Glossary
A quick reference for the terms you'll meet across the Nexus docs. Each entry is a one- or two-sentence definition with a link to the page that covers it in full. Terms are grouped lightly - the platform and its products first, then the building blocks, then routing, memory, and testing.
The platform and its products
Nexus - the Yellow.ai platform, at nexus.yellow.ai. It brings together smart agents, an in-app AI copilot, custom widgets, and an AI Trust Centre. See Nexus platform overview.
Nexus AI Layer - the in-app AI copilot that lets you build and run your bot by asking in plain language instead of clicking - creating agents, writing prompts, indexing knowledge, generating tests, and pulling analytics. It always acts on the bot you have open. See Nexus AI Layer. (Sometimes referred to as the AI layer or Copilot Nexus.)
Harness - the build product in the Nexus rail: where you author AI Agents, Automation, and the AI Trust Centre. The build → test workflow (Configuration, agents, tools, widgets, testing) lives here. See AI agents.
Atlas - the knowledge product in the Nexus rail: the Knowledge Base your agents answer from, plus the support-portal knowledge base. See Knowledge base overview.
Fabric - the data product in the Nexus rail: customer records and segments (the CDP) your bot reads and writes. See Customer data overview.
Quickstart - the fastest path from a fresh bot to a working agent you can talk to (about 10 minutes): give the bot an identity, add one knowledge-base tool, and test it in the Playground. See Quickstart.
Playground - the interactive, single-conversation test panel on every agent's profile (the play ▶ icon in the title bar), where you chat with the bot exactly as a customer would. Your fastest feedback loop while building. See Test your AI agent.
Configuration and agents
Configuration - the project-level settings that apply to all your agents - persona, identity, conversation rules, routing logic, memory, fallback, lifecycle hooks, AI safety, and voice. Configuration shapes every conversation, rather than being one agent among many. See Configuration.
Conversational agent - an LLM-driven specialist that works out each reply on its own from your instructions and knowledge. Best for open-ended Q&A, troubleshooting, and anything where the path depends on what the user says. See Conversational agents.
Guided agent - a deterministic agent that runs the exact steps you lay out on a flow canvas, in the same order every time. Best for fixed procedures that must run consistently and auditably - order returns, KYC checks, booking flows. See Guided agents.
Conversational Agent node - the workhorse node inside a guided agent: a focused, single-step agent with its own instructions, tools, and exits. It has no trigger and is never picked by routing - the flow hands control to it, and it finishes by choosing one of its exits. See The Conversational Agent node.
Sub-agent - a hierarchical child agent created under a parent (not a peer on the Agents page). Only its parent can route to it; it's hidden from top-level routing. Use it for a narrower step inside a parent agent's flow that warrants its own persona, tools, or memory. See Sub-agents.
Routing and handoff
Trigger - the natural-language description at the top of an agent's profile that says when that agent should activate. It's the primary signal routing reads on every turn to pick the best-matching agent. Sometimes called the agent's Start trigger. See Routing Logic. (Inside a guided agent, the Start node carries an equivalent trigger description for the whole flow - see Guided agents.)
Routing Logic - the optional Configuration surface where you write plain-English rules that override or refine how each message is routed between agents and tools. Most bots route correctly with sharp Triggers alone; reach for rules only when you want a deterministic override. See Routing Logic.
Handoff / routing - the runtime act of handing the conversation to a specialist agent, driven by Triggers and any Routing Logic rules. A handoff only fires when something actually triggers routing - an @-mention of an agent in prose is a reference, not a handoff. See @-mentioning vs handing off to an agent.
Agent instructions - the rich-text field on a conversational agent that defines its identity, scope, and rules - how it behaves once it has the conversation (as opposed to the Trigger, which is when it takes over). Write them plain, one action per line. See Writing agent instructions.
Tools, workflows, and UI
Tool - an action an agent can take in the real world: run a workflow, search a knowledge base, escalate to a human, transfer a call. Defined once and usable by any agent in the bot; a tool's description is what the LLM reads to decide when to call it. See Tools - Overview.
Workflow - a callable, deterministic skill (an API call, a lookup, a calculation, multi-step business logic) built in the visual flow editor. It's a reserved term: a guided agent is not a workflow, though a guided agent can call one. Attach a workflow to an agent as a Workflow tool, or run it from a guided agent's Execute Workflow node. See the Workflow tool.
Knowledge Base - the centralized source of truth your agent answers from: documents, websites, articles, and third-party content, imported and organized in one place. Surfaced to an agent as a Knowledge Base tool. See Knowledge base overview and the Knowledge Base tool.
Widget - a custom, self-contained piece of interactive UI (a form, picker, or multi-step wizard) you design in the Widget Builder and drop into a conversation. When the user fills it out, the result flows back as the next agent input. See Widget Builder.
Memory
Memory - how the bot retains context about the customer across turns and across agent handoffs. At runtime it's a single key-value pool scoped to (botId, userId) and persisted for 2 days, shared by every agent in the conversation. See Memory in Nexus agents.
Global memory - variables declared on Configuration → Memory that are shared across every agent in the bot (e.g. customer_id, account_tier). They appear as the Global memory row on each agent's profile. See Memory vs Global memory.
Flow-local memory - the Variables attached to a Conversational Agent node: named values a node writes so that later nodes in the same guided agent run can read them. Scoped to the flow (you don't declare them in Global memory), though at runtime they still share the one per-customer pool. See Memory & conversation history.
AI Trust Centre and testing
AI Trust Centre - the durable, dataset-driven evaluation surface for a Nexus bot (a top-level studio nav item). The Playground answers "does this conversation work?"; the Trust Centre answers "is the bot, overall, getting better or worse, and what should I fix next?". See AI Trust Centre.
Evaluator - a continuous quality or safety score (e.g. Empathy, Accuracy, Hallucination, PII Detector) computed for every agent response, with a tunable threshold. Evaluators make a fuzzy LLM judgement about how good a reply is. See Evaluators & Rules.
Rule - a hard invariant the bot must always (or never) satisfy, evaluated on every run. Unlike an evaluator's score, a Rule is pass/fail. See Evaluators & Rules. (Distinct from a Routing Logic rule, which controls routing decisions - see above.)
Test case - a saved conversation plus its assertions, used to check behaviour repeatably. The detail panel pairs the conversation with the execution trace that produced it, and lets you edit inputs and re-run. See Test Case detail.
Execution trace - the per-turn, deterministic record of what the agent actually did to produce a reply: every tool call and result, memory write, routing decision, knowledge lookup, and guardrail check, in order. The chat bubble shows what the bot said; the trace shows why. See Reading an execution trace.