What Led To

Every timeline on the site with its topic, tags, entry count, date range, last update and a short summary. Start here to find the slug for get_timeline.

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

One timeline in full: TL;DR, dated entries newest first with sources and quotes, relations between entries, links to other timelines, what to watch next and open questions. Pass since=YYYY-MM-DD to get only entries dated on or after that day (what changed recently).

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Timeline slug, from list_timelines or a page URL (/events/<slug>)."
    },
    "since": {
      "type": "string",
      "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
      "description": "Only entries dated on or after this day. Pass the updated_at you last saw to get what changed since."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 200,
      "description": "Most recent entries to return (default 60)."
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

One dated entry in full: its summary, type, the parties it names, every source with the outlet, the publication date and the verbatim quote it was read from, plus the relations and cross-timeline links it takes part in. Use it after search_entries or get_timeline has found an entry and you need the exact wording and source URL to cite. Entry ids are unique within a timeline, not across the site, so pass the slug the entry came from.

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "The timeline the entry sits on."
    },
    "id": {
      "type": "integer",
      "description": "The entry's id on that timeline: the id field of a search_entries result or a get_timeline node, and the number in a page's #n<id> fragment."
    }
  },
  "required": [
    "slug",
    "id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Everything the site records about one company, person or regulator across every timeline: its role on each, the parties it most often appears alongside, and every dated entry that names it, newest first, with sources. Use it instead of search_entries when you want one actor's whole history rather than a keyword match. Returns at most limit entries, with total_entries saying how many exist; a party is named when the editors listed it among an entry's parties, not merely when the name appears in the text.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Party id: a lowercase slug such as nvidia, jensen-huang or federal-reserve. search_entries results and timeline entities carry it, and the parties that have a page are listed under parties in /index.json."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 200,
      "description": "Entries to return, newest first (default 40)."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Find dated entries across every timeline by keywords, party id, timeline slug and date range. Every keyword must match (title, summary, party or timeline name); results are ranked, newest first among equals. Returns the entry text and url; call get_entry for quotes and sources.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 200,
      "description": "Keywords. Every one must match, in the entry's title, summary, a party name or the timeline name; omit it to browse by filter alone."
    },
    "party": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Only entries naming this party id."
    },
    "timeline": {
      "$ref": "#/properties/party",
      "description": "Only entries on this timeline slug."
    },
    "from": {
      "type": "string",
      "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
      "description": "Earliest entry date to include."
    },
    "to": {
      "$ref": "#/properties/from",
      "description": "Latest entry date to include."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Results to return (default 20); total says how many matched."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Scheduled dates the timelines are watching — earnings, rulings, launches, rule deadlines — each with why it matters, the timeline it belongs to and a source where one exists. Use it to answer what happens next across the site, rather than reading each timeline for its own catalysts. Returns the dates from today to the horizon, oldest first, echoing back today and horizon; a date known only to the month carries precision=month and is matched on the month.

{
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "minimum": 1,
      "maximum": 730,
      "description": "How far ahead to look, in days from today (default 90)."
    },
    "timeline": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Only dates belonging to this timeline slug."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Answer a why/how question as a chain: an ordered set of dated, sourced entries from the timelines with one line on why each led to the next, written by the editor rather than generated. Returns the best-matching chain with every step's entry (URL, date, summary, sources), or, when no chain fits, the questions that do exist and how to research the answer with the other tools.

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 3,
      "maxLength": 300,
      "description": "The question in plain words, e.g. \"Why did Nvidia become so dominant in AI?\""
    },
    "since": {
      "type": "string",
      "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
      "description": "Also return what changed on the chain since this day (its changelog entries after it); pass the updated_at you last saw."
    }
  },
  "required": [
    "question"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}