Kate: the engine that turns check-in calls into care actions.
Every persona in the careplans AI family is a voice companion. Kate is the coordination engine behind every careplans AI voice companion: it listens with emotional intelligence, thinks with the right model for each moment, and acts on many threads at once, while the call is still running.
Kate listens
To how a person feels, not just what they say.
Voice analysis reads tone, pitch, pace, and sentiment in real time, while the conversation stays warm and unhurried. Kate arrives knowing the whole relationship: every previous call, every preference, every concern that was ever raised. Nothing has to be repeated.
Kate thinks
With the right intelligence for each moment.
A multi-model architecture routes every moment to the right depth of reasoning: instant, natural responses while someone is speaking, and deeper clinical analysis where it matters. Each call adds to a longitudinal picture, so Kate sees trends across weeks that no single conversation could reveal.
Kate acts
On many threads at once, while the call continues.
The moment a need surfaces, Kate begins orchestrating: care record, logistics, family, and compliance move in parallel, each thread tracked to completion. By the time the goodbye is said, the work is already under way.
While Margaret is still on the phone.
One sentence about a wobbly shower chair, and four threads of work start moving in parallel. Watch the real four and a half seconds.
Sequential systems finish one task before starting the next. Kate runs the threads side by side and converges them into one outcome: ordered, funded, scheduled, documented, and the family informed.
Voice to insight to action
One sentence. Ten actions. Zero data entry.
Margaret mentions she needs a shower chair during a regular check-in. Watch what Kate does next. (Example only, subject to internal processes and procedures. Full support for human-in-the-loop via voice, SMS, email or existing authorisation processes.)
This is what "voice to insight to action" means. Mary cares. Kate acts. Margaret gets her shower chair.
Kate is the coordination engine behind every careplans AI voice companion.
Kate schedules the calls, guides the conversation, and turns what is heard into actions for your care team, making every call purposeful, every insight actionable, and every outcome measurable. Kate is the reason this is more than an AI that makes phone calls.
What Kate does on every call
- Schedules the call at the right time for each person
- Selects the right voice companion for the program (for example Mary for aged care wellbeing, or Bloom for new parents)
- Loads full context from every previous conversation
- Configures the conversational pathway with branching logic, conditions, and guard rails
- Orchestrates the conversation in real time
- Receives emotional signals so the conversation adapts to mood in real time
- Triggers mid-call API actions: check a database, book an appointment, update a CRM record, send an SMS
- All while the person is still on the line
- Transcription and recording
- Routine analysis on cost-optimised local models
- Advanced reasoning through frontier models
- Emotional analysis (tone, sentiment, mood)
- Generates WHO-5 wellbeing scores, structured JSON data, and compliance evidence
What makes Kate different
Escalation and action
Escalation alerts to the care team. Family notifications through nonni.ai. CRM updates. Webhook pushes. Compliance evidence packs. Follow-up call scheduling.
Longitudinal intelligence
Kate maintains memory across calls. It tracks wellbeing trends over weeks and months. It detects a gradual mood decline over three weeks, increasing mentions of pain, growing isolation.
Multi-model architecture
The right model for each task. Routine analysis on cost-optimised local models. Advanced reasoning through frontier models. Emotional analysis through specialised voice models. Cost-optimised without compromising accuracy.
Cross-call memory
Every voice companion remembers. Margaret mentioned her daughter last Tuesday. John has been sleeping poorly for two weeks. Context carries forward automatically.
Conversational pathways
Node-based conversation flows with branching logic, conditions, and guard rails. The AI follows the pathway. Hallucination-proof. Safe by design.
Continuous compliance
Every call maps to the relevant quality standards. Evidence generates as a byproduct of caring, not as an admin task. Always audit-ready.
96+ capabilities across 15 areas of care.
From a single conversation, the platform can check on wellbeing, raise a concern, coordinate a task and keep families informed. This is the breadth at a glance; care teams see the full toolkit once they sign in.
Want to see it for yourself?
Live demos are by appointment, walked through with Andrew. Ten minutes, real conversation, real questions.