Glossary

AI Coach

Updated February 28, 2026

AI Coach gives data-aware coaching for habits, calories, and macro execution. It helps you move from plans to behavior without replacing clinical care.

Core architecture

Adaptive learning in the coach uses behavior inputs, target constraints, and continuity checks to recommend small, reviewable updates.

Onboarding personas

AI onboarding starts by matching prompt depth and safety defaults to your profile. The same knowledge base is used, but the starting friction budget changes.

PersonaStarting objectiveOnboarding emphasisTypical early risk
BeginnerBuild sustainable habits and consistencySimpler daily plan, clear defaults, and daily check-insAll-or-none behavior and over-worrying about meal perfection
Experienced athleteMatch training cycles, recovery, and body trend goalsPerformance context, stronger periodization language, and tighter feedback cadenceIgnoring fatigue signals while chasing numbers
Parent on shift workProtect consistency around changing schedulesQuick planning mode, compressed logs, and late-day recovery cuesMissed sessions and delayed food logging during variable shifts

Required input fields

The model does not improvise without a minimum set of data. Required fields are validated before guidance changes.

Field typeWhat is requiredCoaching purpose
Basic profileage, sex, height, weight, activity baselineBaseline energy and recovery context
Objectivefat loss, maintenance, performance, recompositionPrioritization and expected weekly movement
Logging setupfood journal source, snack frequency, scale timingSignal quality and error correction
Recovery and health flagssleep trend, known stressors, persistent symptomsGuardrails for pause and escalation
Constraintsschedule, food preferences, kitchen limits, budgetFeasible recommendations

Capability boundaries

AI Coach is designed for nutrition coaching and coaching communication, not medical diagnosis.

IncludedExcludedUser action
Energy and macro planning, meal structure, adherence strategyMedical diagnosis, medication changes, treatment planningSeek licensed clinician support when symptoms require care
Recovery-aware pacing advice, plan revision prompts, habit shapingLab interpretation as standalone diagnosisUse clinician and your lab team for formal interpretation
Behavioral coaching for cravings, meal timing, and consistencyEmergency triage for severe acute symptomsFollow emergency local care instructions immediately

Failure modes and controls

Failure modeWhy it occursControl response
Model driftchanging routines create stale assumptionsincrease uncertainty penalty, widen adaptation window
Contradictory guidancemanual edits conflict with automated recommendationssurface one source of truth and ask user to reconcile
Unsafe urgencyrapid, high-intensity recommendation pressure from noisy signalsthrottle output, ask for confirmation, and reduce recommendation magnitude
Over-specific advicesparse context and narrow assumptionsrequest missing fields before final suggestions

Escalation triggers and guardrails

Escalation begins when signals indicate the model cannot safely steer behavior alone.

Trigger patternSystem reactionUser-facing message
Repeated contradictory corrections in three consecutive blockslock further automated changes and request explicit confirmation"Stability mode: confirm your priorities and data quality first"
Medical keyword clusters such as severe dizziness, chest pain, fainting, suicidal intent, or sustained nauseaimmediate pause and care guidance prompt"Seek clinical support now"
Persistent adverse symptoms for 72 hours with poor adherenceshift to safe-maintenance mode and reduce adaptation speed"Temporarily prioritize recovery and hydration"
Missing data for critical fields for 48 hoursrequest re-collection before any major change"Add data for accurate adaptation"

Privacy and retention in plain language

The coach stores session logs, intake context, and outcome notes to keep continuity across days, and applies the retention rules in Privacy and Data. In practical terms:

Log typeWhy it is keptControl option
Conversation historykeep coaching continuity and explain recommendationsdelete specific records when available
Nutrition and body dataimprove trend quality and reduce guessworkpause logs if you want strict local-only mode
Device and timing signalscalibrate recommendations to real-world routinereview connected integrations anytime

For sensitive topics, AI Coach applies higher friction: explicit prompts, confirmation gates, and pause-first behavior.

The product goal is clarity over convenience, so you are nudged to ask for evidence, cite your symptoms, and choose whether to continue auto-adaptation.

Use AI-driven coaching for onboarding flow and coach chat for escalation language, then return here for capability boundaries.

Related

Adaptive Learning

Adaptive Learning updates recommendations as new behavioral and physiologic signals arrive, then recalibrates output to reduce the gap between expected and observed outcomes.

Progress Visualization

Progress Visualization turns logs into charts so you can act with confidence.

Meal Suggestions

Meal suggestions combine remaining macros, timing, and schedule reality to keep choices practical.