> For the complete documentation index, see [llms.txt](https://docs.january.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.january.ai/getting-started/core-use-cases.md).

# Core Use Cases

Four capabilities cover most integrations. They share one vocabulary — a food returned by any of them can be passed to any other.

### Scan food

Turn a meal photo or a plain-English description ("a bowl of oatmeal with honey") into structured detections with nutrition, then let users fix mistakes conversationally through the corrections endpoint. Reading packaged-food labels is coming to the same photo endpoint.

### Search the food database

Full-text search over generic and branded foods, barcode lookup for packaged products, type-ahead autocomplete for logging flows, and healthier alternatives for any food, honoring dietary restrictions and preferences.

### Log food

A per-user food diary: create, list, update, and delete entries with day-range queries. Fetch a food's full serving list first so users can log "1 cup" or "100 g", not just the default serving.

### Predict glucose response

A predicted glucose curve and an impact score for any meal, from a user profile alone — no sensor required. Partners with CGM data can send it for personalized predictions.

### Who builds on this

Health and nutrition apps, GLP-1 and diabetes-care programs, coaching platforms, and employers and payers adding food intelligence to existing products.