Give your agent the desk.

One row per buyer program: what it buys, the per-company figures and size screens it publishes, its stated payment trigger, exclusivity, de-identification and export method, a verbatim quote from its own page, and the day we read that page.

Rows, each with its program URL, source URL, source quote and check date. The same rows render at /data-buyers.

• query string

  Words to find in a program name or in what it buys, such as “tickets” or “Handshake”.

• publishes_a_range boolean

  true for only the programs that publish a per-company dollar figure; false for only those that do not.

• limit integer, 1–50, default 25

  How many rows to return.

The span of published figures across the programs a company of a given size and age clears, naming every source behind the span and every program screened out. It answers with no range, and a reason, when fewer than two programs qualify.

has_range, the low and high figures when there is a range, the programs behind them with their quotes, the programs screened out with the reason for each, and the check date.

• headcount integer, 1–1000000

  Full-time employees. Omit if unknown; a company that has not stated one is not screened on it.

• years integer, 0–200

  Years of records the company holds. Omit if unknown.

• headcount_band string: 1_29, 30_99, 100_249, 250_plus

  A /data headcount band instead of an exact figure.

• years_band string: under_3, 3_5, 6_10, 11_plus

  A /data years band instead of an exact figure.

Reads a pasted offer: the figure against the published span, the payment trigger, exclusivity, export method and retention, each quoted back out of the offer, plus the terms to settle before signing. Nothing is stored.

Each term reported as stated or as not stated, with the offer's own words quoted, and a question to ask on each term worth settling. A term the offer is silent on is reported as a finding, not filled in.

• offer string, 60–20000 characters, required

  The offer text: a term sheet, an email, or the part to be read.

• headcount integer, 1–1000000

  Full-time employees, so the figure is set against the programs this company clears.

• years integer, 0–200

  Years of records.

The desk's published notes, newest first: the title, the day it was published, its own address on the site, and its first sentences.

Rows, each with a slug to pass to get_note, the note's URL, its publication day, what kind of note it is, and how many sourced items it counted. The same notes render at /intel.

• limit integer, 1–50, default 25

  How many notes to return, newest first.

• since string, YYYY-MM-DD

  Only notes published on or after this day.

The published notes that carry every word asked for, in their title or their text, newest first. Matching is literal and case-insensitive: nothing is stemmed, ranked or inferred.

The same rows list_notes returns, filtered. An empty answer means the words are not in the corpus, not that the desk has no view on them.

• query string, 2–120 characters, required

  Words every matching note has to carry, such as “carve-out” or “data centre power”.

• limit integer, 1–50, default 25

  How many notes to return.

One published note in full: its text as written, the day it was published, its address on the site, and every link it cites.

The note's body as markdown, plus a sources list of every link in it, so a reader can check the note rather than take its word.

• slug string, 8–160 characters, required

  The note's slug from list_notes or search_notes. A full /intel/… path works too.

The five markets Frontier Desk maps — services, compute, data, credit and capital — with the relationship graphs drawn in each, the columns each graph runs through, the sectors you can pick, and counts of what is drawn.

One entry per market with its graphs and their columns, the sector slugs to pass to get_market_sector, and the day the model was read. The whole-field graphs render at /markets.

A firm in the markets directory by name: what kind of firm it is in plain words, its own site, the relationships held for it, and a line on its recent activity. Up to eight firms per call.

Each firm with its type in reader words, its site where we hold one, and each relation naming the other party — what it bought, backed, lent to or borrowed from. No internal ids, codes, tags, evidence text or third-party scores cross this.

• query string, 2–60 characters, required

  Part of a firm's name, such as “Monroe” or “CORE Industrial”.

One sector's relationship graphs: the firms drawn in each column, the relations between them in each side's own words, the roster of who does what, and the lines on what the connections show.

The same JSON the /markets page loads when a visitor picks that sector, plus the graphs this sector is not drawn in, which is a fact about the sector rather than a gap.

• sector string: accounting, insurance, wealth, it, healthcare, staffing, legal, engineering, marketing, logistics, distribution, operators, software, business-services, property, manufacturing, build-out, required

  The sector to draw, as list_markets gives it.

• graph string

  One graph instead of all of them, by key, such as “services” or “credit”.

The guides: one page per question an owner asks before a sale, a loan or a data licence, each with the question it answers and a forty-to-sixty-word answer to it.

Rows with a slug to pass to get_guide, the guide's URL, its quick answer, and the day it was last updated. Newest first.

• query string

  Words to find in a guide's title, question or description, such as “MSP” or “data room”.

• limit integer, 1–50, default 25

  How many guides to return.

One guide in full: its quick answer, its text as markdown, the day it was last updated, and its address on the site.

The guide's body as markdown, written to be quoted, with the question it answers and its update date beside it.

• slug string, 2–120 characters, required

  The guide's slug from list_guides, such as “sell-an-msp”.

The standing forecasts: what each one forecasts and over what horizon, the day it was published, and the date it is next rescored.

One row per outlook with its route, to pass to get_outlook, and its own summary and publication date, imported from the report rather than retyped.

One standing forecast: the odds Frontier Desk gives every path at each of the two dates it is scored on, the readings behind them, and the scenarios with the markers that say which one we are on.

Odds tables whose columns each sum to 100, the bottom-line readings with their confidences, and the scenarios. The odds are the desk's own and are settled only by the dated public sources the report names. The whole report is on its page.

• outlook string: /outlook/company-data-market-2027, /outlook/ai-jobs-and-income-2035, required

  The outlook's route, as list_outlooks gives it.

The services verticals the desk writes a page for: what a data licence looks like in that line of work, and the shape of firm each page illustrates.

One row per vertical with the key to pass to get_vertical, its heading and lead, and whether its card is an illustration or built from aggregate data.

One services vertical: the example firm it illustrates, what changes in that line of work, and what decides whether a firm in it may license at all.

The card's headcount and years bands, the tools such a firm runs on, and the routes worth weighing — labelled as an illustration in `evidence`. No dollar figure is ever stored on a vertical; pass the bands to instant_range for the figures the buyer programs publish.

• vertical string, 2–60 characters, required

  The vertical's key, as list_verticals gives it.

The tools Frontier Desk publishes for owners, what each one answers, and the written pages behind them.

Each tool with its route and what a reader gets from running it, and the routes get_public_page carries. One row is a Frontier Desk tool on its own domain and says so.

One public page as written: its heading, its lead, and the sections it carries — what the page says it does, what it covers, and what it does not.

The page's own copy. This is not a run of the tool on it: /first-pass ranks a list from a live read for whoever answers its four questions, and nothing here invents one.

• page string: /tools, /first-pass, /deal-ready-ai, /roadmap, /data, /second-opinion, /compute, /build, /agents, required

  The page's route, as list_public_pages gives it.