AI receptionists and lead follow up
Missed call text back, appointment booking, and instant lead response for service businesses, so inquiries at 9 PM become customers instead of voicemails.
01 / Why Private
This is what private AI actually looks like.
Not a thin wrapper around someone else's API. A complete platform: models, gateway, auth, billing, and monitoring, running on hardware you can physically point at.
Cloud API calls made by this platform: 0
02 / The Platform
Everything a real AI product needs, running in production.
Most "AI consultants" resell someone else's API. I built the whole thing. When I build for you, I know every layer because I've operated every layer.
Client requestHTTPS
Secure edge tunnelZERO OPEN PORTS · TLS
API gatewayOPENAI COMPATIBLE · AUTH · METERING
Llama 3.1 70B+ DEEPSEEK R1
Qwen 3.8 Flash Next100 GB+ · MTP
Qwen 3.8 27B+ UNCENSORED
Apple Silicon · 128GB unified memoryM SERIES GPU · ZERO CLOUD
fig. 01 · request path, edge to silicon · live simulation
- Inference
Six open models, locally served
The Qwen 3.8 family (Flash Next at 100 GB+, the 27B, and an uncensored 27B), Llama 3.1 70B, and DeepSeek R1 on Apple Silicon, plus embeddings for search. Multi token prediction keeps responses fast.
- API layer
OpenAI compatible gateway
A unified API in front of every model. Anything built for OpenAI works against private infrastructure with one URL change.
- Accounts
Auth & usage dashboards
Email code login, per user token tracking, and live usage dashboards backed by a production database.
- Billing
Stripe subscriptions & metering
Plan based token limits, webhooks, and automated provisioning: the full path from checkout to working API key.
- Security
Hardened, tunneled, monitored
Zero open ports to the public internet, locked down CORS, security headers, secrets out of source.
- Operations
Self healing services
Every component runs as a managed service that survives reboots and restarts itself. Built to run unattended.
03 / What I Build
AI systems for businesses that do real work.
From the first missed call to a full product: these are the systems I build and operate for businesses.
Private AI assistants
Internal chat and document assistants running on dedicated hardware, for businesses that want AI without sending customer data to a third party cloud.
Automation and integration
Connecting AI to the tools you already use: CRMs, calendars, payment systems, email. Webhooks and APIs that just work.
Full product builds
Auth, billing, dashboards, and deployment: the same production stack this platform runs on, built for your idea.
04 / About the Builder
Ty Dale, self taught builder.
I learn by building, and I run what I build: this platform, a home media server, and a personal AI agent that studies every night. I've shipped an app to the App Store, I'm finishing a picture book app for kids, and I build premium websites for local businesses. I'm not a classically trained engineer, and that's the point: I build with modern AI tools the way your business will actually use them.
01
Local AI Systems
Open weight language models served privately on Apple Silicon, with no cloud bill.
02
AI Video Pipelines
Script to scheduled post with no hands on the timeline in between.
03
Home Infrastructure
A self hosted media and photo server, a whole home ad blocker, and secure remote access, all keeping itself running.
04
iOS Development
Native apps with in app purchases, taken all the way through App Store review.
05
Website Development
Premium custom websites for local businesses, designed, built, and deployed by hand, like this one.
04 / Selected Work
Things I've built for myself first.
Keep scrolling →
01
Perika
A perimenopause and HRT tracker that shows whether a treatment change is actually working.
Jarvis online
Good morning. Night study finished: skills sharpened, notes filed in the vault.
What's on my calendar today?
02
Jarvis
My personal AI agent on Telegram. It runs on my own Mac, studies every night, and sharpens its own skills.
M5 Max128 GB unified memory
Qwen 3.8 Flash Next100 GB+ · MTP
Qwen 3.8 27BJarvis brain
ModernBERT embedsearch
03
Local Model Server
Large open models served from one Mac: a 100 GB+ model with multi token prediction, plus embeddings for search. It powers Jarvis and my bigger builds.
04
Kids Book App
Native iOS picture books for ages 2 to 4, read aloud by a puppy narrator.
Storage7 TB
- RAID 5 healthy
- Jellyfin
- Immich photos
- Home ad blocker
- VPN downloads
- Remote access
- Nightly backups
- Battery backup
05
Home Media Server
A 7 TB NAS that runs my home: self hosted Jellyfin and photo backup, a whole home ad blocker, secure remote access, and a watchdog that keeps it all running.
05 / Live Demo
Watch a missed call become a booked appointment.
A demo for a business like a day spa: the AI receptionist answers a missed call by text and books the visit. Then the same phone runs a private assistant answering from local files. No human touches either one.
Demo conversation · business and names are illustrative
DG
Desert Glow Spa
AI assistant · SMS
fig. 02 · missed call text back, as the customer sees it
06 / Work With Me
Have a project? Let's scope it.
If you want slideware, hire a consultancy. If you want a working system from someone who runs his own, tell me what you're trying to automate or build. I'll reply with an honest read on whether it's worth doing, and a fixed price if it is.
Replies within one business day