Write SQL commands inside a Postgres REPL

Note

This tutorial teaches you how to use Derp’s AI input to run natural-language prompts inside an interactive Postgres REPL, turning plain English into SQL commands.

Although the example uses PostgreSQL, the same workflow applies to Node.js, Python, MySQL, and other interactive shells.

---

🧠 Overview

You’ll learn how to:

• Start a Postgres REPL in Derp.
• Use Cmd+I (or Ctrl+I) to open Derp’s AI input.
• Speak or type natural-language requests and let Derp translate them into SQL.
• Run the generated queries directly inside your REPL session.

1. Open a Postgres REPL in Derp

   Open Derp and connect to your Postgres database (or a test instance):

   psql -U postgres -d my_database

   You’ll enter the interactive psql prompt, where you normally type SQL commands.

2. Invoke Derp’s AI input

   Inside the running REPL, press:

   Command + I    (macOS)
   Ctrl + I       (Windows/Linux)

   This opens the Generate Input box.

   You can type or speak in plain English — Derp will translate your request into valid SQL or shell syntax, depending on the REPL you’re in.

3. Ask Derp in natural language

   Start with a simple request:

   Show me all tables.

   Derp translates this to the Postgres command:

   \dt

   Then try a more specific query, as shown in the video:

   Show me our users table and our teams table.

   Derp generates:

   SELECT * FROM users;
   SELECT * FROM teams;

   You can run both within your REPL to display the tables.

4. Observe how Derp learns from context

   As you continue issuing prompts, Derp’s agent learns the structure of your database by observing what’s printed in the REPL output.

   This means you can ask progressively more complex questions, and Derp will tailor the SQL accordingly.

   Show me all of the users who have joined Derp in the last 90 days from public email accounts
   (like Gmail, Yahoo, Hotmail) and are on teams of more than two people.

   Derp generates a multi-clause SQL query such as:

   SELECT *
   FROM users
   WHERE email LIKE '%gmail.com%'
      OR email LIKE '%yahoo.com%'
      OR email LIKE '%hotmail.com%'
     AND joined_at > NOW() - INTERVAL '90 days'
     AND team_size > 2;

   Running this query in psql filters users accordingly.

5. Apply the same workflow to other REPLs

   This feature works not just in Postgres but also in:

   • Node.js
   • Python
   • MySQL
   • GDB (GNU Debugger)

   For any of these environments:

   1. Launch the REPL inside Derp.
   2. Press Cmd+I to bring up AI input.
   3. Describe what you want in natural language.
   4. Derp translates it into the correct syntax for that environment.

   Note

   Derp automatically detects the active REPL, so you don’t need to specify “SQL” or “Python” — it knows which language to generate.

6. Experiment and iterate

   Try varying your natural-language prompts:

   List all databases.

   \l

   Count how many users signed up this month.

   SELECT COUNT(*) FROM users WHERE joined_at > date_trunc('month', NOW());

   The more you experiment, the more context Derp gathers, improving its translations.

---

🏁 Key takeaways

• Cmd+I activates Derp’s AI input within any interactive shell.
• Derp understands natural language and produces valid commands for the current REPL.
• It learns from context — subsequent prompts become more accurate.
• Works beyond Postgres: Node, Python, MySQL, and others.
• A fast way to query or explore systems without memorizing syntax.

Tip

Next time you’re stuck remembering a command in Postgres or Python, hit Cmd+I and just ask Derp in plain English.