Skip to content
New this month 24 fresh C++, C#, F#, JavaScript, TypeScript and Lua courses just landed. Browse new releases Use code WELCOME10 for 10% off your first order · 14-day refund
WisdomCharms — home
Cart 0 items in cart
Prompt Packs & Templates Intermediate

The SQL and Data Analysis Prompt Pack

Prompts that write, explain and stress-test SQL against a schema you paste in yourself.

Rated 4.5 out of 5 from 2 reviews 33 students

SN Created by Sofia Navarro

  • Last updated August 2026
  • English
  • 2h 45m of material
  • 21 lessons

What you will learn

7 concrete outcomes

Every bullet below is something you will have built, shipped or be able to explain by the time you finish the last lesson.

  • Give the model a schema so it stops inventing tables and columns
  • Translate a fuzzy business question into a query with stated assumptions
  • Rewrite correlated subqueries into joins the planner can actually optimise
  • Build running totals, rankings and cohorts with window functions
  • Generate sanity checks that expose a wrong answer before anyone acts on it
  • Turn plan output into a concrete list of changes worth trying
  • Adapt prompts across PostgreSQL, MySQL, SQLite and warehouse dialects

Course curriculum

5 modules · 21 lessons · 2h 45m of material

4 lessons running 30m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

4 lessons running 32m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

5 lessons running 40m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

4 lessons running 34m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

4 lessons running 29m in total. Each lesson ships with the finished source files and a short written recap, so you can follow along in your own editor and skim the module again later.

Lesson-by-lesson titles, code downloads and exercises live inside the course library you get access to straight after checkout.

5 modules · 21 lessons

2h 45m total length

Requirements

Short list, and deliberately so. If you meet these you can start today.

  • You can write a basic SELECT with a join
  • Access to a database you can query, or the sample schema included
  • A chat model account such as Claude or ChatGPT

About this course

A model that has never seen your schema will happily write SQL against tables it imagines. This pack starts from the opposite assumption: you paste the schema, the model works only from it, and every query comes back with the assumptions it made written out above the code.

There are prompt sets for translating a business question into a query, for explaining an inherited query line by line, for rewriting a correlated subquery into a join, for building running totals and rankings with window functions, for cohort and retention analysis, and for the sanity checks that catch a wrong answer before it reaches a dashboard. A separate set turns a slow query and its plan output into a short list of concrete changes to try.

A large section deals with correctness rather than syntax, because a query that runs is not a query that is right. Those prompts generate counting checks, boundary probes and small deliberate breakages that reveal whether your filter really did what you meant.

Written for PostgreSQL first, with dialect notes for MySQL, SQLite and common warehouses. Twenty-one recorded lessons work through an analytics schema. Delivered as Markdown, Notion, plain text and a SQL file of example schemas, by an emailed access link.

Topics covered

Frequently asked questions

Still unsure about something? Write to misteryjj100@gmail.com and a human answers, usually the same working day.

PostgreSQL is the default. Every prompt set carries dialect notes for MySQL, SQLite, BigQuery and Snowflake where the syntax differs.

No. A sample analytics schema with seed data is included, so you can practise without connecting to anything of your own.

A section covers exactly that question, including how to strip identifying data, what to redact, and when to use a local model instead.

Checkout is handled on our provider's secure payment page. The moment your payment clears we email your personal access link and access code to the address you used at checkout, and the same link appears in your account library. There is nothing to install and nothing to wait for.

Email misteryjj100@gmail.com within 14 days of your purchase, quote your order number, and we refund the full amount to your original payment method. No form to fill in and no questions about how much of the course you watched.

What students say

Reviews are written by people who bought this course. We publish the critical ones too.

4.5

Rated 4.5 out of 5

Course rating · 2 reviews

Rating distribution

  • 5 stars 50%
  • 4 stars 50%
  • 3 stars 0%
  • 2 stars 0%
  • 1 star 0%
  • ZK

    Zofia Kaminska

    Analytics engineer

    Mar 2026
    Rated 5.0 out of 5

    Feeding the schema properly is most of it

    I had been pasting bare CREATE TABLE statements and wondering why the joins came back subtly wrong. Including the cardinalities and flagging which columns are secretly nullable, as this pack insists on, transformed the output quality overnight.
  • OB

    Owen Blackwood

    Data analyst

    Jan 2026
    Rated 4.0 out of 5

    Deliberate breakage is a clever check

    Getting the model to produce a query and then produce the input that would make that query wrong is a neat trick and I have adopted it permanently. Marked down because the retention prompts quietly assume an event table shaped very much like the author's own.

Your instructor

SN

Sofia Navarro

Python and data engineer

  • 231 students taught
  • 11 courses published
  • 4.5 instructor rating
  • Python
  • SQL
  • PostgreSQL
  • Data engineering

Sofia builds the pipelines that keep analytics teams honest, mostly Python on top of PostgreSQL under uncomfortable load. She teaches schema design, indexing and query planning against anonymised production datasets rather than toy tables, then wires the same data into pandas so the SQL and the Python halves stop being separate skills. Expect to spend real time reading execution plans and rather less time reading slides. She consults on migrations for teams that cannot afford downtime.

See every course by Sofia Navarro
$15 USD

One-time payment · lifetime access

The WisdomCharms dispatch

One useful email a week. No fluff, no spam.

New course releases, discount codes before anyone else, and a short, practical breakdown of one technique — a prompt pattern, a C++ idiom, a TypeScript trick — that you can use the same day.

  • Subscriber-only launch pricing
  • Unsubscribe in one click
  • We never sell your address

By subscribing you agree to our Privacy Policy. Questions? Write to misteryjj100@gmail.com.