AI, agents & prompting prompts
Prompts for building with language models: system prompts, tools, and evaluation.
The builder treats these as agentic / tool use tasks: instructions for a model that plans, calls tools, and acts over multiple steps. That sets the section order and adds the requirements this kind of work implies but people rarely write down.
Ready-made ai, agents & prompting prompts
Written out in full, with every placeholder explained and the techniques behind them broken down.
- System prompt for a tool-using agent
Tool rules, failure handling and stop conditions — the parts agent prompts usually omit.
- Answer strictly from supplied documents
A RAG prompt that says "not in the documents" instead of filling the gap.
- LLM-as-judge evaluation rubric
A judge prompt with binary criteria, so scores are repeatable rather than impressionistic.
System prompts
Agents & tool use
RAG & context
Evaluation
Prompting techniques
Related categories
- Personal & lifestyle prompts
- Health & fitness prompts
- Legal & finance prompts
- Translation & localisation prompts
- Fun & creative prompts
- Writing & content prompts
Or start from scratch in the prompt builder, improve a prompt you already have in the prompt improver, or see how the scoring works.