Alex Morgan

Alex focuses on the unglamorous parts of LLM products: input validation, structured outputs and graceful failure. Their sessions are about turning a promising prototype into code a team can maintain.

How Alex reviews work
Alex reviews projects by reading the README first, then running the code. Feedback focuses on failure paths, schema design and whether another engineer could pick the project up tomorrow.

About

Alex teaches the engineering fundamentals that sit around a model call. That means clear API boundaries, typed inputs and outputs, sensible timeouts and retries, and prompts that are versioned and tested like any other code.

In the programs, Alex leads the modules on tokens and context windows, prompt design for developers and structured outputs. The goal is for learners to understand why a model behaves the way it does, so they can make deliberate trade-offs instead of copying patterns.

Alex cares about readable code and honest documentation. A project that clearly states its limitations is, in Alex's view, more useful than one that hides them.

This is demo content. It does not describe a real person, employer, qualification or track record.

Teaches

Prompt design and versioning for developers
Structured outputs with JSON Schema and Pydantic
Tokens, context windows and request budgeting
Error handling, retries and timeouts around model calls
Building typed LLM-backed APIs with FastAPI

Field notes

fig. — structured outputIllustrative

output · TicketTriage

{

"category": "billing",

"priority": "high",

"order_id": "48213",

"needs_human": true

}

✓ valid JSON
✓ schema v3
✓ enum values
retries: 0 / 2

FundamentalsGuide8 min read

Reliable Structured Outputs with JSON Schema and Validation

When an LLM's output feeds other code, treat it like any untrusted input: define a schema, validate strictly, retry with specific feedback, and fail loudly when the model can't comply.

By Alex Morgan · sample author

fig. — context window budgetIllustrative

08,192 tokens

if over budget → trim history first, then lowest-ranked chunks

FundamentalsExplainer9 min read

Tokens and Context Windows: A Working Engineer's Guide

Models do not read characters or words; they read tokens, and every request has a fixed token budget. This guide shows how to measure that budget, divide it deliberately, and degrade gracefully when content does not fit.

By Alex Morgan · sample author

Other mentors

Move from experimenting with AI to engineering it.

Build the foundations, projects, and habits needed to design more dependable AI applications.

Explore Programs Browse Learning Paths

Alex Morgan

Alex focuses on the unglamorous parts of LLM products: input validation, structured outputs and graceful failure. Their sessions are about turning a promising prototype into code a team can maintain.

How Alex reviews work

Alex reviews projects by reading the README first, then running the code. Feedback focuses on failure paths, schema design and whether another engineer could pick the project up tomorrow.