Agents
All articles
37 total
GPT-6.1 Sol and DevDay 2026: Astra Performance at a Fifth of the Price New
OpenAI released GPT-6.1 Sol on 29 September 2026 at $2 per million input …
News
Added 29 Sep
·
Upd 3 Oct
·4 min
Agentic AI Updated
What makes AI agentic vs assistive, autonomous task execution, tool use, …
Glossary
Added 24 Mar
·
Upd 25 Sep
·5 min
Agentic Loops Updated
An agentic loop is the core execution pattern of an AI agent: the model …
Glossary
Added 22 Jun
·
Upd 25 Sep
·9 min
AI Agent Memory Management Updated
How to give AI agents short-term and long-term memory using …
Guides
Added 23 Jun
·
Upd 25 Sep
·8 min
AutoGen Updated
Multi-Agent Conversation Framework
Tools
Added 28 Mar
·
Upd 25 Sep
·4 min
AWS AgentCore vs Bedrock Agents Updated
When to Use Which AWS Agent Runtime
Comparisons
Added 8 May
·
Upd 25 Sep
·8 min
Context Engineering Updated
Curate the optimal set of tokens for every model call to cut cost and …
Guides
Added 23 Jun
·
Upd 25 Sep
·9 min
Google Vertex AI Updated
Unified ML Platform
Tools
Added 28 Mar
·
Upd 25 Sep
·13 min
LangChain Updated
LLM Application Framework
Tools
Added 28 Mar
·
Upd 25 Sep
·7 min
Model Context Protocol (MCP) Updated
An open protocol that standardises how language models connect to tools, …
Glossary
Added 8 May
·
Upd 25 Sep
·7 min
Model Context Protocol (MCP) Updated
Universal Tool Interface for AI Agents
Tools
Added 25 Mar
·
Upd 25 Sep
·4 min
Multi-Agent AI Systems Updated
When One Model Is Not Enough
Guides
Added 24 Mar
·
Upd 25 Sep
·4 min
Multi-Agent Systems Updated
Definition, architecture patterns, and frameworks for multi-agent AI …
Glossary
Added 24 Mar
·
Upd 25 Sep
·4 min
Pydantic AI Updated
Type-Safe Agent Development
Tools
Added 25 Mar
·
Upd 25 Sep
·3 min
Tool Use (in Language Models) Updated
The capability of a language model to invoke external tools: APIs, code …
Glossary
Added 8 May
·
Upd 25 Sep
·5 min
What If AI Really Takes Over? New
Taking the takeover argument seriously enough to test it link by link. …
Blog
Added 13 Sep
·
Upd 25 Sep
·8 min
Agent-as-a-Judge
An evaluation approach that uses a full agentic system to judge another …
Glossary
Added 6 Jul
·
Upd 6 Jul
·2 min
Agentic Context Engineering (ACE)
A self-improvement method where an agent curates its own context as a …
Glossary
Added 6 Jul
·
Upd 6 Jul
·2 min
Agentic RAG
Retrieval-Augmented Generation systems in which the language model …
Glossary
Added 8 May
·
Upd 30 May
·5 min
AI Agent Security Incidents 2025-2026: The Year Agentic AI Became an Attack Vector
A documented wave of AI agent security breaches, from prompt injection …
News
Added 30 Jul
·
Upd 30 Jul
·4 min
AI Concepts Knowledge Graph
Interactive learning-path map of 124 concepts and 237 connections. Click …
Added 22 Jun
·
Upd 22 Jun
AI21 Labs
AI21 Labs built the Jamba hybrid Mamba-Transformer model family, but …
Added 29 Jun
·
Upd 9 Sep
·6 min
Backstage as an Agent Interface
How to let a coding agent create real infrastructure through a Backstage …
Guides
Added 2 Sep
·
Upd 3 Sep
·10 min
Context Engineering
The practice of curating and maintaining the optimal set of tokens an …
Glossary
Added 14 Jun
·
Upd 14 Jun
·4 min
Context Engineering vs Prompt Engineering
How context engineering differs from prompt engineering, why the framing …
Comparisons
Added 14 Jun
·
Upd 14 Jun
·3 min
Declarative Control Planes for Agents
Two different answers to how an agent safely changes infrastructure: run …
Patterns
Added 3 Sep
·
Upd 3 Sep
·11 min
Deliberative Alignment
A safety-training method where a model explicitly recalls and reasons …
Glossary
Added 6 Jul
·
Upd 6 Jul
·2 min
Function Calling
Structured tool invocation by language models: how the model emits typed …
Glossary
Added 8 May
·
Upd 30 May
·6 min
LangChain 1.0: The First Stable Release Consolidates on LangGraph
LangChain 1.0 shipped on October 22, 2025 with create_agent, agent …
News
Added 22 Oct 2025
·
Upd 15 Jun
·4 min
Latent Reasoning (Chain of Continuous Thought)
Reasoning performed in a continuous latent space instead of by emitting …
Glossary
Added 6 Jul
·
Upd 6 Jul
·2 min
Orchestrator-Worker Pattern
An orchestrator LLM decomposes complex tasks and delegates subtasks to …
Patterns
Added 28 Mar
·
Upd 30 May
·3 min
Reinforcement Learning
What reinforcement learning is, how agents learn from rewards, and where …
Glossary
Added 28 Mar
·
Upd 30 May
·3 min
Single Agent vs Multi-Agent Architectures
When to use a single AI agent versus a multi-agent system, covering …
Comparisons
Added 28 Mar
·
Upd 14 Jun
·5 min
The Catalog as Agent Context
A developer portal can answer an agent's questions, not just execute its …
Guides
Added 3 Sep
·
Upd 3 Sep
·11 min
Trajectory Evaluation
Scoring the full path an agent takes, including tool calls and …
Glossary
Added 6 Jul
·
Upd 6 Jul
·2 min
What Your AI Assistant Can Actually Do
The same model behaves very differently depending on which product it …
Guides
Added 2 Sep
·
Upd 2 Sep
·5 min
Workflow Evaluation
Testing a chain of AI steps and hand-offs end to end, because small …
Added 29 Jun
·
Upd 29 Jun
·4 min
37 articles in this section. Search for a specific topic.
Work with Linda Mohamed, AWS Community Hero