Deep Agents
blog.langchain.com
Deep Agents
When developing agents, these three components are the most crucial:
1. System Prompt (persona, tasks, examples…)
2. Tool prompts (how/when to use the tool, what to retrieve, how to present the findings…)
3. Protocols (which tools to chain, what are the constraints, prerequisites,... See more
Muratcan Koylanx.com
Anthropic published their prompts for their advanced research agent. These are long reasoning prompts. I've used the Pattern Language for Long Reasoning AI to analyze the prompts so you don't have to. https://t.co/MIuWc4715q
a simple definition for agents: LLMs autonomously using tools in a loop