The app shelf / Privacy and work
Storyline
Private writing where the AI runs on your device.
For people bound by confidentiality: clinicians, lawyers, journalists. Privileged work is locked to on-device models by construction, and every action lands in a tamper-evident audit log.
What runs on your device
- Apple Foundation Models
- WhisperKit dictation
- Argon2id and AES-256 encryption at rest
- Hash-chained audit log
About Storyline
Storyline is a writing studio for people whose words are confidential by law: clinicians, lawyers, journalists, and anyone who cannot paste sensitive work into a cloud chatbot. Your documents, research and every AI conversation stay encrypted on your device and sync only through your own iCloud.
For privileged work, the AI runs on your Mac, iPad or iPhone and is locked out of cloud models by construction. When you allow it, Storyline can use a model on another of your devices, or your own OpenAI, Anthropic or Ollama key.
What you can do
- An AI co-author that plans, drafts and revises, with every suggestion arriving as a branch you adopt or discard
- Private on-device dictation, on the page or in almost any field
- One capture bar for links, PDFs, notes and spoken thoughts, read and summarised on device
- Web research with cited notes, screened so protected names never leave in a query
- Snapshots, branches and full version history
How it’s built
- Fail-closed AI routing: privileged content cannot reach a cloud provider
- Providers behind one abstraction: Apple Foundation Models, local Ollama and bring-your-own-key cloud models
- Argon2id and AES-256 encryption at rest, with vault keys behind biometrics
- A tamper-evident, hash-chained audit log, signed by a key that never leaves the Secure Enclave
- WhisperKit for on-device speech to text
A closer look
Behind the build
Your own devices as a private AI cluster
The most capable AI computer you own is probably asleep in the next room. Storyline's next bet is to use it.
Promised versus provable
Private AI is becoming a marketing phrase. For confidential work, privacy has to be something you can check, not something you are told.
My research agent cited example.com
Getting a small on-device model to actually do research, and a ledger that shows exactly what left the device.
I tried to search the web from my own app. It said no.
Storyline 1.2.1: protected names are held back, the query is rewritten on device, and the research still comes back cited.
Siri can call Google now. Where does confidential work go?
If Apple sends its hardest questions to a partner cloud, "it runs on my device" is no longer a given. For some professionals, that is a dealbreaker.
Show me: what happens to a sentence you write in Storyline
No server, an Argon2id vault and a tamper-evident audit log you can verify yourself. The machinery behind provable privacy.