Signal Board

Build a ai agent called Signal Board: ask your warehouse a question in plain English, get a chart you can share.

What it does

Signal Board is an agent that knows your data warehouse. Ask “weekly signups by country since June” and it writes the SQL, runs it, and draws the chart. Every answer shows the query, so analysts can check it.

Stack

Use Python, DuckDB, Streamlit. The original was built with Claude Code and Gemini in 2 weeks, for about $37 in AI usage.

How it fits together

• An agent loop that reads input, decides and acts through a few tools
• A store for what it did, so a person can review and undo
• An evaluation set to measure it after every prompt change

Build it in this order

1. Write down the agent's job in one paragraph and the cases where it must ask a person
2. Build the loop with one tool and a review screen
3. Collect 50 to 200 labelled examples and build an evaluation harness
4. Add the remaining tools one at a time, re-running the evaluation each time
5. Add limits: cost per run, rate limits and a stop button

Tools to connect

• Postgres MCP: read-only access to the warehouse

A prompt that worked: Show your query, every time

When answering a data question: 1) restate the question as you understood it, 2) list the tables and columns you'll use, 3) write the SQL, 4) run it with a LIMIT first, 5) draw the chart. If the result looks surprising (a jump over 50%, nulls, duplicates), say so before showing the chart.

Watch out for

• Measure before you tune the prompt; otherwise you can't tell if a change helped
• Log every action with the reason the model gave

Done when

• The evaluation runs with one command
• A person can see and undo every action
• Costs per run are capped

Before writing code, ask me up to five questions about who this data ai agent is for and what the first version must do. Then work in small steps: after each one, tell me how to try it and wait for my feedback.