Multimodal Conversation
Ask questions alongside images, photos, or PDF documents. The vision model reads and reasons about what it sees — attachments become part of the conversation.
A private algorithmic assistant built for the questions you actually ask.
Harold is an AI-powered assistant built with privacy and practicality at its core. Available on iOS and Android, it brings the capabilities of frontier language models — including multimodal vision understanding — to a focused, thoughtfully designed mobile experience that doesn't compromise on data principles or user dignity.
Built on a Flutter foundation with a Cloudflare Workers backend, Harold processes requests at the network edge rather than in centralized server farms — keeping inference fast, architecturally lean, and under careful governance. Conversation history is tied to your account, exportable as a PDF, and deletable in full at any time.
Harold is not a general-purpose chatbot. It is designed around a specific personality, a clear purpose, and appropriate limits. It anchors a growing family of specialized assistants built on the same technical infrastructure — including Ask Tutor, a COPPA-compliant learning companion for students — both emerging from a single shared codebase.
Architecture
Harold runs on a Cloudflare Workers backend routing requests to AI models on Cloudflare's global edge network. Two models handle different kinds of requests: a compact 3-billion-parameter text model for everyday queries, and an 11-billion-parameter vision model when images, photos, or documents enter the conversation.
Before any response is returned, a dedicated safety model reviews AI output against thirteen harm categories. Crucially, moderation is applied to AI responses only — not user input — a deliberate decision that eliminates the false positives that frustrate users of most content-filtering implementations.
Both Harold and Ask Tutor are built from a single Flutter codebase using a flavor system. Platform identity, branding, AI personality, feature flags, and compliance requirements — including COPPA compliance for the tutor — are all determined by a single build-time parameter. One codebase, two distinct products.
Capabilities
Ask questions alongside images, photos, or PDF documents. The vision model reads and reasons about what it sees — attachments become part of the conversation.
Conversations are stored under your account, not sold or shared. Full data deletion is available on demand — no dark patterns, no buried settings.
Export any conversation to a clean, formatted PDF — ideal for saving research sessions, technical walkthroughs, or anything worth keeping.
Responses arrive as a live stream via Server-Sent Events — no waiting for the full answer to generate before reading begins.
Conversations are protected by device biometrics — Face ID, Touch ID, or fingerprint — using secure hardware-backed storage.
Inject your own persistent system instructions — tailor Harold's tone, focus, and behavior to match exactly how you like to work.
Coming Soon
Ask Harold and Ask Tutor are the first in a planned family of purpose-built assistants — each with its own personality, domain, and constraints. Harold will be central to The Care Plan, our forthcoming ongoing support subscription.