· 6 min read
AI answers with sources: why not trust AI-written SQL
Can you trust AI data analysis? Five ways AI-written SQL produces wrong numbers, and why official numbers should come from defined metrics with sources.
Blog
· 6 min read
Can you trust AI data analysis? Five ways AI-written SQL produces wrong numbers, and why official numbers should come from defined metrics with sources.
· 6 min read
Connect Claude Code and Cursor to business numbers over MCP: create a read-only token, configure the client, keep the token out of the repo, and sample prompts.
· 6 min read
A Telegram bot your whole team can ask about revenue: link accounts, bind the group to a workspace, ask with /ask, and set group rules so numbers stay safe.
· 5 min read
Why profit falls hard when revenue dips only a little: how to split a profit change by formula, channel and product, and how to read Si's answer.
· 6 min read
Set up scheduled P&L reports and alerts in Telegram: which metrics to send, when, how to set thresholds without noise, and how to ask Si in the group.
· 5 min read
What the Model Context Protocol is, why pasting sales files into a chatbot is risky, and how to give Claude or your own agent read-only access to approved metrics.
· 5 min read
The semantic layer explained with small-business examples: why dashboards, accounting spreadsheets and AI answers disagree, and how one versioned definition per metric fixes it.