Agentic-AI
All articles
Tool Use Pattern - Function Calling for AI Agents
Enabling LLMs to invoke external tools and APIs through function calling, extending model capabilities beyond …Reflection Pattern - Self-Critique and Iterative Refinement for LLMs
Using self-reflection loops where an LLM evaluates and improves its own output, catching errors and improving …ReAct Pattern - Reasoning and Acting in AI Agents
The ReAct pattern interleaves chain-of-thought reasoning with tool actions, enabling AI agents to think before …Plan-and-Execute Pattern - Separating Planning from Execution in AI Agents
A two-phase agent pattern where a capable planner model creates a step-by-step plan, then delegates each step …Kiro
What Kiro is, how AWS's spec-driven AI IDE structures development through requirements, design, and task …Compound AI Systems - Architecture Framework for Multi-Model Coordination
How compound AI systems combine multiple models, retrievers, tools, and control logic to achieve capabilities …Amazon Bedrock AgentCore
Amazon Bedrock AgentCore is a managed runtime and governance layer for deploying, operating, and securing AI …AI Agent
What AI agents are, how they autonomously plan and execute tasks, and the architectural patterns that …Agentic AI
What makes AI agentic vs assistive, autonomous task execution, tool use, planning capabilities, and current …
Open source projects