Now onboarding

Your SLA. Your API docs.
The system builds the flows.
You approve. It runs.

Upload your contracts and your booking system's API request/response samples. The system reads both, generates operational call flows autonomously, presents them for your approval, and executes them across voice and email — tied to one case per booking.

Flow gen< 1hr
Latency450ms
UnifiedCall + Email
The gap in travel AI

Most travel AI is a chatbot that deflects tickets.

It answers FAQ. It opens a ticket. It hands off to a human for anything real. It does not read your contracts. It does not know your fare rules. It does not touch your booking system.

Chatbot

Answers FAQ. Deflects tickets. No operational logic.

Not us

Does not read your SLA. Does not touch your booking system.

What we are

An operations layer that runs your contact center.

The system reads your SLA and your API docs, generates operational flows autonomously, and executes them across voice and email — with every interaction tied to one case per booking.

Autonomous flow generation

Reads your SLA + API docs. Builds operational logic without human coding.

Unified case management

Voice, email, and API data — one case per booking, not per channel.

Voice execution

Handles schedule changes, rebooking, refunds, retention — live on calls.

Email execution

Same flows as voice. Inbound email to outbound reply, end-to-end.

How it works

From contract to live call. Autonomously.

01

Upload

Your SLA and your API request/response samples. The system consumes both inputs simultaneously.

02

Generate

The system autonomously bridges contract clauses to API calls — building operational flows without manual coding.

03

Approve

Review every generated flow. Accept, reject, or modify. Your approval gates what goes live.

04

Execute

Approved flows become live rules. The agent handles voice calls and email — one case per booking.

The system does not use templates. It reads your actual SLA and your actual API docs, then generates flows specific to your operational logic. When your contracts change, the diff is auditable.

Unified operations

One case per booking. Voice + email + API data.

Every interaction about the same PNR lives in one case. The agent sees the full history — regardless of channel.

VOICE+44 20 7946 0381
14:02
Inbound call · LHR → NRT delayed
PNR XK7-92F · locale: ja
14:06
Schedule change quoted · BA0007 → BA0009
flow: schedule_change_v3 · API: /rebook called
14:09
Caller wants confirmation by email
handoff requested · case remains open
case2026-04-9214
passengerK. Yamamoto
bookingPNR XK7-92F
channels
VOICEEMAIL
api calls/rebook · /confirm
flowschedule_change_v3
statein progress
audit · 11 events · 2 channels · 2 API calls
EMAILk.yamamoto@example.jp
14:11
Inbound · "please confirm in writing"
matched on PNR + phone · same case
14:11
Reply drafted with rebooking context
locale: ja · flow: schedule_change_v3
14:12
Sent · linked to case 2026-04-9214
no new ticket · same audit trail
Matcher: PNR + phone + email + recent case window
When in doubt, asks for confirmation digit — never silently merges
Operations console

One pane for every call. Every email. Every API call.

app.travelcalls.ai / ops
meridian-travelLIVE
Active calls live
Voice trafficconcurrency · per tenant
Email replies24h
Auto-sentdrafted from clauses · queue: none
Cross-channelopen
Voice → emailsame case-id · auto-linked
Latency · p50measured
450ms
production · last 24h
Live activitylast 15 minutes
  • VOICE
    Schedule change · LHR → NRT · PNR XK7-92F
    case 2026-04-9214 · locale: ja · flow: schedule_change_v3 · API: /rebook
    in progress02:34
  • EMAIL
    Refund request · booking BR-44188
    case 2026-04-9213 · auto-replied · clause matched · API: /refund
    review00:38
  • VOICE
    Cancellation · PNR ZQ2-118
    case 2026-04-9201 · flow: cancellation_v2 · 30% retention · API: /cancel
    resolved04:12
  • EMAIL
    Itinerary confirmation · BR-44102
    case 2026-04-9198 · auto-sent · locale: de · API: /confirm
    resolved00:04
  • VOICE
    Group booking modification · PNR HM4-771
    case 2026-04-9192 · escalated · API: /modify queued
    escalated06:48

Latency is the only number a buyer can hold us to. The rest tells you what the console tracks.

Performance

Reproducible on the demo call.

Not roadmap. What you can measure today on our production stack.

Flow generation
< 1hr

SLA + API docs → operational flows

Email reply
< 1min

Inbound to outbound. Same flow as voice.

Voice latency
450ms

p50. Human pause is 200-500ms.

Languages
9

Detected at call open. Switched mid-turn.

Dogfooded before it reaches you

  • FlexoTripsvoice + emailOur metasearch travel agency — real bookings, real ops load.
  • AiOrchemail onlyThe multi-agent code orchestrator we use to ship TravelCalls.ai itself.
Languages

Detect the language. Route the call. Hand off mid-turn.

Each call opens with detection. When confidence crosses threshold, the agent re-binds to that locale — without restarting. Email inherits inbound language.

Contact

Send us your SLA and your API docs.
We generate flows in under an hour.

Email the contract and a sample API request/response from your booking system. The system reads both, drafts the operational flows, and surfaces them on a 30-minute call — together we review what it generated, what it got wrong, and what to harden before going live.

The same upload-and-walkthrough becomes your production onboarding. Nothing is staged for the demo.

Email us your SLA + API docsBook 30 minutes
info@travelcalls.ai·one working day