The gap in workplace physical health

1.7 billion people worldwide suffer from musculoskeletal disorders caused by prolonged sitting (WHO). The solution—regular movement breaks—requires sustained behavior change, which existing workplace tools fail to support:

• Movement apps (Stretchy, Desk Yogi): Evidence-based exercises but no calendar awareness, requiring users to remember and interrupt work
• Calendar assistants (x.ai, Reclaim): Schedule breaks but provide no movement guidance or adaptation to physical needs
• Wellness chatbots (Headspace Bot, Calm): Generic reminders with static prompts regardless of schedule stress or context

The design challenge

Starting from zero, how do you design conversational flows for a multi-agent health coaching system that:

1. Adapt persuasion strategy based on schedule stress (meeting-heavy days need different approaches than light schedules)
2. Guide users toward active movement breaks without feeling pushy or interruptive
3. Handle multiple conversation paths (queries, scheduling, conflicts, rescheduling)
4. Maintain natural conversation across multiple turns while managing complex state
5. Apply behavioral science systematically to movement behavior change, not just "friendly tone"
6. Create reusable conversation patterns for other health coaching agents (reminders, lifestyle coaching)

Success criteria for pilot

• Agent feels "helpful, not pushy" in qualitative testing
• Multi-turn conversations complete in ≤3 turns
• Conversation flows handle edge cases gracefully (missing info, conflicts, API failures)
• 95% scheduling accuracy (no double-bookings, correct buffers)
• System ready for deployment with ~200 users at a pilot government company

Research foundation

The founding team conducted initial user research (15 interviews + surveys with 50+ desk workers) revealing key insights for conversational flow design:

• Pattern references dominate: "Like yesterday", "my usual breaks", "same as last week" appeared in 40% of conversations—users think in patterns, not discrete time slots
• Incomplete initial requests: 60% lacked time, duration, or date ("Schedule a break")—flows need progressive clarification
• Multi-turn refinement expected: Users modify suggestions conversationally ("Move the 1 PM to 2 PM") rather than starting over
• Schedule queries as entry point: Users would use the AI health coach for general schedule queries—creating an opportunity to suggest break scheduling when none exist
• Efficiency target: Scheduling should complete in ≤3 turns
• Conflict handling must be conversational: Alternatives with reasoning, not just "unavailable"

Design rationale

Mapping complete conversation paths before implementation served three purposes. First, understanding conversation patterns shaped technical architecture: what data must persist between turns (pending suggestions, conflict alternatives, conversation context), how agents communicate decisions to the coordinator (structured outputs), and which calendar operations were needed. Second, each decision node in the flows revealed edge cases that became test scenarios directly. Third, could demonstrate conversation paths to the founding team using mockups before implementation.