your API key. No magic memory. No auto-capture.

Install is just 2–3 minutes: 👉 https://sovant.ai/docs/mcp

If you try it, I’d really appreciate blunt feedback, especially:

• when memory should or shouldn’t be written
• whether scoped recall actually reduces confusion
• what feels unnecessary or annoying

Building this slowly and trying to get the foundations right. Happy to answer questions here.

— Henry

Heads up / early signal

I've been building Sovant as a developer-focused AI memory layer, but am now experimenting with opening it up to non-developers as well, for people who want an AI that remembers customers, decisions and context without thinking about prompts or setup.

No launch or signups yet, and still early. Just exploring whether this is actually useful outside dev circles.

I'll share more once it's ready to be tested!

Thanks.

-Henry