A personal AI for neurodiverse families.
Learns your child, grows with them, works 24/7.

Track behaviour. Find services. Surface research. Connect with similar parents. All from one chat that knows your child by name — every meltdown, milestone, trigger, and routine.

Now in private beta with design-partner families · waitlist open

Safety-first · Grounded · Always on · v2.3 shipped 326 tests green 20 capabilities Private beta · waitlist open
Meet your AI

The AI does the homework.
You stay the parent.

It learns your child the way you do — over time, from every meltdown, milestone, and 2am question — then quietly does the reading, searching, and matching so you don't have to.

Reads the research so you don't have to

Turns dense studies into “what does this mean for my child?” Tier-ranked, freshness-gated, plain English.

Finds the videos and articles that actually fit

Curated for your child's age, diagnosis, and sensory profile. Not generic “autism content” — content for your family.

Matches you to services that worked for similar kids

Recommends therapists, programs, and groups based on outcomes from families with children like yours.

Learns as your child grows

What helps at 4 won't be what helps at 8. The AI adapts as your child develops and new patterns emerge.

Realistic AI — not futuristic hype. Grounded in real behavioural data, provider expertise, and outcomes from families navigating similar journeys.

The problem

Parents are the frontline clinicians of their child's life.
Here's what we actually fix for them.

Can't find the right services

Local resource directory

Crowdsourced therapy centres, schools, and support groups. Auto-verified after 2 parent submissions.

Can't track behaviour

Meltdown pattern tracking

4-step intake (time → place → trigger → resolution) auto-logs every incident.

Don't know causes of behaviour

Trigger analysis

After 3+ entries, the AI finds time-of-day, location, and sensory clusters in your data.

No time to read research

Personalised daily digest

Live-web sources, tier-ranked, freshness-gated, tailored to your child's age, therapies, and sensory profile.

Can't find the right videos / insights

Tier-ranked content publishing

Bot agents publish news + research filtered through quality, freshness, and grounding gates. No filler.

No guidance from similar parents

Parent-to-parent matching

Weighted on age, challenges, therapies, level. Opt-in, mutual-consent intros, first names only.

Can't track long-term progress

Monthly progress reports

Weekly capture → monthly markdown report you can share with therapists, insurance, or IEP teams.

How it works

Three steps. Then your AI grows with your family.

  1. 1

    Build your child's profile

    Seven short questions — name, age, diagnosis, therapies, challenges, strengths, goals. About five minutes. You can update it any time.

  2. 2

    Your AI learns continuously

    Every milestone, meltdown, insight, and question is logged automatically. Your agent builds a real picture of your child over weeks and months.

  3. 3

    Support, any time

    24/7 grounded chat, daily check-ins, a Sunday behaviour digest, IEP prep briefs, and crisis hotlines one tap away if things escalate.

Agent capabilities

Twenty skills. One conversation.

Every capability is exposed through natural-language chat — you never learn a command syntax. Routing is keyword-first for safety-critical paths, with an LLM fallback when intent is ambiguous.

Crisis detection, three tiers

Tier 3 suicidal language triggers hardcoded hotlines (988, 741741) with zero LLM in the path. Safety over optimization.

24/7 grounded chat

Replies use child profile + last 15 memories + 20 messages of history. Never a generic template.

Meltdown pattern tracking

4-step follow-up — time → location → trigger → resolution. LLM pattern analysis after 3+ entries.

Proactive check-ins

Daily "how is Alex doing?" messages — milestone celebrations auto-detected from memory.

Weekly behaviour reports

Sunday digest of patterns, wins, and one actionable suggestion. Grounded in 7-day memory logs.

Personalized daily digest

Live-web news filtered by tier and freshness, tailored to age + therapies + sensory profile.

Parent-to-parent matching

Weighted on age (30%) / challenges (35%) / therapies (25%) / level (10%). Opt-in, mutual-consent intro.

Anonymous community Q&A

Low-confidence AI answers trigger "ask the community?" — posts anonymously, relays answers back.

Natural-language reminders

"Remind me about OT at 4pm weekdays" — AI parses time + days, fires every 5 min.

IEP / therapy prep v2.3

30-day brief: wins, challenges, patterns, questions to ask. Grounded in real memories, zero fabrication.

Sensory profile builder v2.3

3-question intake. Triggers + calming supports feed every downstream prompt — digest, tips, IEP.

Monthly progress reports v2.3

Weekly capture via chat → monthly markdown report shareable with therapists, insurance, IEP teams.

Local resource directory v2.3

Crowdsourced therapy centers / schools / support groups. Auto-verified after 2 parent submissions.

Sibling & family support v2.3

Register siblings, get family-activity ideas respecting sensory profile, biweekly sibling-dynamics tips.

Post monitoring & alerts

Agents comment on community posts and alert relevant parents — "this mentions ABA, might help you."

Content publishing bots

Dedicated bots publish news + research blogs through tier, freshness, and grounding gates.

Onboarding state machine

7-step profile collection — name, age, diagnosis, therapies, challenges, strengths, goals.

Memory & milestone recall

Every meaningful detail saved as typed memory (milestone / behaviour / insight / question), surfaced in every reply.

Profile completeness nudges

Daily scheduled + every-5th-message chat nudges to fill missing profile fields, without being pushy.

Help & capability listing

"What can you do?" returns a warm, tailored list using your child's name. Never a command menu.

Inside the intelligence

It's not a chatbot.
It's a system.

Four deliberate design choices make this feel different from a generic LLM wrapper. Each one compounds into a product your family can actually rely on.

01 · Memory

It remembers every detail.

Every meltdown, milestone, insight, and question is saved as a typed memory. On every reply, the agent loads the last 15 memories and 20 messages, plus your child's profile — so it speaks in continuity, not in isolated sessions.

02 · Reasoning

Patterns emerge after just 3 entries.

Report a meltdown and the agent runs a four-step structured intake — time, place, trigger, resolution. After three entries, an LLM analyses the 60-day window for time-of-day, location, and trigger patterns, and returns recommendations grounded in your actual data.

03 · Crisis safety

Tier 3 messages never touch an LLM.

A deterministic keyword scan runs before any AI call. Tier 3 language ("want to die", "kill myself") triggers a hardcoded response with 988 and Crisis Text Line 741741. Model hallucination rates are acceptable for "draft an email." Not for "I want to die."

04 · Grounding

Every brief cites your real data.

Ask for an IEP prep brief and the agent pulls 30 days of meltdowns + memories, builds a SOURCE_DATA block, and runs a grounding prompt that forbids invented stats, dates, or quotes. A second LLM pass fact-checks against the source. If something can't be supported, we skip it — we don't fabricate.

20skills
15scheduled jobs
24DB tables
30+grounded prompts
10+5poll · reply workers
50call circuit breaker
Why this is safe

Four design pillars we won't compromise on.

01

Crisis safety is non-negotiable

Tier 3 suicidal messages route through a hardcoded keyword scan that bypasses every LLM. Hallucination rates are acceptable for "draft an email". Not for "I want to die."

02

Grounded, never fabricated

Every IEP brief, blog rewrite, and progress report includes a SOURCE_EXCERPT block and strict rules: do not invent statistics, dates, quotes, or events. A second LLM pass fact-checks the draft.

03

Live-web, one backend, quality gated

Perplexity is the sole research backend — no RSS, no pre-selected URLs. Everything routes through one pipeline: circuit breaker, freshness, domain tier, URL reachability, persistent dedup.

04

No filler, no fake fallbacks

When Perplexity is down, we skip the digest rather than send hardcoded tips. When no real events exist, the event bot stays silent. Silence over slop — parents notice either way.

Engineering

Built. Tested. Ready for families.

v2.3 has shipped. We're in private beta and opening to families on the waitlist in waves.

v2.3
platform shipped
326
tests, all green
20
capabilities
24/7
always-on

Last 30 days: six commits landed the full v2.3 roadmap — Sensory Profile Builder, IEP Prep, Monthly Progress Reports, Local Resource Directory, Sibling Support — plus a content-quality overhaul that replaced the entire RSS pipeline with a single Perplexity-backed, grounded, tier-ranked backend. Test coverage grew 171 → 326.

Frequently asked

Questions we've heard from other parents.

Is my child's data private?
Every family's data is isolated. Only you — and any admins you explicitly grant access to — can see your child's profile, memories, and reports. We never share, sell, or train external models on your data.
How is this different from ChatGPT?
ChatGPT forgets you between sessions. Your AutismCare AI agent remembers your child by name, tracks every meltdown pattern, builds a picture over months and years, and roots every reply in your child's actual profile — not a generic autism template.
What if my child has a crisis?
Tier 3 crisis language triggers a hardcoded keyword scan that bypasses every AI and surfaces real hotlines — 988 Suicide & Crisis Lifeline, Crisis Text Line 741741 — immediately. This is a safety property, not a feature; it works even if the AI is offline.
What ages does this support?
Any age where a parent or caregiver is the primary advocate — toddlers through teens through young adults. The agent adapts tone and suggestions based on your child's age, diagnosis level, and sensory profile.
Co-parents, grandparents, siblings?
Yes. Register siblings to get family-activity suggestions that respect your child's sensory profile, and share your child's profile with co-parents or grandparents so everyone has the same picture.
What does it cost?
We're in early-access. Pricing will be announced soon. Families who join today get grandfathered pricing when paid tiers launch.
Is it HIPAA-compliant?
Not yet — HIPAA compliance (with a BAA-eligible LLM provider) is on the near-term roadmap. Until it ships, treat the platform like any consumer app: don't share information you wouldn't share with a close friend over text.
Can my therapist or school see the reports?
Only at your discretion. Every monthly progress report is a shareable markdown document you can send to therapists, insurance, IEP teams, or schools. Nothing is shared without your explicit action.

Be among the first families
on AutismCare AI.

We're opening the platform to families on the waitlist in waves. Free while we're in early access.

By creating an account you agree to our Terms and Privacy Policy.