Reduce support load
Resolve high-volume booking and travel questions automatically across the channels passengers already use.
Always-on passenger concierge for airlines
From the moment a booking is created, flyjeeves gives every passenger a 24/7 concierge that can answer questions, assist across channels, manage ancillaries and keep service moving.
- Available from booking to travel
- Voice, chat, WhatsApp, SMS and email
- Built to drive ancillary conversion
- Learns gaps. Ships fixes.
Live passenger flowActive
ReservationO522US
IntentAdd baggage
Booking createdContext loaded
Locator, passenger and trip details become available to the concierge.
Passenger asksChannel understood
Voice, chat, WhatsApp, SMS and email flow into the same service layer.
Action neededPolicy checked
Sensitive requests pass through confirmation, OTP and execution controls.
Revenue momentAncillary served
Baggage, seats and priority can move from question to quote to payment.
Solution
A concierge that starts working when the booking starts living
flyjeeves connects customer service, booking context and airline workflows into one AI concierge experience. Instead of fragmented channels, airlines can offer one always-available service layer that understands the reservation and helps passengers move forward.
Increase ancillary revenue
Turn service interactions into conversion opportunities for baggage, seats, priority and payment-related flows.
Keep journeys moving
Help customers with check-in readiness, booking context, contact updates and next-step actions in one continuous service layer.
Capabilities
Built for real airline service flows
flyjeeves is not positioned as a generic chatbot. It is a service layer for airline operations: reservation-aware, action-oriented and designed to move a passenger from question to outcome.
Grounded in the booking, not just in a prompt
Retrieve reservation details from locator and surname, understand context and explain the trip in passenger-friendly language.
- Booking lookup and context-aware replies
- Reservation questions across the trip lifecycle
- Passenger-facing explanations, not raw system output
Built to assist and to act
Support baggage, seats, priority, quotes and payment-adjacent workflows from the same concierge experience.
- Extra baggage, seats and priority boarding
- Quote generation and payment-link flows
- Action-oriented servicing instead of FAQ deflection
Verification before execution
Gate sensitive requests through offer-confirm-execute patterns and cross-channel verification instead of blind automation.
- Cross-channel OTP for sensitive actions
- Explicit confirmation before outbound execution
- Operational traceability with cost and token signals
Operational controls
Built with the controls airlines expect around AI execution
flyjeeves is not just about answering well. It is designed to operate with approvals, policy controls, privacy-aware handling and quality review loops around the runtime.
AUTH / OTP
Verify sensitive passenger actions with explicit authentication and OTP gates before execution.
Files and knowledge
Ground answers and assistance flows with policy files, FAQs and curated airline knowledge sources.
GDPR-aware handling
Passenger interactions can be operated with privacy-sensitive handling, controlled memory and traceability requirements in mind.
Guardrails
Apply policy-aware controls around what the concierge can say, trigger and execute across service flows.
VoiceTwilio voice
Web chatPassenger chat
WhatsAppWhatsApp
EmailPassenger email
OrchestratorAirline CX Copilot
PlannerDefault planner
ComposerDefault composer
MemoryHybrid memory
GuardrailDefault guardrail
AssistantAncillary assistant
AssistantPrimary CX assistant
AssistantPolicy assistant
AssistantBooking assistant
ToolAdd baggage
ToolAdd payment
FilePolicy FAQs
ToolBooking lookup
Human-in-the-loop
Escalate sensitive or ambiguous cases to human teams with explicit HITL routing instead of forcing full automation.
Memory
Use controlled memory and booking context so the concierge stays consistent across the passenger journey.
Quality assurance
Semantic QA and runtime evaluation help teams review quality, observe issues and tighten operational performance over time.
Tools
Expose airline actions like baggage, payment or booking operations through controlled tool execution paths.
Continuous improvement
The system can learn where service breaks down and help ship the fix
flyjeeves is not limited to handling conversations. Through Intel and Dev Squads, it can analyze live interaction patterns, surface improvement opportunities and translate those findings into delivery work that expands the product itself.
01 · Intel
Detect operational findings from real conversations
Intel can review conversations to detect repeated friction, missing capabilities, unresolved intents, handoff patterns and ancillary opportunities that the current runtime is not fully capturing.
02 · Dev Squads
Convert findings into concrete implementation work
Those findings can flow into Dev Squads, where the system structures the work needed to add or improve runtime behavior instead of leaving insights trapped in dashboards.
03 · Runtime
Deploy new tasks, nodes and workflows back into service
The outcome is a concierge that can evolve from production evidence: new tasks, new nodes, new orchestration paths and better support coverage tied directly to observed passenger demand.
Intel reads the conversation layer
Conversation traces, outcomes, friction points and unresolved intents can be analyzed to identify where the concierge is underperforming or leaving revenue on the table.
Dev Squads turn findings into delivery work
Detected opportunities can become scoped implementation work, so insight moves from reporting into product improvement.
New nodes and tasks close the gap
The platform can evolve by adding new tasks, workflows and nodes that address real passenger issues discovered in production conversations.
The product is not static after launch. It can inspect real service behavior, identify what is missing and help create the code work required to expand coverage where it matters most.
Technology
Built on a stack that can support production-grade airline service
The product story is service-led, but the operating model matters. flyjeeves runs on proven infrastructure, runtime and data components that support scale, control and extensibility.
aws
AWS
Cloud infrastructure, network boundaries, storage and runtime services provide the operational base for a production-grade airline concierge.
ElevenLabs
Speech-to-text and text-to-speech capabilities support responsive voice conversations across Twilio-powered passenger service flows.
Google Gemma
Open model routing can support low-latency semantic tasks, focused classification and evaluation paths where quality thresholds are met.
Neo4j
Graph projections connect profiles, aliases, memory and interaction context so retrieval can follow passenger relationships instead of isolated records.
Node.js / Next.js / TypeScript
The development stack combines typed backend services, fast app routing and production-ready web surfaces across Studio and landing experiences.
OpenAI
High-quality language intelligence remains available for passenger-facing reasoning and tasks that need stronger model guarantees.
Postgres
Structured tenant data, booking records, memory items, traces and operational state sit on a robust relational foundation.
Redis
Low-latency session state, cache coordination and fast runtime lookups support responsive conversations where speed matters.
NestJSPrismaBullMQAPI GatewayCloudFrontRoute53SESLambdaECRSSM / Secrets
AWS architecture
How the platform is shaped in AWS
Based on the Terraform topology in the repo: Route53 and CloudFront in front, ALB and API Gateway for ingress, ECS for the app runtime, Aurora/Postgres and Redis for state, Neo4j on EC2 for graph memory, and SES plus Lambda for inbound email flows.
Edge and delivery
Route53
CloudFront
S3 landing
Ingress and APIs
ALB
API Gateway REST
API Gateway WS
Runtime on ECS
Studio
Agents
Intel
Squads
State and memory
Aurora / Postgres
Redis
Neo4j on EC2
Semantic ECS / EC2
Support services
SES inbound
Lambda
ECR
SSM / Secrets
In a nutshell
Turn every booking into a service and revenue channel
flyjeeves helps airlines offer faster service, better passenger continuity and more monetizable post-booking interactions, without forcing customers through fragmented support journeys.