Skip to main content

What the Nexus engine does for you

These are the platform-enforced behaviours you get out of the box, on top of the specialised-agents + shared-Configuration + tools model described in the Harness overview.

AreaNexus changeWhy it matters
RoutingTwo-stage LLM call - a small Context Expert picks the agent from each agent's Trigger description only, then a Conversation Agent runs that agent's instructions + tools.Faster routing (smaller Stage 1 model), narrower Stage 2 prompt, fewer wrong-tool calls.
ContinuityThe platform enforces a fixed continuity rule every turn - keep on the same agent unless the user has clearly switched topics.Fewer mid-flow drop-offs without writing defensive "stay here" logic.
Numbered stepsIf your Agent instructions list Step 1: / Step 2: …, the platform auto-injects sequential-execution rules: one step per turn, with step progress tracked automatically.Multi-step procedures stay on track without per-flow boilerplate.
Parent-child agent triggersA parent agent can call a child agent: the platform snapshots the parent's state, runs the child, and auto-restores the parent when the child completes. 1 level deep.Reusable sub-tasks (verify identity, capture payment) callable from any parent without writing return logic.
Conversation historyOnce history exceeds ~15 messages / ~10K characters, older turns are automatically summarised; the last 2 user turns stay verbatim.Long support conversations don't blow context; recent turns stay verbatim.
Tool failurePlatform rule: don't retry the same tool. Return the error as the tool result so the LLM phrases a recovery message.Predictable failure UX; no silent retries.
Execution traceEvery turn stores a structured executionTrace - tool calls + results, memory writes, intent classifications, the Context Expert decision.Testing lab and Copilot Debug share one underlying record. A buggy production conversation becomes a regression test in one click.
Routing Logic surfaceNew sub-page under Configuration (Configuration → Routing logic) where you write optional plain-English rules ("if billing → billing-agent").Deterministic handoff when you want it; routing falls back to each agent's Trigger when you don't.
Widget BuilderNew top-level surface for designing custom in-conversation UI (forms, pickers, multi-step wizards).Custom UI without channel-specific code.
AI Trust CentreNew top-level menu - Testing lab + Evaluators & Rules (Quality / Safety scoring with thresholds).Durable regression coverage and automated scoring.
Versioned configurationEvery Configuration change is versioned with history.Roll back; review behaviour shifts over time.
@-mentions in promptsType @ in most prompt fields (bot identity, conversation rules, welcome/fallback - Routing Logic rules are the one exception, plain text only) to insert a live reference to an agent, workflow, tool, or rich-media item. Chips stay linked through renames.Prompts don't go stale when you rename a target.
Welcome / Fallback optionsWelcome supports Instruct, Send message, or any welcome workflow you've defined (each workflow shows up as its own option). Fallback supports Instruct + a retry count for validation failures.Cleaner UX; workflows attach as options instead of via a generic "Trigger a flow" item.

Back to: Harness overview