Is tool-calling all you need?Interaction patterns in multi-agent systems
Thursday, August 22, 2024
Part IV: MotleyСrew design choices
Is tool-calling all you need?Interaction patterns in multi-agent systems
Monday, August 19, 2024
Part III: Existing Agent Orchestration methods dissimilar to agents-as-tools
Is tool-calling all you need?Interaction patterns in multi-agent systems
Friday, August 9, 2024
Part II: Existing Agent Orchestration methods similar to agents-as-tools
Reliable AI at your fingertips: how we built universal ReAct agents that just work
Monday, July 22, 2024
AI agents are autonomous programs designed to perform specific tasks by processing information and taking actions. Like with any LLM application, careful prompting is crucial for agents to get sensible and reliable results. One of the most robust and universal prompting techniques is ReAct, which combines step-by-step reasoning and acting.
Easier development of LLM applications with motleycache
Wednesday, July 10, 2024
As any experienced developer knows, for any reasonably mature system the time spent writing new code is tiny compared to the time spent debugging it, writing tests for it, and making sure these tests pass - and especially in a duck-typed language like Python, debugging often means literally stepping through the code with a debugger and inspecting the local state.
Search