14 terms
Definitions in this topic
- Agentic AIA2A protocolThe A2A protocol explained: how agent to agent communication works, and how it differs from MCP.
- Agentic AIAgent cardAgent cards explained: the A2A discovery document that advertises an agent's capabilities and connection details.
- ProductionAI GatewayAI gateway explained: the production control layer that routes, secures, measures, and governs calls to language model providers.
- Agentic AIBrowser useWhat browser use means for AI agents, how it relates to computer use, and what to check before agents operate web apps.
- Agentic AIComputer useComputer use explained: the screenshot, reason, act loop, real use cases, and the risks worth knowing before enabling it.
- ProductionLLM GatewayLLM gateway defined, with its role in routing, policy, observability, reliability, and provider portability.
- Agentic AIMCPMCP explained for developers: what problem it solves, how the client-server architecture works, and when to build a server.
- Agentic AIMulti round-trip requestsHow multi round-trip requests work in MCP: input_required results, request state tokens, and why stateless servers need the pattern.
- ProductionOpenAI-Compatible APIWhat an OpenAI-compatible API covers, which request fields providers silently ignore, and how we call one in production without an SDK.
- Agentic AIProgrammatic tool callingProgrammatic tool calling explained: the model orchestrates tools in code, cutting round trips, latency and token use.
- ProductionRealtime AI APIRealtime AI APIs explained: persistent sessions, streamed events, low-latency audio, interruptions, and the production controls they require.
- Agentic AIStateless MCPStateless MCP explained: what the 2026-07-28 spec removed, why, and what it changes for MCP servers in production.
- LLM foundationsStructured outputStructured output explained: how schema-constrained generation works, and why it matters for tool calling and agents.
- Agentic AITool callingTool calling (also called function calling) explained: how it works, and why it is what makes an AI agent possible.