Grounded search
Search GenAIWiki
Search across models, tools, comparisons, tutorials, and glossary entries — with sources shown.
GenAIWiki
·Grounded AI answer — wiki index sources only
Searching GenAIWiki index…
Grounded search
Search across models, tools, comparisons, tutorials, and glossary entries — with sources shown.
GenAIWiki
·Grounded AI answer — wiki index sources only
Searching GenAIWiki index…
All matches for “AI agents”, grouped by content type.
Agent2Agent protocol
Agent2Agent, or A2A, is an open protocol from Google for agent-to-agent communication, capability discovery, task management, and artifact exchange.
Strong match
Computer use agent
A computer use agent is an AI agent that can inspect screenshots and control a desktop or browser with mouse and keyboard actions.
Strong match
Agentic AI
Agentic AI refers to AI systems that can plan, call tools, maintain task state, and take multi-step actions toward a goal.
Agentjacking
Agentjacking is an informal term for hijacking an AI agent's tools, context, or execution path so it performs attacker-directed actions.
Agent memory
Agent memory is the state an AI agent keeps across steps or sessions, such as scratchpad notes, retrieved facts, user preferences, or task history.
multi-agent-learning
A framework where multiple agents learn and adapt through interaction with each other and the environment.
Indirect prompt injection
Indirect prompt injection happens when untrusted external content, such as a webpage, email, document, or tool result, contains instructions that try to steer an AI system.
MCP server
An MCP server exposes tools, data sources, prompts, or workflows to AI clients through the Model Context Protocol.
Want a cited narrative answer?
Ask GenAIWiki →CrewAI
CrewAI is a Python framework for defining multi-agent “crews” with roles, goals, and delegated tasks—focused on readable orchestration of collaborative LLM agents for automation and research workflows.
Strong match
AutoGen
AutoGen is a Microsoft Research–driven framework for building multi-agent conversations and tool-using agents with flexible conversation patterns—aimed at experimentation and production agents that coordinate LLMs, humans, and tools in complex flows.
Strong match
Cursor
Cursor is an AI-native code editor (VS Code–familiar) with repo-wide context, inline edits, and agentic refactors aimed at product engineers shipping quickly. Model integrations and privacy controls evolve—verify the current product documentation for your plan and deployment mode.
Azure OpenAI
Azure OpenAI Service delivers OpenAI models inside Microsoft Azure with private networking, regional deployment, and enterprise policy controls—so teams can use GPT-family models with the same procurement, identity, and compliance patterns as the rest of their Azure estate.
OpenAI Playground
Provider of widely used frontier model APIs for text, vision, and audio, with strong developer tooling and broad ecosystem adoption across production AI applications.
Agentjacking Defense Checklist for AI Agents
A practical checklist for defending AI agents against agentjacking, indirect prompt injection, unsafe tool calls, and computer-use hijacking.
Strong match
A2A vs MCP for Agent Integrations
A clear comparison of Agent2Agent (A2A) and Model Context Protocol (MCP), including when to use each in multi-agent systems.
Strong match
Computer-Use Agent Sandboxing Checklist
A production checklist for running computer-use agents in isolated desktops or browsers with safer permissions and approval gates.
Agent Memory: Scratchpad vs Vector Store
This tutorial compares scratchpad memory and vector store memory in AI agents, focusing on their use cases and performance characteristics. Prerequisites include a basic understanding of AI memory architectures.
MAI-Code-1-Flash
Microsoft AI's agentic coding model in the MAI family, announced for fast code editing, debugging, and tool-driven developer workflows.
Strong match
Grok-2
Grok-2 is xAI’s flagship chat model positioned for real-time knowledge integrations and high-throughput conversational products on xAI’s API. Availability and pricing evolve—treat capabilities as vendor-specific.
Strong match
Claude 3.5 Sonnet
Anthropic’s balanced Sonnet-tier model tuned for long-context reasoning, careful instruction following, and strong performance on coding and analysis workloads. It is a common enterprise choice on the Anthropic API and on AWS Bedrock when teams need large context for RAG and document review.
MAI-Thinking-1
Microsoft AI's frontier reasoning model in the MAI family, announced for difficult prompts, science, math, and complex planning workloads, with Microsoft Foundry access documented as private preview.
MAI-Voice-2
Microsoft AI's voice generation model in the MAI family, announced for natural text-to-speech and voice experiences.