For data analysts who want to use AI for SQL, Python and statistical work while keeping results correct, reproducible and safe to share.
The curriculum is being prepared and reviewed. Enrollment is not open yet.
About this course
An assistant that writes a plausible query in seconds is valuable only if the query is right, and analytical errors are quiet: a fan-out join or a time-zone mistake produces a confident wrong number. This course teaches analysts to use AI for speed while building in the checks that catch those errors. It covers code-executing assistants (ChatGPT data analysis, Claude's analysis tools, Gemini in Colab), notebook assistants in Jupyter, Hex and Databricks, and what data should never be uploaded.
The SQL module covers text-to-SQL with schema context and semantic layers, warehouse-native assistants such as Snowflake Cortex Analyst, Databricks Genie and Gemini in BigQuery, and a review checklist for joins, NULLs and time. Later modules cover pandas and Polars cleaning pipelines, classifying free text with an LLM at row level with sampling and agreement checks, choosing statistical tests with effect sizes and power, spotting leakage, p-hacking and Simpson's paradox in AI-proposed analyses, baseline-first forecasting, and reproducibility. BI dashboards and spreadsheet AI are covered in wrk-202. Product details are as of October 2026. Completion and a passing exam score earn a Wirewalk Institute of AI certificate of completion and assessment; it is not a vendor certification or endorsement.
What you will be able to do
Choose between a code-executing assistant, a notebook assistant and a warehouse-native assistant for a given analysis and data sensitivity
Produce correct text-to-SQL by supplying schema and semantic context and reviewing joins, NULL handling and time logic
Build a reproducible data-cleaning pipeline in pandas or Polars with AI assistance
Classify or extract fields from free text with an LLM and measure agreement against a human-labeled sample
Select an appropriate statistical test, report effect sizes, and identify leakage, p-hacking and Simpson's paradox in an analysis
Package an analysis so code, prompts and data versions can be rerun and audited
Syllabus
5 modules · 15 lessons · about 12 hours
1
Module 1: The Analyst's AI Toolkit
Assistants that execute code, notebook copilots and the data rules around them.3 lessons
Code-Executing Assistants: ChatGPT Data Analysis, Claude and Gemini in Colab
Notebook Assistants in Jupyter, Hex and Databricks
What Never to Upload: Data Classification and Synthetic Stand-Ins
2
Module 2: SQL with AI
Getting correct queries, not just plausible ones.3 lessons
Text-to-SQL That Is Right: Schema Context, Semantic Layers and Validation
Warehouse-Native Assistants: Snowflake Cortex Analyst, Databricks Genie and Gemini in BigQuery
Reviewing Generated SQL: Fan-Out Joins, NULLs, Duplicates and Time Zones
3
Module 3: Cleaning and Enriching Data
Pipelines and row-level LLM work with measured quality.3 lessons
Cleaning Pipelines in pandas and Polars with an Assistant
Row-Level Classification and Extraction from Free Text with LLMs
Exploratory Analysis Prompts That Surface Patterns Instead of Inventing Them
4
Module 4: Statistics Without Fooling Yourself
Tests, pitfalls and forecasting baselines.3 lessons
Choosing the Right Test: Assumptions, Effect Sizes and Power
Leakage, p-Hacking and Simpson's Paradox in AI-Proposed Analyses
Forecasting with AI Help: Baselines Before Models
5
Module 5: Communicating and Reproducing Results
Narratives, reproducibility and the changing analyst role.3 lessons
Charts and Written Findings from Analysis Output
Reproducibility: Versioning Code, Prompts and Data
Self-Serve AI for Stakeholders and the Analyst's Changing Role
Exam and certificate
The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 45 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.
Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.
The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by OpenAI, Anthropic, Google, Snowflake, Databricks, Hex, or Project Jupyter. Product and company names are trademarks of their respective owners.
Practical AI for finance and accounting: reviewing models in Excel with Copilot and Claude, reconciliation and close support, invoice extraction, FP&A commentary, and the SOX and audit-evidence discipline that keeps AI-assisted numbers reliable.
Using AI in legal work without ethical or evidentiary missteps: ABA Formal Opinion 512 and the Model Rules, grounded research in Westlaw and Lexis, contract review, eDiscovery, court AI-disclosure orders and building a practice-group AI policy.
AI across the employee lifecycle with the legal guardrails built in: drafting and screening in recruiting, NYC Local Law 144, Illinois HB 3773 and the EU AI Act's employment rules, handbook assistants, performance writing, and employee privacy.