Overview
Artificial intelligence supports selected High IQ workflows, including label reading and research tools. Each feature has its own model, privacy, availability, and validation boundary. Notebook companion generation is currently disabled while its first-party content and evidence pipeline is validated. This page covers the four primary AI-powered capabilities in High IQ and the technology behind each.Label Scanner
The AI Label Scanner is one of High IQ’s signature features. Point your phone’s camera at a dispensary label — whether it is a Certificate of Analysis (COA) sticker, retail packaging, or a jar label — and AI extracts structured data in seconds.What It Extracts
How It Works
1
Image Capture
You photograph the label using the in-app scanner. The scanner supports single images or batch mode (up to 4 images for front, back, COA, and additional angles of the same product).
2
AI Vision Analysis
The image is sent to Google Gemini 3 Flash, a multimodal AI model optimized for visual document understanding. The model reads printed text, tables, charts, and even handwritten notes on labels.
3
Data Extraction
The AI extracts structured fields — strain name, cannabinoid percentages, terpene names and values — from the unstructured label image. For batch scans, terpene profiles are merged using the maximum value found across all images.
4
High Family Classification
Extracted terpene data is run through the High Families classification algorithm to assign the product to a High Family.
5
Database Matching
The identified strain name is fuzzy-matched against the High IQ database. If a match is found, the scan results are linked to the existing strain profile. If not, the data is stored for future enrichment.
Batch Scanning
Cannabis products often split information across multiple labels. Batch mode lets you scan up to 4 images of the same product:- Front label — Strain name, brand, product type
- Back label — Cannabinoid percentages, warnings, ingredients
- COA sticker — Full terpene profile with lab-verified concentrations
Privacy
Label scanner data is handled with strict privacy controls:- Images are not stored — After AI analysis, the image is discarded. We do not retain your photographs.
- IP addresses are hashed — SHA-256 hashing ensures your IP address is anonymized before any scan metadata is stored.
- Scan data is anonymized — Extracted strain data contributes to aggregate database quality but is not linked to your personal account in any identifiable way.
The label scanner works best with clear, well-lit photographs. COA labels with printed terpene tables yield the most detailed extractions. Blurry or low-contrast images may result in incomplete data.
Notebooks
High IQ is validating personalized readable notebooks built from order or selected-stash task inputs plus available TIWIH strain research. Current Report V1 is legacy-unvalidated: it can synthesize fallback/default content and does not consistently preserve source absence. The first-party Report V2 implementation persists a minimized immutable source snapshot, rejects unsupported claims, and retains validated immutable publications, but its write and customer-update gates remain off during launch review. Stories, Daily Stories, audio, mindmaps, infographics, images, and video are optional companion-format prototypes. Their durable ledger is implemented, but its executor registry has zero selected entries and its execution gate is off. Daily Story scheduling and generation are inert. No current account should be promised automatic daily recaps or rich-media generation. The provider-neutral evaluation rules, independent hard gates, synthetic-only fixtures, private-storage requirements, and current research posture are documented in Notebook Media Governance.Notebook Capabilities
Depending on the frozen task input and validated output, a readable notebook can organize:- Task input facts — Selected strains, original quantities, order date, and available dispensary or price fields
- Strain context — Available TIWIH research for strains resolved from the task input
- Source visibility — Notebook- or strain-source-group provenance where present
- Educational synthesis — Only where output exists and passes the current validation boundary
Durable generation state
Notebook work does not depend on keeping one screen or streaming connection open:- Frozen run input — The generation task freezes its input and source references. Evidence-first Report V2 also persists a minimized immutable source snapshot; this is not a Report V1 guarantee.
- Persisted sections — Completed section state remains available if another section fails.
- Recoverable progress — The app reads the latest server state when reopened; there is no fixed generation-time promise.
- Fail-closed companions — The artifact ledger records disabled or blocked plans without calling a text, speech, image, or video executor.
Ask AI (Professor High)
Ask AI, powered by Professor High, is the in-app AI assistant for cannabis research, strain science, and terpene education. Conversations auto-save and can be resumed anytime from the history sheet.- Cannabis research — Ask questions about any strain, terpene, cannabinoid, or effect
- Strain science — Understand terpene profiles, the entourage effect, genetics, and growing info
- Personal data tools — Access your stash, favorites, orders, spending stats, and collection directly in the conversation
- Image attachments — Attach up to 4 images per message (labels, COAs, packaging) for visual analysis
- Markdown responses — Tables, lists, and code blocks for structured comparisons
- Conversation persistence — Chats auto-save and can be resumed anytime from the history sheet
Example Questions
How It Differs from Generic AI
Professor High is not a generic language model answering cannabis questions from training data. It has:- Cannabis domain expertise — Prompts are tuned with cannabis-specific knowledge from the
@tiwih/cannabisand@tiwih/ai-promptspackages - Source citations — When referencing research, the AI links to specific papers in the research hub
- Streaming responses — Text arrives word by word via Server-Sent Events so you don’t wait for the full response
AI-Generated Content
High IQ uses AI to generate educational content at scale:Blog Articles
The platform’s blog features AI-generated cannabis education articles covering strain reviews, terpene deep dives, consumption guides, and industry news. Each article goes through:- AI writing — Long-form content generated with cannabis domain context
- Image generation — Thumbnail images created by Google Gemini with cannabis-appropriate visual styles
- Human review — All AI-generated content is reviewed for accuracy before publication
Strain Descriptions
When a new strain enters the database through the research pipeline, AI generates:- Comprehensive descriptions — Multi-paragraph overviews covering genetics, effects, and recommended use cases
- Effect summaries — Concise effect profiles for quick scanning
- Growing notes — Cultivation information synthesized from multiple sources
Research Paper Summaries
The daily paper pipeline uses Claude to generate plain-language summaries of published cannabis research. These summaries make academic papers accessible to consumers who want science-backed knowledge without reading full journal articles.AI Models Used
Model routing varies by feature and must be verified against its current implementation and provider terms. The notebook artifact registry is separate from the API model registry: it is candidate-only, has zero selected executors, and cannot be activated through a client flag or provider environment value.
Responsible AI Practices
High IQ follows these principles in its AI implementation:- Transparency — AI-generated content is labeled as such. Users know when they are reading AI output.
- Accuracy over speed — Quality gates and human review catch AI hallucinations before content reaches users.
- Privacy first — Each feature must minimize inputs and pass provider retention, training, regional-processing, and deletion review before it handles personal data.
- No medical claims — AI is instructed to never make specific medical claims or recommend cannabis as treatment for conditions. It provides educational information only.
- Continuous improvement — We monitor AI output quality and update prompts and models as better options become available.
Frequently Asked Questions
Is my data used to train AI models?
Is my data used to train AI models?
Notebook companion execution is currently off, so the artifact ledger sends no notebook companion request to an AI provider. Other AI features use their documented processors and data controls; review the applicable privacy notice for the feature you use.
How accurate is the label scanner?
How accurate is the label scanner?
Accuracy depends heavily on image quality and label clarity. COA labels with printed terpene tables achieve the highest extraction rates. Retail packaging with large text and clear layouts also performs well. Handwritten or low-contrast labels may require manual correction.
Can I use Ask AI for medical advice?
Can I use Ask AI for medical advice?
No. Ask AI is an educational tool. It can help you understand terpene science, compare strain profiles, and find research papers, but it cannot and should not replace professional medical advice. Always consult a healthcare provider for medical decisions.
Why can notebook progress continue after I leave the screen?
Why can notebook progress continue after I leave the screen?
Notebook lifecycle and section state are persisted on the server. Reopening the app reads the latest saved state; there is no fixed 30–60 second promise and optional companion generation remains disabled.