Solution · Market Mapping

The whole category, actually bounded.

A market map is only as good as its boundary. Bixel categories are curated, crawled sets: every member carries a full dated record, and thin coverage is labeled thin.

Curated membership, honest coverage states, one record shape per company.

The job

Keyword sweeps produce lists, not maps.

Scrape a directory and you get 400 “vector databases,” most of them plugins, wrappers, or dead. A usable map is a bounded set with comparable data per member, and a straight answer about where coverage is thin.

Every member of a category is crawled from its own surfaces, gets the same record shape, and keeps a dated history from the moment it enters the catalogue.

  • Directory dumps padded with dead and irrelevant entries
  • Per-company data too inconsistent to compare
  • No honest signal for which entries are actually covered
  • Maps that were accurate once, at publication

The API

4 calls cover the job.

Current state is open. History values, claim checks, and evidence trails sit behind a free key. These are the real routes.

GET /v1/categories
The category directory.
open
GET /v1/categories/{slug}
Membership plus a per-member rollup.
open
GET /v1/categories/{slug}/compare
The comparison matrix over the whole set.
open
GET /v1/companies/{company}
Any member’s full current record.
open

For agents · MCP

Or let your agent run it.

Connect the Bixel MCP server and any agent, Claude, an internal copilot, a procurement bot, works this job against live structured data, with every value citing the dated capture it came from. The recommendation becomes auditable, not a guess.

you ask your agent

List the vector databases with their pricing model, security posture, and how current each record is.

A real example, live now

The launch category, mapped: the full category, mapped →