AI Finance Analyst

6 Interactive Sessions

Short, interactive sessions: watch it work, try it, then build it yourself. You can go deeper at any time in the written chapters.

1. 1

   Five kinds of financial data, and why they disagree

   Bring filings, earnings calls, market data, internal reports and analyst notes into one shape, called a Document, without losing the labels that make each one useful.

2. 2

   Cut documents into chunks without breaking the tables

   Cut financial documents into chunks so that each table stays in one piece, and label every chunk so the right ones can be found.

3. 3

   Three kinds of search, combined

   Combine search by meaning, search by exact words and filters on labels, so an exact financial question gets the exact chunks, then re-order them by what matters in finance.

4. 4

   Check every number before an analyst sees it

   Put a series of explicit checks between the model and the analyst, and make checking the numbers the one that matters most.

5. 5

   The model writes the words, the code does the maths

   Turn the system into something an analyst opens every morning: full of numbers, with every figure traceable to its filing.

6. 6

   Put it in front of analysts, and know it still works

   Put the system where analysts already work, and measure the one signal that tells you whether it can still be trusted.

How this certificate is scored

Your certificate shows how many of your written answers met the rubric below, checked by an AI grader. Anyone who checks your certificate sees it.

• You answer 6 short questions, one for each module, in your own words (at least 40 words each).
• An AI grader checks each answer against what its module asks for: it must answer the question, use the course's practice case specifically, and be correct.
• To pass, at least 5 of the 6 answers must meet that bar. The certificate says the answers were graded by AI.

The rubric

1. Module 1, Data Lake: Financial document ingestion pipeline.
2. Module 2, Encode: Table-aware chunking + embeddings.
3. Module 3, Retrieve: Financial relevance hybrid search.
4. Module 4, AI Gateway: Disclaimer guardrails + accuracy checks.
5. Module 5, Finance App: SEC filing analysis + comparisons.
6. Module 6, Deploy: Slack bot + MCP server.

What you walk away with