Your Repository's Mentat
"It is by will alone I set my mind in motion."
Welcome back,
You'll need this token in Step 5
You'll need this token in Step 5
"Every sietch has its own ways. Choose wisely."
The Mentat requires certain instruments
First, get a Claude Code subscription ($20/mo). Once you have it, run these two commands — the first installs the Claude Code CLI, and the second opens your browser to log in with your Anthropic account:
npm install -g @anthropic-ai/claude
claude auth loginnpm install -g @anthropic-ai/claude
claude auth loginRequires Node.js (v18+) — npm is included when you install Node.
After installing Node.js on Windows, close and reopen your terminal before running npm.
Your AI colleague uses GitHub to manage code. Install the GitHub CLI, then log in — it will open your browser to authenticate with GitHub:
brew install gh
gh auth loginwinget install GitHub.cli
gh auth loginIf brew is not recognized, install Homebrew first: brew.sh
Don't have a GitHub account? Create one here — it's free.
Create a new folder for your project and initialize it as a git repository. Replace my-project with whatever you'd like to name it:
mkdir my-project && cd my-project
git initmkdir my-project; cd my-project
git initDownload and install Typeless for speech-to-text.
Once installed, click into your terminal where Claude Code is running, tap the Fn key (bottom-left of your keyboard) once, and start speaking. Typeless captures up to 9 minutes of speech and sends it directly to the agent as text. Tap Fn again to stop.
Once installed, click into your terminal where Claude Code is running, tap your Typeless hotkey once, and start speaking. Check your Typeless settings to see or change the hotkey. Typeless captures up to 9 minutes of speech and sends it directly to the agent as text. Tap the hotkey again to stop.
This is especially useful for brain dumps — describing your project, glossary, or taxonomy in your own words. The agent will make sense of it and structure it for you.
Access the spice reserves
Go to the Microsoft Access Portal and request the packages you need:
dmn_core_analytics, svc_sft_temporal_backend)Access is not automatic — someone from the analytics team or your manager needs to approve it. You'll get a Slack notification. Follow up directly if it takes too long.
Log in to Databricks, then:
Copy the token immediately — you won't be able to see it again. Save it somewhere safe. You'll paste it into your project's .env file in the next step.
In your project folder, create a file called .env and paste these three lines, replacing the placeholder with your actual token:
DATABRICKS_HOST=adb-2350007385231210.10.azuredatabricks.net
DATABRICKS_TOKEN=<paste your token here>
SQL_WAREHOUSE_ID=05bd6e6a717c8be7This file is automatically gitignored — your token will never be committed or shared.
Open Claude Code in your project and run:
claude "Check my Databricks connection and list available schemas"Initialize your repository's intelligence
Your token:
Make sure you're inside your project folder (from Step 3), then run this command. npx downloads and runs the installer without a permanent install. It will ask for your token — paste the one from the "Get Your Token" page:
npx thufir initIf npx is not recognized, you need to install Node.js first (same prerequisite as Claude Code).
Confirm Claude Code is installed and working. You should see a version number like 1.x.x:
claude --versionIf you see "command not found," go back to Slide 3 Step 1 and re-run the npm install command. On Windows, try closing and reopening your terminal first.
Start Claude Code and talk to your new AI colleague. That's it — you're ready for the workshop:
claude
The pre-work is complete. Your tools are sharp.
The spice will flow when the council convenes.
Workshop begins in
--:--:--
"The sleeper must awaken."
Give your colleague deep knowledge of your data systems
This prompt teaches your Mentat everything about how data works — the four layers, source tables, naming conventions, and how to build a data mart. Copy it and paste it into Claude Code.
Loading prompt...Loading example...After your Mentat processes this, it will save the knowledge for future sessions.
Establish the pipeline between your Mentat and your warehouse
This prompt sets up your Mentat's connection to the data warehouse — credentials, catalogs, schemas, and how to execute queries. Copy it and paste it into Claude Code.
Loading prompt...Loading example...Your Mentat will verify the connection and confirm it can reach your data.
The first step to understanding is naming things precisely
This prompt tells your Mentat to listen for your project description and structure it into a glossary.
Loading prompt...Loading example...After pasting the prompt, the agent will wait for you to describe your project. Use Typeless (tap Fn) or type. Talk about:
You don't need to mention table names, column names, or any technical details. The agent already knows the data sources — it will connect your language to the right tables.
Turn your glossary into queryable data
This prompt tells your Mentat to use /brainstorm to plan a data mart view with you, then build it.
Loading prompt...Loading example...After pasting the prompt, use Typeless (hold Fn) or type to tell the agent what data you want. Describe:
The agent will use /brainstorm to ask you clarifying questions, design the view, then build and test the SQL automatically.
Ask questions. Get answers. Debug what breaks.
This prompt sets up your Mentat for ongoing data exploration and debugging.
Loading prompt...Loading example...After pasting the prompt, just start asking questions naturally:
When something looks off, use Typeless to explain what seems wrong:
The agent will invoke /systematic-debugging to investigate. Speak naturally about what seems off — the agent handles the technical diagnosis.
Continue exploring at home — your Mentat remembers everything. Push your work before you close: git push