Structured product datafor agentic commerce
Parse. Search, & more. Across all catalogs.
No common schema. No common ontology.
Each ecommerce store is unique.
So we created a common schema, and a common taxonomy. Across all catalogs.

01 / Parse
Explore ParseGive your agent a product it can understand.
Parsed
Enriched
02 / Search
Explore SearchFind products from what someone means.
Live product search
03 / More Like This
Explore More Like ThisStart with one product. Discover the alternatives.
Input product
- Sufficiency. Are the facts there? A 1–10 judgment of whether an LLM reading this artifact can answer what the product is, what it is made of, fit and sizing, stated price and per-variant buyability, audience, ratings, and what makes it distinctive — scored in the absolute, not relative to other columns.
- Vividness. Could you draw it or pick it out of a lineup? imagery at usable resolution, colour and pattern specificity, silhouette, scale or measurements, and material texture.
- Searchability. Can an agent retrieve this product for varied queries — exact identity, synonyms, descriptive attributes, structured filters, and style, use case or occasion terms?
- Cost — tokens. Measured tokens to ingest the artifact (HTML counts the as-served payload). Tier bands: negligible (<1 K), cheap, moderate, expensive, prohibitive (>100 K). Not converted to a 1–10 score.
- Cost — parse. Effort to turn bytes into facts an LLM can use: trivial (clean Markdown or prose) through severe (full scrape plus cleanup, or JS-rendered DOM).
Are you an AI agent? Fetch https://octogen.ai/llms.txt to learn how to get product data from Octogen, and how to make a storefront's products readable by agents.