The Bourne AI demo gallery shows the embed SDK in action across nine industry applications. Each uses a real agent and a real guided-task or coaching flow. Use these as starting templates when building your own embed.
Reference Implementations
The demos cover two interaction modes and two transport configurations:
- Guided steps — the agent walks the worker through a numbered plan, advancing step by step.
- Immediate feedback — the agent watches continuously and offers coaching tips on a regular interval without a fixed plan.
- Video + voice — the worker's camera is published so the agent can observe their environment or technique.
- Voice only — the agent listens and responds without a video feed.
FAIRWAY/AI — Golf Swing Coaching
- Mode: video + voice
- Interaction: guided steps
- Shows: video transport with rear camera, step-by-step swing coaching, plan state machine advancing through setup, backswing, and follow-through phases.
Baseline — Tennis Technique Coaching
- Mode: video + voice
- Interaction: guided steps
- Shows: video transport, multi-step technique coaching from ready position through stroke completion, glanceable overlay for real-time form cues.
Diamond Mechanics — Baseball Mechanics
- Mode: video + voice
- Interaction: guided steps
- Shows: video transport, pitch and swing mechanics broken into discrete plan steps, agent advancing the worker through each mechanical checkpoint.
Restora — Rehabilitation Exercise Guidance
- Mode: video + voice
- Interaction: guided steps
- Shows: video transport, exercise procedure guidance with visual confirmation at each step, safe-range feedback via glanceable overlay.
REPSET — Form Check Coaching
- Mode: voice only
- Interaction: immediate feedback
- Shows: coaching mode without a video feed, auto-interval feedback on a configurable timer, glanceable overlays delivering short-form cues between feedback cycles.
Handyman — Home Repair Task Guidance
- Mode: voice only
- Interaction: guided steps
- Shows: voice-only guided steps for trades tasks, knowledge base lookup surfacing relevant instructions or specs mid-task,
onKnowledgesources panel.
Cadence — Presentation Coaching
- Mode: video + voice
- Interaction: guided steps
- Shows: front camera observation combined with guided presentation coaching, agent observing the speaker's posture and delivery across structured plan steps.
Tend — Care Procedure Guidance
- Mode: video + voice
- Interaction: guided steps
- Shows: care procedure guidance with visual confirmation at each step, agent using the video feed to verify correct technique before allowing the worker to advance.
Counsel — Evidence Documentation
- Mode: video + voice
- Interaction: guided steps
- Shows: evidence capture workflow with guided documentation steps, agent directing the worker to photograph specific items and confirm capture before moving forward.
Source files for each demo are available through the Bourne AI demo gallery (contact your account team for access) and make good starting points when building industry-specific embeds. Each page is a self-contained component that wires createSession, attachVoice, attachVideo, and the plan state machine together in a single file.
Next Steps
- API & SDK Overview — Package map and architecture overview
- Getting a Session Credential — Backend token endpoint and
createSession()