Prompt-Engineering

• MCP16 min read
  Sam Austinon October 23, 2026MCPLLMAI-Agents

  Writing Tool Descriptions and Schemas That Help LLMs Choose

• Tool-Calling13 min read
  Sam Austinon October 22, 2026Tool-CallingLLM-APIsAI-Agents

  How LLMs Decide to Call a Tool: A Step-by-Step Walkthrough

• Large-Language-Models13 min read
  Sam Austinon October 17, 2026Large-Language-ModelsModel-EvaluationLLMOps

  RLAIF and Constitutional AI: Feedback from AI Instead of Humans

• Large-Language-Models13 min read
  Sam Austinon October 17, 2026Large-Language-ModelsLLMOpsModel-Evaluation

  How Reasoning Models Are Trained: RL and Chain-of-Thought

• Model-Evaluation12 min read
  Sam Austinon October 16, 2026Model-EvaluationLLMOpsTesting

  LLM-as-a-Judge: How to Use One Model to Grade Another

• Model-Evaluation13 min read
  Sam Austinon October 15, 2026Model-EvaluationLLMOpsLarge-Language-Models

  Feedback Loops for LLM Apps: Turn User Signals into Better Outputs

• LLMOps12 min read
  Sam Austinon October 15, 2026LLMOpsTestingLarge-Language-Models

  LLM Regression Testing: Catch Broken Outputs After Prompt Changes

• Prompt-Engineering12 min read
  Sam Austinon October 15, 2026Prompt-EngineeringLLMOpsVersion-Control

  Prompt Versioning Best Practices: Manage Prompts Like Code

← All archives