AI-IF-Mesh Framework

Hayley Features

Four intelligent capabilities — orchestration-first tour scheduling, intent-driven apartment discovery, specialized fee reasoning, and a unified multi-modal API — all centralizing intelligence in Hayley Engine while keeping every adapter thin, traceable, and consistent.

Schedule a TourFind an ApartmentFee ManagementMulti-modal
01

Schedule a Tour

Reference Flow

SAT is implemented as an orchestration handoff — not an in-service booking engine. The adapter accepts a tourScheduleEnabled flag, forwards schedule_a_tour_flag to Hayley Engine, and returns the engine's answer with full context and latency. Scheduling intelligence stays centralized; the adapter stays as a reliable routing layer.

01
Flag-drivenFeature Control
02
Engine-ledDecisioning
03
FullTraceability
Use Cases
Accepts tourScheduleEnabled flag and routes to Hayley Engine
Returns engine answer + context + latency in a single response
Optional agent handoff for complex scheduling workflows
Representative conversational workflow
H
Hayley
Online
Hey, I'm Hayley. How can I help you?
Enter your question here...
02

Find an Apartment

Reference Flow

FAA is intent-level support — not a local inventory module. The adapter packages user query and history, sends it to Hayley Engine, and surfaces apartment outputs when the engine classifies intent as find_an_apartment (mapped to "unit availability"). One stable conversational API contract; all business logic in the engine.

01
EngineIntent Routing
02
ThinAdapter Transform
03
ConsistentMetadata Output
Use Cases
Chat context + history packaged and sent to Hayley Engine
Engine classifies find_an_apartment intent → availability response
Adapter formats output (markdown / concise) based on retrieval_type
Representative conversational workflow
H
Hayley
Online
Hey, I'm Hayley. How can I help you?
Enter your question here...
03

Fee Sub-agent

Reference Flow

The fee sub-agent is recognized via retrieval_type="fee_sub_agent" (a Constants.CONCISE_RETRIEVAL_TYPES member). Hayley Engine routes fee queries to this dedicated reasoning track; the adapter selects concise output, attaches logs and latency, and persists both sides via GraphQL — with zero fee logic duplicated inside the microservice.

01
ConciseResponse Path
02
ZeroDuplicated Logic
03
GraphQLPersistence
Use Cases
Engine returns retrieval_type=fee_sub_agent → adapter picks concise output
Logs, latency, trace ID attached to every fee response automatically
User question + assistant answer stored via GraphQL create_message_api
Representative conversational workflow
H
Hayley
Online
Hey, I'm Hayley. How can I help you?
Enter your question here...
04

Multi-modality

Reference Flow

Multi-modality here means multi-response-mode + multilingual orchestration — not native image/audio parsing. The adapter handles retrieval modes (node, rag, fixed, adapter, fee_sub_agent, spf), supports english/spanish toggles, and passes through context, follow_up, and memory. Clients get one stable endpoint that serves varied AI behaviors without any client-side complexity.

01
6Retrieval Modes
02
EN / ESLanguage Support
03
1Stable Endpoint
Use Cases
Mode detection by Hayley Engine → adapter formats markdown or concise
spanish_support_enabled + spanish_toggle flags for multilingual replies
context, follow_up, and memory passed through for full conversation continuity
Representative conversational workflow
H
Hayley
Online
Hey, I'm Hayley. You can reach me via Chat, SMS, Email, or Voice — I'll remember our conversation across all channels.
Enter your question here...