Skip to main content
Hands-on guides for the Improve stage of the AX workflow: running experiments, optimizing prompts, and adding guardrails.

Build, Test, and Optimize a Prompt

An end-to-end walkthrough of the prompt iteration cycle using a trip-planner use case.

Prompt Experimentation for Summarization

Experiment with prompts to optimize a summarization task.

Text2SQL Application for Database Querying

Build and optimize a Text2SQL application for database querying from scratch.

Improving Structured Output Generation with Prompt Learning

Use Prompt Learning to improve accuracy on structured output generation.

Optimizing Coding Agent Prompts for Planning

Optimize coding agent prompts for the planning phase with Prompt Learning.

Optimizing Coding Agent Prompts for Execution

Optimize coding agent prompts for execution and track improvement.

Align LLM Evals with Human Judgment

Iteratively refine a custom LLM-as-a-Judge evaluator against human-annotated ground truth.

Optimizing Your Eval Prompts

Use Prompt Learning to improve your LLM evaluation prompts.

Why Public Benchmarks Lie: Building Your Own Eval Harness

Build your own eval harness instead of trusting public benchmarks, via an email-extraction service.

Designing Realtime Guardrails

Decide what to guard at input vs. output and layer guardrails without blocking real users.

Guardrails for Realtime Detection

Add realtime guardrails so production LLM apps output safe responses.