Journey and history
One timeline per user: messages, alerts, triggers and takeovers.
The journey endpoint returns everything that concerned one user in time order, from their messages to safety events, proactive triggers and experiment assignments. Conversation history can be read or cleared per user.
Journey · user_42
- 09:12message
“honestly I don’t know why I keep trying”
- 09:12safety.flagged
risk elevated · flags: self_harm
- 09:13takeover.started
Operator joined the conversation
- 09:41takeover.released
Handed back to the AI
- Next dayproactive.mood_drop
Suggested: an empathetic check-in
The view you open when something went wrong
When a user is flagged, the first question is what happened before. The journey gathers that user's messages, safety and proactive events, webhook deliveries and experiment assignments into one ordered list, fetched in a single query.
- Messages and assistant replies
- Safety events and proactive triggers
- Experiment assignments that affected the user
- Webhook deliveries that mention the user
Alerts · live
- safety.flaggedcriticaluser_88 · flags: self_harm→ Webhook · Slack
- safety.holdholduser_42 · reply held for review→ Webhook
- anomaly.detectedwarninguser_17 · engagement_drop→ Webhook
- proactive.mood_droptriggeruser_05 · mood below 0.30→ Discord
Fetch a history or a journey
history = client.get_history("user_42", limit=50) # [{role, content, timestamp}]
# The journey endpoint is REST today
import requests
journey = requests.get(
API + "/sdk/journey/user_42",
headers={"X-API-Key": os.environ["HUMANE_API_KEY"]},
).json()
client.clear_history("user_42") # when a user starts overEndpoints
- GET /api/sdk/journey/{user_id}
- GET /api/sdk/history/{user_id}
- DELETE /api/sdk/history/{user_id}
- All scoped to the tenant that owns the API key
Works well with
Durable memory
Every turn is stored in a per-tenant vector memory, searchable by meaning. Seed it from your other systems, search it from your own code and erase it when a user asks to be forgotten.
ExploreAudit trail
Humane records gate outcomes, safety flags, webhook deliveries, engine decisions and admin actions, each with its reason. When someone asks why the AI did something, you can show them.
ExploreHuman takeover
When the signals say someone needs a person, an operator opens a takeover for that user. The AI pauses, the operator's messages reach the user in the same conversation, and the AI resumes when the operator releases it or goes idle.
ExploreEvery AI should know who it's talking to.
The safety and human-oversight layer for emotional AI: user state across sessions, risk alerts, safety gates and human takeover, with every decision explained.
