Optimizer University

Optimization for the Agentic AI Era

A learning hub for learners and builders who want to measure, iterate, and improve AI systems — starting with DSPy, evaluations, and practical LLM workflows.

Built for developers, analysts, operators, and AI-curious professionals turning concepts into working systems.

Start Here

A practical path into DSPy.

We are starting narrow on purpose. The first version of Optimizer University focuses on the DSPy concepts most learners need before the broader world of agentic AI optimization starts to make sense.

Featured Resources

Curated, not cluttered.

Early on, this library stays small. We will add more videos, field notes, docs, and community links as they earn their place.

These cards are rendered from a local JavaScript array so the homepage behaves like a future database-driven resource library without needing a backend yet.

DSPy Evaluation Optimizers
The Optimizer Loop

Better AI systems come from better learning loops.

DSPy gives us a sharp starting point, but the larger discipline is broader: define the goal, measure behavior, diagnose failures, and improve the system with evidence.

1

Define

Name the task, success criteria, inputs, outputs, and failure modes.

2

Measure

Build examples, metrics, and evaluations that reveal behavior.

3

Iterate

Test prompts, signatures, modules, retrieval, tools, and workflows.

4

Improve

Ship better behavior because the evidence says it is better.

YouTube

Watch us learn and build in public.

Our channel will collect practical walkthroughs, DSPy explainers, optimizer experiments, and mental models for learners and builders working through the new AI stack.