Agents & LLM Applications

Prompt engineering for engineers

System prompts, few-shot examples, structured output and reasoning, treated as code you version and test.

Tool use, streaming and agents

How function calling works, the agent loop, streaming responses, and when an agent is the wrong choice.

Testing and evaluating LLM applications

Unit tests, eval suites, LLM-as-judge and regression testing for non-deterministic code.

How does function calling / tool use work under the hood?

Implement an agent loop. What safeguards do you add?

When would you use a workflow (chained prompts) instead of an autonomous agent?

How do you handle a conversation that exceeds the context window?

How do you test code that calls an LLM?

How would you stream an LLM response to a web client?

What is MCP?

How do you handle rate limits from an LLM provider at scale?

Your prompt change improved one test case but you're unsure it's better overall. What do you do?