Build · the app already in every pocket

Everyone already installed it. Now build something in it.

Messaging is the one app on every phone on earth — already open, already trusted, nothing to download and no password to forget. Listrak Converse is how you put real, working things inside it: guided ordering, returns, bookings, intake, delivery, care. Cards, carousels, buttons, photos, payments and memory — authored once, running on whichever rail the customer answers.

Start building free See what you can send

Beyond the sale

One engine, a whole concierge program.

None of these is a separate product, an integration, or another vendor. They are workflows — the same thing, authored the same way, running in the same thread your customer is already in.

●Delivery day

“Your order arrives today” — confirm, reschedule, or get doorstep photo proof without a phone call.

●Order check-in

“Where’s my order?” answered in-thread, instantly, without sending anyone to a tracking page.

●Care series

A check-in a few days in, then real answers to product questions for as long as they own the thing.

●Occasion reminders

Birthdays and anniversaries banked in conversation — reminders that convert because the customer put them there.

●Registry & gifting

Recipients, dates and tastes on file. Gifting becomes a subscription in spirit, without anyone subscribing.

●VIP drops

Early access to a new collection for your best segments — conversational, not broadcast.

●Corporate & bulk intake

Recipient lists, budgets, card messages and delivery windows — collected at scale, validated as they arrive.

●Win-back

“We’ve missed you” as a conversation — predictive picks and a real reply, not a coupon blast.

Every play is a workflow — triggered by Journey Hub, a QR code, an email link, or a keyword. Authored in hours, not quarters.

Three ways to build — same engine, same rules

However you like to work.

Headline · docs-optional

Bring your own AI

Claude, ChatGPT, Replit, Claude Code, or your own agent — connect with one URL + your key and, over MCP and the API, it can 100% control the platform. It reads the docs itself, learns your data, and builds — with validate-before-save so it builds correctly. A working rich-messaging solution in an afternoon; no GUI, no lessons, no manual.

The code way

REST API

Hundreds of endpoints, one wire format, UTC always. Forms are write endpoints; validation is identical to the Portal. An entire working pizza-shop tenant — schema, menu, five published workflows — was built by one program over this API. Zero clicks.

The point-and-click way

Visual builder

Prefer a screen? A drag-and-drop studio plus an AI Copilot draft it for you. Describe the process in plain words — or drop in a PDF — and the workflow appears, fully formed, ready to tweak and publish.

The visual builder — a workflow on the canvas: choices, splits, and loops

Before you point an AI at us

You're not sending messages. You're publishing an app.

Nearly every agent that connects here reaches for a send endpoint first, because that is what “RCS” means everywhere else. It is the one assumption worth unlearning up front. The unit of work is a workflow: the questions, the branches, the captures and the validation. You author it, you publish it, and the published workflow runs on RCS, Apple Messages for Business, WhatsApp, the mobile runner, or by voice. send_message is for a one-off notification, not for building.

1 · Learn the tenant

get_entity_dictionary, list_contexts, describe_relationships. Find out what this business already has before you model anything new.

2 · Author & validate

upsert_workflow_tree, then validate_workflow_tree. Bind a context so [[ ]] tokens reach real data.

3 · Publish & deliver

publish_workflow freezes the snapshot the runner executes. Then launch it on a channel, a link, a QR, mobile, or voice.

Stuck? docs_index maps the library, docs_search is free, and howto_search will synthesise a grounded build plan as a last resort. There are 366 tools behind your key, and playbooks of proven sequences it can follow step by step.

The /mcp handshake

One URL. Your key. Then just ask.

Listrak Converse speaks the Model Context Protocol, so any MCP-capable assistant plugs in as a native tool source. It reads the docs itself, discovers the tools your key is allowed to use, and builds — everything role-gated by that key, nothing it can't do.

# Connect any MCP-speaking AI — no SDK, no manual.
connect https://wtfapi.serviceproof.net/mcp Authorization: Bearer <your-key>

you ▸ "Learn my customer list from our Google Sheet, build a plumbing
      service-call workflow, deliver it over WhatsApp, and text me the
      proof PDF when each job closes."
ai  ▸ read_docs ✓ connect_sheet ✓ learn_context ✓ upsert_workflow_tree ✓ publish ✓ launched.

Reads the docs for you

The whole integrator library is a tool call away — your AI pulls exactly what it needs.

Validate before save

Every definition is checked the same way the Portal checks it — with “did you mean” fixes — so nothing ships broken.

Role-gated by your key

The key decides what the agent can touch; a tool it can't use returns a clear refusal, never a silent misfire.

You're never starting from scratch

Everything your AI needs is a tool call away.

Ready-to-go

Playbooks

Pre-baked, dress-rehearsed tool sequences for whole arcs — provision a tenant, model your data, author a workflow, set up dispatch, read the proof. Your AI lists them, runs them, and saves each success as a new recipe for next time.

Copy-paste safe

Example code

Real, runnable source — a whole working pizza-shop tenant built over the public API — plus request/response examples pulled straight from the passing test suite. Your agent reads the sample, then writes yours.

Docs on tap

Voluminous documentation

The entire integrator library is readable through the same connector — so your AI looks up exactly what it needs the moment it needs it, instead of guessing. Docs-optional for you; docs-fluent for it.

End to end

What building looks like.

01 · CONNECT

Bring your data

Sync from your ERP, connect a Google Sheet, drop a CSV, or push over the API. Model it fresh if you're starting clean.

02 · AUTHOR

Build the workflow

Describe it, drop a PDF, or drag it out. Context-aware steps, parallel paths, branching, loops, photos, signatures, payments.

03 · DELIVER

Publish to a phone

One tap publishes over RCS, Apple Messages for Business, or WhatsApp — plus a mobile + web fallback for the rare gap.

04 · PROVE

Read the results

Structured answers, photos, GPS, timestamps flow back — as data, a proof PDF, and a webhook to your systems.

Connect your data

From your ERP to a Google Sheet.

We meet your data where it lives and hand results back — start with a job number and a webhook, or go all the way to near-real-time two-way sync. New connectors and partnerships land every week.

Enterprise ERP / CRM / CMMS

ServiceTitan, dESCO, SAP-class — near-real-time, two-way.

On-prem SQL agent

Secure sync of your database; filters run on your side so PII never leaves.

Google Sheets

Connect a sheet; rows become live data in minutes.

Excel / CSV

Drag in a file; we map it to your model and keep it synced.

REST API + Webhooks

Push, pull, and subscribe — one wire format, UTC always.

Bring your own everything

Storage, AI key, messaging sender, database — your rails or ours.

Start free

Point your AI at us and ship this afternoon.

Spin up a free trial, connect your assistant to /mcp, and launch your first rich-messaging solution. No card, no install, no manual.

Start a free trial Connect your AI Developer portal & API docs