assess
01Agent
A market map is being built for {{anchor}} — {{sells}} Its buyer: {{buyer}}.
Plug in one domain. Get a full market map and a knowledge graph that plugs straight into your agent. Agents search the job instead of the brand name, read every host's own page, and cite it.
Agent
A market map is being built for {{anchor}} — {{sells}} Its buyer: {{buyer}}.
Agent
You are writing search queries that will find everyone competing with ONE product.
Agent
Classify this one host. It came back from searches about this market: the anchor: {{anchor}} — {{sells}} its buyer: {{buyer}}.
Agent
You read a company's own website and find every product it sells. Nobody hands you the pages: you pull them. Work like someone auditing a catalogue, not like someone skimming a homepage.
Agent
A model read each of these hosts' own front page once and decided, page in hand, that none of them have any place on a map of this market: relation: none, the one verdict that costs a host its place on the map entirely. That judgement never gets a second opinion — until now.
Agent
An investigation of {{anchor}}'s own site just finished. It read the pages itself and submitted every product it could establish; the list below is what it found, each line naming the page that establishes it. Your job is the judgement that list does not carry: group the products into the markets they actually sit in.
Agent
You are investigating one angle of a market, on behalf of a map someone else is assembling.
Agent
Say how these pairs of companies relate to EACH OTHER.
Agent
Below are rows this run's own searches already returned — a title and a description apiece — whose shape looks like a roundup: "10 best X", "X alternatives", "X vs Y", a comparison post. A roundup names several vendors in its own text, and this run's search phase only ever followed the one URL each row points at…
Agent
These entities are on a market map of {{anchor}} — {{sells}} — and not one of them has an edge to any other player. Each was judged from its own page; what was never asked is where it STANDS.
Agent
Sixty hosts came back from searches about one market. Before this run spends a fetch and a judgement on each, say which are worth it — from the search metadata alone.
Agent
Read this company's own material and work out what it sells.