Our Platform

Many patient engagements. One agentic platform.

Our current product offerings aren't separate codebases. They're configurations of the same voice-agent runtime. WellSaid's platform defines what the agent can do; member context determines what it does next — so launching a new experience is configuration, not engineering.

New experiences without new codeResponses in near-human timeEvery session makes the next one better

Configure

Platform blueprint

Agents, workflows, modules, scripts, templates, and tool contracts.

Compose

Agentic worker

Speech, reasoning, approved tools, and routing composed per member.

Connect

Real-time responses

Streaming voice, bi-directional views, commands, and events.

Present

Edge

Native interactive UI, speech synthesis, and avatar animation.

Why the platform compounds

Three architectural choices that change the economics.

Each one was a technical decision. Each one changes how the company scales — what it costs to add an experience, what it costs to hold a conversation, and how hard we are to replace.

01

Leverage

Configure, don't build

Orchestration, instructions, tool contracts, and UI views are authored as content rather than written in code. New modules, experiences, and personas ship as configuration, so engineering cost does not scale with how many experiences we run.

02

Margin

Send meaning, not pixels

No dynamically generated avatar video crosses the media stream. The backend sends compact speech markup and structured UI data; the edge renders the audio and the animation.

03

Moat

Context compounds

Every session leaves durable context — answers, goals, preferences, progress, results. The experience does not reset, so the longer a member stays, the harder the platform is to swap out.

Inside a session

How one conversation actually runs.

The edge and the agent worker are peers in the same real-time room. Media travels over WebRTC; application commands and rendered view payloads travel over RPC. There is no direct edge-to-worker HTTP call.

Edge

1

Authenticate and join

Identity provider login and a signed first-party API session. A token service mints a room-scoped access token.

4

Member input

Microphone over WebRTC. Buttons, forms, and games over command RPC. Typed responses, push-to-talk, chat, pause, and resume.

9

Render and speak

The template renderer selects the UI. Neural speech synthesis returns audio, visemes, word timing, and bookmarks for avatar lip-sync.

Real-time transport

2

Real-time room

Signaling plus WebRTC media, with participant identity bound to a verified member email.

5

Room traffic

Up: encoded audio and UI commands. Down: view and client-event RPC. Every event resets the idle timeout.

8

Structured response

A view RPC carries template, speech, and content. Speech mirrors into transcript history; server-side audio output stays off.

Agent worker

3

Worker joins

A containerized worker joins the session. The router loads member and experience context, then selects the dialog, dynamic, demo, scripted, or free-form mode.

6

Voice intelligence

Streaming speech recognition, voice activity detection with tuned endpointing, a configurable language model, and preemptive generation.

7

Orchestration and tools

CMS-driven prompts and workflows, with tools for navigation, goals, meals, assessments, exercise, shopping, and games. State survives agent transfers.

Session end

The session layer records audio, transcript, traces, and logs. The worker uploads audio, reports, and vocal biomarker windows to object storage.

Functional technology stack

Four layers, cleanly separated.

Responsibilities are split so each layer can change independently — the edge owns presentation, the real-time core owns the boundary, the worker owns reasoning, and the platform owns durable state.

Closest to the member

1

Edge

Owns presentation

  • Server-rendered web application with a component-based UI
  • Real-time room client and WebRTC media handling
  • Identity provider integration plus signed API sessions
  • Neural speech synthesis with visemes and word timing
  • Animated avatar renderer, design system, and cached speech
  • Product analytics and tag management
WebRTC media · RPC for views, commands, and events
2

Real-time core

Owns the boundary

  • Room service with participant identity bound to a verified user
  • WebRTC microphone and optional media tracks
  • Bidirectional RPC for views, commands, and client events
  • Data channel plus chat and transcription events
  • Room-scoped access token minted by the web API
  • No custom socket protocol and no direct edge-to-worker HTTP
The agent worker joins the room as a peer participant
3

Backend AI pipeline

Owns reasoning

  • Containerized agent session framework
  • Streaming speech recognition with optional per-agent override
  • Voice activity detection, eager endpointing, and preemptive generation
  • Configurable language model with agent- and task-specific choices
  • Function tools assembled from CMS configuration
Authenticated API calls · CMS configuration
4

Platform and data

Owns durable state

  • Application API for users, content, meals, preferences, and reporting
  • CMS for agents, workflows, modules, scripts, templates, and tool schemas
  • Weather API and a media content delivery network
  • Cloud container runtime, image registry, logs, and object storage
  • Absolute and idle session timeout management

System of record

Where speech is owned

Text-to-speech is an edge responsibility. The backend disables real-time room audio output and sends speech text through the view RPC, so the edge can synchronize speech with the animated avatar.

Functional architecture only. Vendor and product names are intentionally omitted; specific providers remain implementation choices.

Already in production

This is shipped surface area, not roadmap.

The breadth below is running today across both experiences — which is why launching a new one is a configuration exercise rather than a build.

Voice experience

Low-latency recognition, endpointing, preemptive generation, push-to-talk, typed input, pause and resume, and mobile audio unlock.

Avatar

Animation synchronized to speech visemes, word boundaries, markup bookmarks, speech rate, and optional sentiment.

Adaptive content

The router chooses demo, scripted, dialog, dynamic, workflow, subscription-expired, or evergreen experiences from member and CMS state.

Wellness programs

Check-ins, assessments, nutrition and activity goals, exercises, meals, meal plans, cookbook, shopping lists, and brain games.

Multimodal UI

The backend sends named templates, images, video, forms, timers, spotlight content, and navigation state through the view RPC.

Persistence

Profiles, completed assessments, session time, answers, preferences, goals, game scores, and progress through each experience.

Vocal biomarkers

Timed or hold-to-talk windows switch turn detection to manual, capture speech segments, and annotate the full-session recording.

Reliability

RPC retry, shared HTTP session, fallback routing, holding messages, token refresh, room timeouts, and graceful reporting failures.

Observability

The session layer records audio, transcript, traces, and logs. Object storage archives artifacts; centralized logs and analytics cover usage.

Why this wins

Two experiences today. Room for many more.

01

Leverage

New experiences are configuration. Engineering cost does not scale with how many we run.

02

Margin

Speech and animation render at the edge. Conversation cost does not scale with generated video.

03

Moat

Durable member context compounds. The longer someone stays, the harder we are to replace.

The platform is the product. The experiences are configuration.