proofite

Read the user's personal AI-written news briefing (daily digest) in full markdown: every story selected today from their newsletters, RSS feeds and monitored web searches, with sources. Returns the latest briefing by default, or a specific one by id or date. Also returns an index of entry ids, needed to rate or correct individual stories.

{
  "type": "object",
  "properties": {
    "briefing_id": {
      "type": "string",
      "description": "Specific briefing id (from list_briefings). Omit for the latest."
    },
    "include_markdown": {
      "type": "boolean",
      "description": "Include the full text. Default true; set false for just the index."
    }
  },
  "additionalProperties": false
}

List the user's past daily briefings (most recent first) with date, title, number of stories and whether an episode exists. Use it to find the id of a specific day before reading or correcting it.

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "description": "How many, default 10"
    }
  },
  "additionalProperties": false
}

Read everything that shapes what reaches this person: delivery schedule, length, technicality, depth, stance and tone, stated interests and no-go topics, the profile the system has learned about them, the per-topic preferences built from their feedback (affinity, muted, followed themes) and the specific stories they pinned with "follow" (every development of those gets reported). This is the full picture of their news filter — read it before changing anything.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

List the topic inboxes this person feeds their briefing with: each one has a dedicated email address for newsletter subscriptions, plus RSS feeds and monitored web searches. Shows how much each produced recently, its priority and whether it is included in the briefing.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Inspect one topic inbox in detail: every RSS feed (with its health and last fetch), every monitored web search, X/Twitter profiles, and the newsletters currently arriving at its dedicated address. Use it before removing or reorganising anything.

{
  "type": "object",
  "properties": {
    "source_id": {
      "type": "string",
      "description": "Id from list_sources"
    }
  },
  "required": [
    "source_id"
  ],
  "additionalProperties": false
}

Get the audio episode generated from a briefing: a private podcast narrated in the user's language, with a playable URL and the show notes listing every source. Returns the latest episode by default.

{
  "type": "object",
  "properties": {
    "briefing_id": {
      "type": "string",
      "description": "Episode of a specific briefing. Omit for the latest."
    }
  },
  "additionalProperties": false
}

List what is queued in the read-later inbox: links and forwarded emails that are guaranteed to be covered in the next briefing.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

List the deep-dive research requests waiting to be covered: topics the user asked the briefing to investigate with fresh web research.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Account status: plan, whether the briefing is currently running, when the next one is due, how many sources and stories are in the system, and the AI cost accrued this month.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Change how and when the briefing reaches this person: delivery time and days, length, technicality, depth, stance, tone, stated interests and topics to avoid, language, timezone, podcast and email delivery. Pass only the keys you want to change. Read get_information_diet first — these are global settings, not per-topic ones (for a single topic use tune_topic).

{
  "type": "object",
  "properties": {
    "digest_enabled": {
      "description": "ricevere o meno il briefing quotidiano",
      "type": "boolean"
    },
    "digest_time": {
      "description": "orario di consegna, HH:MM nel fuso dell'utente",
      "type": "string"
    },
    "digest_days": {
      "description": "giorni della settimana, ISO 1=lunedì … 7=domenica",
      "type": "array",
      "items": {
        "type": "integer",
        "minimum": 1,
        "maximum": 7
      }
    },
    "digest_length": {
      "description": "quanto deve essere lungo",
      "type": "string",
      "enum": [
        "short",
        "medium",
        "long",
        "xlong",
        "full"
      ]
    },
    "technicality": {
      "description": "1 divulgativo … 5 da addetti ai lavori",
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "depth": {
      "description": "1 solo i fatti … 5 analisi e implicazioni",
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "entry_mix": {
      "description": "1 poche voci trattate a fondo … 5 tante voci brevi (la lunghezza totale non cambia)",
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "stance": {
      "description": "1 neutro … 5 l'editor si sbilancia",
      "type": "integer",
      "minimum": 1,
      "maximum": 5
    },
    "tone": {
      "description": "come deve scrivere («diretto, zero fuffa»)",
      "type": "string"
    },
    "interests": {
      "description": "cosa seguire, in linguaggio naturale",
      "type": "string"
    },
    "avoid": {
      "description": "cosa non vuole leggere mai",
      "type": "string"
    },
    "language": {
      "description": "lingua del briefing e del podcast",
      "type": "string",
      "enum": [
        "it",
        "en",
        "es",
        "de",
        "fr"
      ]
    },
    "timezone": {
      "description": "fuso orario IANA (Europe/Rome)",
      "type": "string"
    },
    "podcast_enabled": {
      "description": "generare anche l'episodio audio",
      "type": "boolean"
    },
    "podcast_minutes": {
      "description": "durata desiderata dell'episodio",
      "type": "integer",
      "minimum": 2,
      "maximum": 20
    },
    "podcast_formato": {
      "description": "show = due conduttori che si rispondono (il formato di casa); classico = una voce che legge il briefing",
      "type": "string",
      "enum": [
        "show",
        "classico"
      ]
    },
    "podcast_accento": {
      "description": "accento della voce, per la lingua scelta: inglese us/gb/au/ie/in, spagnolo es/latam, francese fr/ca, tedesco de/at/ch (l'italiano non ha varianti)",
      "type": "string",
      "enum": [
        "us",
        "gb",
        "au",
        "ie",
        "in",
        "es",
        "latam",
        "fr",
        "ca",
        "de",
        "at",
        "ch"
      ]
    },
    "email_digest_enabled": {
      "description": "ricevere il briefing anche per email",
      "type": "boolean"
    },
    "weekly_recap_enabled": {
      "description": "riepilogo settimanale di ciò che non è stato letto",
      "type": "boolean"
    },
    "chicca_enabled": {
      "description": "nei giorni senza notizie, una storia vera dall'archivio",
      "type": "boolean"
    },
    "smalltalking_enabled": {
      "description": "ogni giorno, in coda al briefing, due o tre storie brevi da raccontare",
      "type": "boolean"
    },
    "serper_enrich": {
      "description": "arricchire il briefing con ricerche web fresche",
      "type": "boolean"
    }
  },
  "description": "Any subset of the settings.",
  "additionalProperties": false
}

Tune how a single topic is treated in future briefings: more or less of it, more or less technical, deeper or shorter, more or less often, muted entirely, or followed so every development of that WHOLE THEME gets reported (to follow one specific story, use rate_briefing_entry with "follow" on that entry). This is the precise instrument — for a vague comment like "too much crypto lately" use correct_briefing instead.

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "The topic, as it appears in get_information_diet or in a briefing entry (e.g. \"intelligenza artificiale\")"
    },
    "action": {
      "type": "string",
      "enum": [
        "more",
        "less",
        "more_technical",
        "simpler",
        "deeper",
        "shorter",
        "more_often",
        "less_often",
        "mute",
        "unmute",
        "follow",
        "unfollow"
      ],
      "description": "What to change about it"
    }
  },
  "required": [
    "topic",
    "action"
  ],
  "additionalProperties": false
}

Tell the briefing what was wrong with it, in plain language — "too much crypto and not enough on the EU regulation", "keep it shorter", "explain the technical parts more simply", "follow this story". An AI editor reads the note against the actual briefing and turns it into concrete adjustments: topic preferences, settings, deep-dive requests. This is the main way a person retunes their news feed by talking.

{
  "type": "object",
  "properties": {
    "note": {
      "type": "string",
      "description": "What was wrong or what they want changed, in their own words"
    },
    "briefing_id": {
      "type": "string",
      "description": "Which briefing the note refers to. Omit for the latest."
    },
    "entry_id": {
      "type": "string",
      "description": "Optional: the specific story the note is about (entry id from get_briefing)"
    }
  },
  "required": [
    "note"
  ],
  "additionalProperties": false
}

Give a precise up/down signal on one story of a briefing: more like this, less like this, more technical, simpler, deeper, shorter, or mute its topics. These apply to the topics of that story, so the next briefing weighs them differently. A story usually has several topics: pass `topics` to hit only some of them (e.g. "less" of "demographics" but not of "japan"). Sending the same signal again with different topics REPLACES the previous one: the topics you drop are restored, nothing is double-counted. "follow" is different: it pins THIS story — from then on every development of this specific story (and only of it) gets a full entry flagged as an update; "unfollow" releases it. Pinned stories are listed by get_information_diet.

{
  "type": "object",
  "properties": {
    "entry_id": {
      "type": "string",
      "description": "Entry id from get_briefing"
    },
    "signal": {
      "type": "string",
      "enum": [
        "more",
        "less",
        "more_technical",
        "simpler",
        "deeper",
        "shorter",
        "more_often",
        "less_often",
        "mute",
        "follow",
        "unfollow"
      ],
      "description": "The signal to record"
    },
    "topics": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "description": "Only these topics of the story (as listed by get_briefing). Omit to apply to all of its topics."
    },
    "briefing_id": {
      "type": "string",
      "description": "Which briefing. Omit for the latest."
    }
  },
  "required": [
    "entry_id",
    "signal"
  ],
  "additionalProperties": false
}

The reader expected a story and the briefing did not have it. Describe it in their words; the editor investigates their own sources of the last days, today's briefing, their preferences and a web search, and answers with a verdict: it was in the briefing, none of their sources carried it (and proposes the missing source), it was dropped because of a preference (and corrects it), it was seen but undervalued, or it could not be found. Topics get followed so similar stories do not slip again; a deep-dive may be queued for the next briefing. Five per day.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "What story they expected, in their own words"
    },
    "briefing_id": {
      "type": "string",
      "description": "Which briefing it was missing from. Omit for the latest."
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}

Read or rewrite the free-text profile the briefing uses to know who this person is — their work, projects, recurring interests, what they already know. Appending is usually better than replacing: pass mode "append" to add a line.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The profile text, or the line to add"
    },
    "mode": {
      "type": "string",
      "enum": [
        "append",
        "replace"
      ],
      "description": "Default append"
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}

Ask the next briefing to investigate a topic properly, with fresh web research: it will include a mini-dossier with sources. Use it whenever the person says "I want to know more about X" or "keep digging on this".

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The question or topic to research"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

Put a link or a note into the read-later queue: whatever lands there is guaranteed to be covered in the next briefing. The page is fetched and its text stored, so it can be summarised even if the site later blocks access.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The link to save"
    },
    "text": {
      "type": "string",
      "description": "Alternative to url: a free-text note to keep"
    },
    "title": {
      "type": "string",
      "description": "Optional title for a text note"
    }
  },
  "additionalProperties": false
}

Generate a briefing immediately instead of waiting for the scheduled time, using everything collected so far. Costs real AI money and takes a couple of minutes, so use it only when explicitly asked. Returns the id to poll with get_briefing.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Create a new topic inbox: a themed container with its own dedicated email address (subscribe newsletters to it), which can hold RSS feeds and monitored web searches. This is how you add a whole new subject to someone's information diet.

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Short name, e.g. \"AI research\" or \"Local news\""
    },
    "description": {
      "type": "string",
      "description": "Optional brief: what the reader expects from this inbox and what to skip — the editor reads it at every briefing"
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false
}

Change a topic inbox: rename it, change its description, raise or lower its priority in the briefing, set a per-inbox technicality level, temporarily exclude it from the briefing or pause it entirely.

{
  "type": "object",
  "properties": {
    "source_id": {
      "type": "string",
      "description": "Id from list_sources"
    },
    "name": {
      "type": "string",
      "description": "New name for the inbox"
    },
    "description": {
      "type": "string",
      "description": "The inbox brief: what the reader expects from it and what to skip — the editor reads it at every briefing"
    },
    "priority": {
      "type": "integer",
      "minimum": 1,
      "maximum": 5,
      "description": "1 marginal … 5 always first"
    },
    "include_in_digest": {
      "type": "boolean",
      "description": "false = keep collecting but leave it out of the briefing"
    },
    "is_active": {
      "type": "boolean",
      "description": "false = stop collecting entirely"
    },
    "technicality": {
      "type": "integer",
      "minimum": 1,
      "maximum": 5,
      "description": "Override just for this inbox"
    }
  },
  "required": [
    "source_id"
  ],
  "additionalProperties": false
}

Permanently delete a topic inbox with all its feeds, searches and collected content. Irreversible: the dedicated email address stops working too. Prefer update_source with is_active false when in doubt.

{
  "type": "object",
  "properties": {
    "source_id": {
      "type": "string",
      "description": "Id from list_sources"
    }
  },
  "required": [
    "source_id"
  ],
  "additionalProperties": false
}

Add an RSS/Atom feed to a topic inbox. You can pass the site address instead of the feed URL — the server fetches the page and discovers the feed. If it fails, the reason is precise (blocked by the site, gone, unreadable) so it can be reported honestly.

{
  "type": "object",
  "properties": {
    "source_id": {
      "type": "string",
      "description": "Which inbox (from list_sources)"
    },
    "url": {
      "type": "string",
      "description": "Feed URL or plain site address, e.g. \"ilpost.it\""
    }
  },
  "required": [
    "source_id",
    "url"
  ],
  "additionalProperties": false
}

Remove an RSS feed from a topic inbox. Already-collected content stays; nothing new arrives from it.

{
  "type": "object",
  "properties": {
    "feed_id": {
      "type": "string",
      "description": "Id from get_source"
    }
  },
  "required": [
    "feed_id"
  ],
  "additionalProperties": false
}

Monitor a Google query every day and feed the results into a topic inbox: the standing-search way to follow a company, a person, a law or a niche subject that has no RSS feed. kind "news" watches the news index, "search" the whole web.

{
  "type": "object",
  "properties": {
    "source_id": {
      "type": "string",
      "description": "Which inbox (from list_sources)"
    },
    "query": {
      "type": "string",
      "description": "The query, as you would type it into Google"
    },
    "kind": {
      "type": "string",
      "enum": [
        "news",
        "search"
      ],
      "description": "Default news"
    }
  },
  "required": [
    "source_id",
    "query"
  ],
  "additionalProperties": false
}

Stop monitoring a standing web search: no new results from that query will reach the briefing. What it already collected stays where it is.

{
  "type": "object",
  "properties": {
    "search_id": {
      "type": "string",
      "description": "Id from get_source"
    }
  },
  "required": [
    "search_id"
  ],
  "additionalProperties": false
}

Describe a subject in plain words and get back real, working sources for it: RSS feeds validated live by the server (dead ones are dropped before you see them), web searches worth monitoring, and newsletters worth subscribing to. Nothing is added — it returns proposals to pass to add_feed / add_web_search.

{
  "type": "object",
  "properties": {
    "source_id": {
      "type": "string",
      "description": "The inbox the proposals are for (its existing sources are excluded)"
    },
    "description": {
      "type": "string",
      "description": "What they want to follow, in plain words"
    }
  },
  "required": [
    "source_id",
    "description"
  ],
  "additionalProperties": false
}

Import subscriptions from another RSS reader (Feedly, Inoreader, FreshRSS, NetNewsWire) by passing the OPML file contents. Set dry_run true first to see what is in it and what is already present; then run it for real to add them (they are validated one by one, and the ones that fail come back with the reason).

{
  "type": "object",
  "properties": {
    "source_id": {
      "type": "string",
      "description": "Which inbox to import into"
    },
    "opml": {
      "type": "string",
      "description": "The full OPML/XML file contents"
    },
    "dry_run": {
      "type": "boolean",
      "description": "true = only list what would be imported"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 40,
      "description": "Max feeds to add in this call (default 20 — big imports go in batches)"
    }
  },
  "required": [
    "source_id",
    "opml"
  ],
  "additionalProperties": false
}

Unsubscribe from a newsletter arriving in one of the inboxes. When the sender supports one-click unsubscribe the server does it directly; otherwise it returns the URL a human has to open, and says so honestly.

{
  "type": "object",
  "properties": {
    "newsletter_id": {
      "type": "string",
      "description": "Id from get_source (newsletters)"
    }
  },
  "required": [
    "newsletter_id"
  ],
  "additionalProperties": false
}