Skip to content

0.7. Glossary

What does each course term mean?

Every term links to the section that introduces it. New to agents? Start with Agent, Tool, MCP, and A2A, then follow the links into the chapters.

  • A2A: Protocol for discovering agents and exchanging tasks across process boundaries. 3.6. A2A
  • A2A card: JSON descriptor an A2A server publishes declaring its skills, endpoints, and streaming support. 3.6. A2A
  • ADK: Google Agent Development Kit: the framework providing the agent runner, sessions, tools, and telemetry. 2.0. Concepts
  • Agent: A model-driven loop that selects tools or delegates work toward a goal. 0.1. Agents
  • Agent Skill: A small, discoverable instruction package rooted at SKILL.md, loaded only for a relevant task. 3.2. Skills
  • agentgateway: The proxy placed in front of agents, models, and tools that enforces policy, auth, and observability. 5.0. Gateway
  • agentic loop: The iterative reason-act-observe cycle an agent runs to reach a goal. 0.1. Agents
  • AgentOps: Practices for operating agents in production: capabilities, guardrails, HITL, and lifecycle. 0.2. AgentOps
  • backoff and retry: Retrying transient read failures (cold start, restart, locked SQLite) instead of failing the turn. 4.5. Guardrails
  • BYO Agent: A kagent "bring your own" Agent resource where the course ships its own A2A container image. 6.3. Platform Agents
  • checkpoint: The per-page verification exercise a learner completes to confirm the result before continuing. 0.0. Course
  • cosign: Tool used to verify an image is the exact one CI built and signed. 6.1. Containers
  • cosine distance: Embedding-similarity measure used by the optional semantic retrieval branch. 3.4. Memory
  • cost attribution: Assigning model and token cost to a session or tool for budgeting. 7.3. Costs
  • deadline: A bounded time limit wrapping read tools so a slow dependency costs a retry, not a hang. 4.5. Guardrails
  • Evaluation: Repeatable measurement of behavior, trajectory, safety, or output quality. 4.4. Evaluations
  • Grafana: Dashboarding UI that visualizes the shipped AgentOps metric and log panels. 7.2. Monitoring
  • Guardrail: Deterministic or model-assisted policy at an input, model, tool, or output boundary. 4.5. Guardrails
  • HITL: Human-in-the-loop: a human decision inserted before a sensitive action continues. 4.5. Guardrails
  • kagent: CNCF Sandbox project that manages agents as Kubernetes custom resources. 6.0. Platform
  • Loki: Log store that receives OTLP logs and backs the dashboard's log panel. 7.2. Monitoring
  • MCP: Model Context Protocol for discovering and invoking tool or context servers. 3.3. MCP
  • MLflow: Self-hosted store for prompt versions, traces, and evaluations. 7.0. Reproducibility
  • Multi-agent: A system where one agent delegates to several specialist agents under a coordinator. 3.7. Multi-Agent
  • NetworkPolicy: Kubernetes resource that restricts pod reachability and egress to reduce attack surface. 6.5. Platform Gateway
  • OpenTelemetry (OTel): Vendor-neutral instrumentation and transport layer for traces, metrics, and logs. 7.1. Tracing
  • OTLP: The OpenTelemetry wire protocol (HTTP/gRPC) the app and gateway use to export telemetry. 7.1. Tracing
  • PII: Personally identifiable information, redacted before requests reach the model. 4.5. Guardrails
  • Prometheus: Time-series database that scrapes collector and gateway metrics. 7.2. Monitoring
  • prompt injection: Attacker-controlled text that tries to override agent instructions. 5.5. Gateway Security
  • prompt registry: MLflow-backed registry used to version and compare prompts in the host development/evaluation environment; production images use the committed instruction. 7.0. Reproducibility
  • RAG: Retrieval that adds relevant external knowledge to the model context. 3.4. Memory
  • RED metrics: Rate, Errors, Duration: bounded request metrics derived from spans under namespace agentops. 7.2. Monitoring
  • SBOM: Software Bill of Materials listing an image's components for supply-chain auditing. 6.1. Containers
  • semantic retrieval: Optional embedding-based search enabled only when it beats the keyword baseline. 3.4. Memory
  • session: Per-conversation runtime state (events, history) owned by the ADK runner. 2.4. Sessions
  • SLO: Service Level Objective tied to an observable user outcome (e.g. 99% error-free requests). 4.3. Metrics
  • SOPS: Tool for keeping encrypted secrets in git and decrypting them at deploy time. 6.5. Platform Gateway
  • span: A single timed unit of work in a trace, emitted by ADK and gateway instrumentation. 7.1. Tracing
  • spanmetrics: OTel connector that turns spans into request-count and duration metrics. 7.1. Tracing
  • spotlighting: Wrapping attacker-influenceable tool output in a marked prefix so the model treats it as data, not instructions. 4.5. Guardrails
  • stdio: Default MCP transport where the agent launches the server as a child process. 3.3. MCP
  • streamable HTTP: MCP HTTP transport option for a networked server. 3.3. MCP
  • Tool: A typed function or remote capability an agent can invoke. 3.1. Tools
  • Trace: A correlated record of model, tool, gateway, and application work in one request. 7.1. Tracing
  • WIF: Workload Identity Federation: maps workload identity to cloud IAM without a static key. 6.5. Platform Gateway
  • Workflow: A declared graph of steps used instead of one autonomous loop for deterministic control. 3.5. Workflows