Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started

AI glossary

Clear, plain-English explanations of the terms shaping artificial intelligence.

AllAgents16Development29Fundamentals10Generative AI18Machine Learning24Models14Protocols12Safety12

All terms

135 terms

  • ProtocolsAG-UI ProtocolAn open protocol that streams events between an AI agent's backend and a user-facing app, so the interface can show progress, tool use and results as they happen.
  • ProtocolsAgent Communication ProtocolAn open protocol that lets AI agents built by different teams send each other messages over standard web requests. Not to be confused with the Agentic Commerce Protocol, which shares the abbreviation.
  • AgentsAgent HarnessEverything around an AI model that turns it into a working agent: its instructions, tools, context handling, memory, sandbox, checks and permissions.
  • ProtocolsAgent Network ProtocolAn open protocol proposal for agents to find, identify and talk to each other across the internet, using decentralised identity rather than a central registry.
  • AgentsAgent OrchestrationThe coordination of multiple agents, tools, tasks, state, and permissions within an AI system.
  • ProtocolsAgent Payments ProtocolAn open protocol, announced by Google, that lets AI agents make payments for users with cryptographic proof of what the user authorised.
  • AgentsAgent SkillsFolders of instructions, scripts and resources that an AI agent loads only when a task needs them, to do that kind of task well.
  • Protocols · A2AAgent-to-Agent ProtocolA protocol designed to help independent AI agents discover capabilities, exchange information, and coordinate work.
  • AgentsAgentic AIA paradigm of artificial intelligence focused on creating systems that act with agency and autonomy.
  • ProtocolsAgentic Commerce ProtocolAn open standard, from OpenAI and Stripe, that lets an AI agent complete a purchase for a user while the merchant stays the seller. Not the same as the Agent Communication Protocol.
  • AgentsAgentic WorkflowA process where AI models carry out several steps of a task, using tools and checking results, rather than answering a single prompt.
  • AgentsAI AgentAn AI system that can autonomously plan and execute actions using tools to achieve a goal.
  • AgentsAI Agent MemoryAn application-level system that stores and retrieves relevant information across steps or sessions for an AI agent.
  • SafetyAI AlignmentThe effort to ensure an AI system’s behavior and objectives reliably match intended human goals and constraints.
  • DevelopmentAI API KeyA secret code that identifies your account to an AI provider's API, so your requests are allowed, limited and billed to you.
  • DevelopmentAI BenchmarkA standardized test or dataset used to objectively measure and compare the capabilities of different AI models.
  • SafetyAI BiasSystematic skew in AI outputs resulting from flawed data, design, or deployment choices.
  • AgentsAI CopilotAn AI assistant built into the software you already use, which suggests and drafts while you stay in control of each decision.
Showing 1–18 of 135
Page 1 of 8
…