Autonomy Support for Neurodivergent Lives
Event-driven decision automation for complex support needs. Processes 24,000+ annual events—support worker messages, medication alerts, behavioural observations—through policy-based automation that augments human judgment without replacing it.
Named for my son Axel. Built because he deserves technology that preserves his autonomy.
The Problem
People with complex neurodevelopmental and physical support needs generate thousands of daily decisions. Support worker messages, medication scheduling, meal choices, appointment coordination, behavioural observations.
For family coordinators, this creates an impossible cognitive load. For the person themselves, the system often optimises for carer convenience rather than their actual preferences.
The insight: What if we could automate routine decisions while actively protecting the person's expressed preferences from being overridden by support workers?
Core Principles
Non-negotiable commitments that guide every design decision.
Augment, Never Replace
The system augments human judgment—it never replaces it. Every automated decision can be overridden. Complex or novel situations always escalate to a human.
Expressed Preferences First
The person's expressed preferences are the primary signal. Not what support workers think they want. Not what historical patterns suggest. What they actually indicate they want.
Graduated Autonomy
The system earns direct-send authority through consecutive human approvals. Autonomy is granted incrementally based on demonstrated accuracy, not all-or-nothing.
Power-Check Safeguard
Continuous monitoring detects when support workers' preferences override the person's actual choices. Flags capacity changes, worker anomalies, and pattern deviations.
Event Processing
24,000+ events per year, each routed through classification, pattern matching, policy application, and confidence evaluation.
| Event Type | Annual Volume | Automation Level |
|---|---|---|
| Support Worker Messages | ~8,000/year | |
| Medication Alerts | ~2,500/year | |
| Meal Choice Decisions | ~4,000/year | |
| Behavioural Observations | ~3,500/year | |
| Health Changes | ~1,500/year | |
| Schedule Coordination | ~4,500/year |
The Guardian Layer
Continuous cross-stream analytics that protect autonomy and catch problems early.
Worker Quality Monitoring
Flags anomalies in support worker behaviour, communication patterns, and response quality.
Degradation Tracking
Detects changes in the person's capacity, health indicators, or behavioural patterns over time.
Episode Identification
Clusters related behavioural incidents to identify triggers, patterns, and effective interventions.
Preference Drift Detection
Notices when recorded preferences start diverging from expressed choices—a signal of external influence.
Dialectica Integration
Two-role model: offline policy generation and on-demand complex analysis.
Role A: Policy Generation
For novel decision categories, runs Dialectica to determine: "Should this type of decision be automated?" Considers multiple perspectives—accessibility, care ethics, legal constraints, practical effectiveness—and outputs an automation policy.
Example: Meal choices: automatable at 0.7 threshold. Dietary constraints are hard rules. New foods escalate first time.
Role B: Complex Analysis
When routine policies can't resolve a decision, routes to Dialectica for multi-perspective analysis. Used for conflicting professional advice, ethical dilemmas, and novel situations.
Example: Two specialists recommend conflicting treatments. Present all framework perspectives without prescribing a single answer.
System Architecture
AxelV1 is built on the Savanax event-driven platform. Explore the full architecture—click on any node for details, and use the flow buttons to trace events through the system.
Why This Matters
My son Axel has complex communication needs. The support system around him is extensive—multiple workers, therapists, medical appointments, medication schedules.
Without technology that actively preserves his preferences, the system optimises for carer convenience. His choices get averaged out. His autonomy erodes through a thousand small decisions made without his input.
AxelV1 exists because everyone deserves technology that amplifies their voice, not silences it.
Technical Architecture
Interested in Autonomy-Preserving Systems?
Whether you're building for disability support, aged care, or any domain where automation must preserve human agency, I'd love to discuss the architecture.