Real AI agent use cases, with sources and setup prompts

Give your coding agent a semantic layer for correct data analysis

Two BI veterans built Graphene so a coding agent can do analyst work: a token-efficient semantic layer with SQL queries, plus Markdown dashboards it can publish, connected to warehouses or local DuckDB.

See pricing page1-2 hoursIntermediateSource linked

Source

kcmarr on Hacker News · 2026-10-01 · Project link

Written in our own words. Credit to the original author. Link checked 2026-10-16.

What they did

Two BI veterans built Graphene so a coding agent can do analyst work: a token-efficient semantic layer with SQL queries, plus Markdown dashboards it can publish, connected to warehouses or local DuckDB.

Result (as claimed)

Open source on GitHub; 32 points on Show HN.

Tools they used

DuckDB

Cost: Pricing depends on the tools you pick; check each official pricing page.

Set it up

  1. Gather your sources

    Collect the papers, notes, links or files you want to work from in one place.

  2. Load them into the tool

    Open DuckDB and add your sources. Keep the original files so you can check claims later.

  3. Ask focused questions

    Ask for summaries, comparisons or connections with citations to the source passages.

  4. Verify and save

    Spot check claims against the sources, then save the output as notes you can reuse.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Give your coding agent a semantic layer for correct data analysis
What the original author did: Two BI veterans built Graphene so a coding agent can do analyst work: a token-efficient semantic layer with SQL queries, plus Markdown dashboards it can publish, connected to warehouses or local DuckDB.
Reported result (as claimed by the author): Open source on GitHub; 32 points on Show HN.
Source: https://news.ycombinator.com/item?id=49927295
Tools they used: DuckDB
Category: Research & learning

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

The Daily 5

Get five new use cases tomorrow morning

Free. Real sources. Unsubscribe any time.

Related use cases