Skip to content
All features
AI runtimepackages/ai/support-deflector

support-deflector package

Inline AI support layer — answers from your docs + past tickets before a human is needed. Hands off cleanly with full transcript.

Open docs
Stability
Stable
Scope
Global
Boundary
packages/ai/support-deflector

support-deflector

packages/ai/support-deflector

AI runtime · tool registry · MCP boundary

Ready

Capability graph

ai/support-deflector
support-deflector
Tool policy
Stream UI
Output

Run ledger

  1. 1
    Input
    packages/ai/support-deflector/request
  2. 2
    Plan
    message reducer -> model turn
  3. 3
    Tool policy
    tool schema · auth scope · rate limit
  4. 4
    Stream UI
    events -> UI state machine
  5. 5
    Output
    @nebutra/agents response envelope
p50 latency
136 ms
events/sec
399/s
providers
5
eval score
91
Usagesupport-deflector.ts
typescript
support-deflector.ts
1import { supportDeflector } from "@nebutra/support-deflector";
2
3const result = await supportDeflector.run({
4  tenantId: org.id,
5  // support-deflector is part of the AI runtime — composable with other AI primitives.
6  input: payload,
7});
More in domain · AI runtime
3d-pipelinePackage
packages/ai/3d-pipeline

3D asset generation + render — text-to-mesh + USD export + Three.js preview, with GPU-pool routing on the backend.

Explore
agent-runtimePackage
packages/ai/agent-runtime

Lower-level agent execution — message reducer, tool invocation, streaming state machine. The kernel @nebutra/agents wraps.

Explore
agentsPackage
packages/ai/agents

Multi-step agent runtime — Vercel AI SDK foundation, tool registry, streaming UI, MCP integration. The skeleton for every Sailor agentic feature.

Explore
ai-primitivesPackage
packages/ai/ai-primitives

Shared helpers used across all AI packages — token counting, prompt templating, stream-parser, retry-with-backoff. No provider dependency.

Explore