NOW ON THE APP STORE · PRISMSAI CAMPUS OS

Put the AI hub
back on your iPhone.

PRISMSAI is not a chat box that hands students over to a backend. Agents, memory, profiles, and task orchestration live on the phone. Only what the chosen model needs for the current inference travels through an isolated stateless relay.

PRISMSAI 1.0 · FreeiPhone + iPad · iOS 17+Available outside mainland China

On-device agentsStateless relayProvenance memory
Today · PRISMSAI
ASK

What do you want to solve today?

Ask about courses, activities, or campus life…↑
TODAY'S ASSISTANTOrganizing your course plan
Intake → Advising Agent → Knowledge
MEMORYUnderstands your learning rhythm

Derived from traceable source history

KNOWLEDGESchool + external sources

Uncertainty remains explicit

A DIFFERENT AI ARCHITECTURE

The server provides a channel.
It does not take over the student.

Conventional AI products centralize conversation, memory, and orchestration in the cloud. PRISMSAI places the intelligent runtime on the iPhone and separates the model-content path from the management control plane.

01STUDENT iPHONEPrivate workspace

Agent Runtime

Intake routing, the responsible business agent, skills, profile context, memory recall, task ledger, and output rendering run on device.

IntakeMemoryKnowledgeTasks
02STATELESS RELAYIn-memory only

Model Data Plane

A separate process authenticates use, injects provider credentials, and forwards requests without a database, admin interface, or content logs.

No DBNo body logsNo student ID upstream
03CLOUD LLMReasoning engine

Chosen Model

The selected model reasons and returns a result. It does not own PRISMSAI's profile store, task ledger, personal knowledge, or agent orchestration.

Provider-agnosticReplaceablePolicy-selected
SEPARATE CONTROL PLANEManage the system, not student conversations

Accounts, agent and skill versions, school knowledge retrieval, anonymous technical failures, and knowledge gaps use a separate control plane. Full conversations, profile text, memory bodies, and model answers do not enter it.

The boundary, precisely: stateless means content passes through memory without PRISMSAI persistence or management-plane visibility. It is not end-to-end encryption between the phone and model provider; the provider receives what it needs for inference. Data that must never leave the phone requires an on-device model.

WHAT WE BELIEVE

Not another chat box.
A system that works for campus life.

01

Think on device

Student questions, personal profiles, and task orchestration stay on the student's device first.

02

Answer with evidence

Search both school and external knowledge. If reliable evidence is missing, make the gap visible.

03

Deliver the result

From concise text to interactive HTML, present each result in the form that best fits the task.

PROVENANCE-FIRST MEMORY

Memory is not accumulated history.
It is traceable understanding.

PRISMSAI does not repeatedly stuff entire conversations into a model. It turns use into memory structures that are sourced, updateable, and deletable, so personalization can grow without losing its evidence boundary.

01 · SOURCE

Detailed source capsules

Preserve exact student inputs, selected images, and imported files under stable source IDs.

What actually happened
02 · PROFILE

Incremental student profile

The profile agent compresses durable preferences, goals, habits, and uncertainty into per-claim conclusions bound to source, freshness, and confidence.

What remains useful
03 · RECALL

Precise recall on demand

A task receives only a minimal relevant profile. When more support is needed, the business agent retrieves detailed memory by locator.

Only what this task needs
SHORT-TERM MEMORYCurrent conversation, active task, and follow-up input

Preserves continuity with the responsible business agent without routing a follow-up through intake again.

LONG-TERM MEMORYSource-bound profile and personal knowledge

Updates through real use and checks for age, conflict, weak evidence, and review needs.

MEMORY QUALITYNot a second hidden structural validator

Assesses semantic quality, source conflict, freshness, and confidence without inventing missing legacy citations.

THE PHONE IS THE TOOLBOX

Agents that do more than answer.
They can use this phone.

With explicit user intent and iOS permission, the on-device runtime can read necessary context, prepare local actions, and return real system receipts.

CAL

Calendar and reminders

Read nearby conflicts and create events or local notifications the student explicitly requests.

LOC

Maps, location, and weather

Use current coarse location without building location history, then hand off to Apple Maps when needed.

CAM

Camera, photos, and OCR

Process only content the user captures or selects, then add it to image memory and personal knowledge.

HLT

Health summaries

Read authorized step and sleep summaries without writing Health data or offering medical diagnosis.

SHR

Share Extension

Persist text, webpages, images, and files from other apps, then continue organization and indexing in the background.

SYS

Speech, files, and related apps

Use system dictation and file selection in Unified Ask, then hand results to relevant applications.

THE AI CENTER FOUNDATION

Not a pile of features.
One continuously working intelligence layer.

The same on-device hub connects agents, memory, personal knowledge, device capabilities, and durable tasks. Each agent has a clear responsibility while sharing the same sources, identity context, and execution truth.

LIVECOLLABORATIVE AGENT MEMORY

Share evidence, not hallucinations.

Profile, intake, business, and artifact agents read the same stable source IDs, minimal profile, and task receipts instead of maintaining conflicting hidden memories.

LIVEPROACTIVE MEMORY

Prepare grounded help before it is requested.

The profile agent can ground a Today Tip in authorized memory, reminders, calendar, and device facts. It proposes; it does not act without confirmation.

LIVECROSS-APP CONTINUITY

Bring any content back to one student workspace.

Share Extension persists text, webpages, images, and files from other apps. Maps, calendar, and related tasks can be handed to the appropriate system app.

ROADMAPCROSS-DEVICE CONTINUITY

The architecture is reserved; personal sync remains off.

Future continuity requires explicit opt-in, revocation, auditability, and encryption. Today, personal memory, private knowledge, and task bodies remain authoritative on the current iPhone.

IMPLEMENTED, NOT CONCEPT ART

Innovation already
inside the runtime.

These are not roadmap slogans. Every capability maps to the current iOS app, agent contract, or durable runtime infrastructure.

01
Per-claim memory quality

Every profile claim has its own evidence state.

Review supporting and conflicting sources, freshness, confidence, and next action without fabricating legacy source references.

02
Local image memory

Images become searchable memory on the phone first.

Vision OCR and image classification combine with capture time, dimensions, and available location metadata to form local source capsules.

03
Private hybrid retrieval

Semantic and lexical signals find the student's own knowledge.

The iPhone chunks personal knowledge, combines lexical scoring with system semantic vectors, and audits index version, count, and content digest.

04
Failure-indexed corrective retry

Change the method after failure instead of repeating output.

The runtime selects a correction skill by stage and failure code, asks the original agent to rebuild the complete object, and records every correction result.

05
Semantic evidence and knowledge gaps

Valid structure does not guarantee factual support.

Independent semantic verification checks claims against bound sources. Weak evidence produces a stable gap ID for the school's completion queue.

06
Durable tasks and system surfaces

Real task state survives leaving the app.

Tasks, events, confirmations, and corrections share one ledger that drives BGProcessing, Widget, Live Activity, notifications, and privacy-safe Spotlight summaries.

07
Safe interactive HTML

Rich artifacts can interact without silently networking.

Infographics, mind maps, and flows render in an isolated WebView governed by CSP, navigation blocking, and evidence constraints.

08
Traceable runtime fingerprint

Know which agent, model, skill, and contract actually ran.

Receipts capture stages, model attribution, knowledge queries, correction paths, and one runtime fingerprint; failures can flush anonymous diagnostics.

BUILDING IN PUBLIC · SINCE JULY 2026

Update log

Six weeks of architecture, product, knowledge, and live-runtime work—kept directly inspectable.

Loading updates…

QUESTIONS, ANSWERED

About PRISMSAI

01

Where can I download PRISMSAI?

PRISMSAI 1.0 is free on the App Store for iPhone and iPad in supported storefronts outside mainland China. The Download button opens the official listing directly in the App Store app.

02

What is PRISMSAI?

A local-first student AI campus assistant connecting questions, personal memory, knowledge retrieval, specialist agents, and task artifacts.

03

How does it protect privacy?

Planning, profiles, and task context stay on device first. The public website never serves as the student's private assistant client.

04

What can it help students do?

Course planning, campus policy and safety, clubs, schedules, reminders, knowledge organization, text, and interactive HTML artifacts.

STUDENT COMMONS

A student community
that starts with real questions.

Share campus experience, discuss product ideas, and ask other students for help. Real names are not required. Do not post private information, grades, or account details.

Recent discussions

Connecting to the community…

NEW DISCUSSION

Start a discussion

By publishing, you agree to discuss respectfully and not expose anyone's sensitive personal information.