youspot.com

What this user should deal with right now, computed from their sent mail, their calendar and their LinkedIn export: people who went quiet after real correspondence, people they are meeting this week, who they write to most, invitations nobody answered, and the shape of their network.

The Linear issues completed in one Monday-to-Sunday week (Eastern time), last week by default, that have not been announced in a changelog and do not carry the no-changelog label.

Save the week's changelog draft for an editor to review and publish.

Research one specific company in depth — the same engine behind the CompanyResearch.ai app.

Recent news and hiring movement for companies the user already knows, several at once, split into what is new since the last check and what was already reported.

Look up the public registration (WHOIS) record for a website domain: who registered it, which registrar holds it, when it was created and last updated, when it expires, its nameservers, and its registry status codes.

Estimate what a domain name is worth (the /domainvalue appraisal): an estimated market value in dollars with the signals behind it — comparable sales, marketplace listings, an appraisal model, SEO data.

Send an email to the signed-in user at their own account email address.

Read the content of a file the user uploaded — use this when the answer may live in a document in their Second Brain: schedules, itineraries, contracts, exports, scans.

Download a file from a public http(s) URL and store it in the user's Second Brain as a file object — use when the user shares a direct link to a PDF, image, spreadsheet, or other file and asks to save, download, or keep it.

Import every contact or company from a file the user uploaded — a CSV or spreadsheet export, a .vcf of contacts, or a zip.

Search the user's connected Gmail mailboxes and return matching messages, newest first — from, to, subject, date, and a short snippet of the body.

Fetch one Gmail message by its id from the user's connected mailbox, including the full plain-text body (rare header-only connections get headers and the snippet instead).

List the labels in the user's connected Gmail mailboxes — system labels (INBOX, STARRED, ...) and the user's own labels, with their ids.

Create a DRAFT email in the user's connected Gmail mailbox, addressed to anyone — 'draft an email to jane@acme.com about X'.

Archive one Gmail message — it leaves the inbox but stays in All Mail, fully recoverable.

List events from the user's connected Google Calendar, ordered by start time — summary, start/end, location, organizer, attendees and their RSVP status, and a meeting link when there is one.

List the calendars in the user's connected Google account(s) — name, id, whether it's the primary, and the user's access role.

Prepare or queue one calendar event through the shared suggestion service.

Update one Google Calendar event — change its title (summary), description, location, or start/end times.

List objects in the user's graph, newest first, with counts by type.

Get one object from the user's graph, with the objects connected to it (its edges, e.g.

Rename or re-describe an object in the user's graph, or set any of its type-specific fields: a contact's phone, email, headline or location, a company's funding stage, and so on.

Search the user's graph by matching a term against object names and descriptions — plus semantic matching over text-bearing objects (notes, facts, posts, links, files, emails), so a search finds what the user means, not just exact words.

Create a new object in the user's graph.

Set up a standing search the user wants watched — 'track LinkedIn posts that mention hubspot', 'track tweets mentioning @dharmesh', 'watch acme.com/pricing for changes'.

Connect two objects in the user's graph with a directed edge — e.g.

Delete an object from the user's graph.

Delete EVERY object of one type from the user's graph, however many there are: what to reach for when they ask to clear out a whole category ('delete all my HubSpot contacts') rather than one record.

Record one dated touchpoint with someone in the user's graph — an email exchanged, a call, a meeting, a LinkedIn touch, or a manually noted contact — so 'when did I last talk to them?' has an answer.

Merge two duplicate records in the user's graph into one — person or company only.

Permanently delete one object from the user's graph, along with every connection touching it.

Delete one connection between two objects in the user's graph — the edge from_object_id -> to_object_id of the given connection_type, nothing else; both objects stay.

How two objects in the user's graph are connected: the shortest chain of real relationships between them, up to 3 hops, e.g.

The objects in the user's graph directly connected to BOTH of two given objects — mutual contacts between two people, shared people between two companies.

The objects in the user's graph closest in MEANING to one object — nearest neighbours by stored embedding, so it finds related notes, facts, links, files, and posts even when no words match.

Set a dated follow-up about an object in the user's graph — 'follow up with Jane in March'.

Read back objects a skill wrote earlier, filtered precisely.

People the user has not written to in a while, quietest first, with the date of the last thing they sent.

Who introduced the people in the user's graph, aggregated per introducer, so a skill can see which relationships actually produce work rather than which are warm.

Query the user's HubSpot contacts — the people synced from the HubSpot portals they've connected.

Query the user's HubSpot companies — the companies synced from the HubSpot portals they've connected.

Overview of the user's synced HubSpot data: which portals they have connected, how many contacts and companies came from each, and when each was last synced.

Look up a person or company in the user's connected HubSpot CRM, live, by email address, domain, or name.

Read one internal email that arrived at tickets@, by the intake_id named in the triggering event.

Record what became of an intake email when nothing goes to Linear: `skipped_fyi` for a real message that is not work (a heads-up, a thank-you, a status note, a receipt), `skipped_noise` for automated mail that slipped through, `needs_review` when you cannot decide or a Linear tool kept failing.

Answer the teammate who sent an email to the tickets address directly, threaded onto their message: one or two plain sentences naming the issue you filed or added their email to, with its link.

What the user has connected, and what they could connect.

The URL that starts connecting one integration, for surfaces that cannot render a card (Slack, SMS, email).

Disconnect one connected account.

Read an invoice PDF the user uploaded and return its fields: supplier, invoice number, dates, currency, subtotal, tax, total, PO number, payment terms, and every line item.

The open Linear projects and the area labels an issue may carry, with their descriptions, plus the rules: the category label (Bug, Feature, Improvement; a question gets none) and the from-email provenance are set for you; you choose at most one project and up to two area labels, copying names exactly, and null or none is the common right answer.

Find issues that may already track the same work.

One issue by identifier (YOU-142): title, description, state, labels, project and url.

File the email behind intake_id as a new Linear issue.

The email behind intake_id is the same work an existing issue already tracks: add its new evidence to that issue as a comment, attributed to the person who wrote in, and link the email to the issue.

Mark two issues as related (or one as a duplicate of the other) so triage sees them together.

Search the user's own LinkedIn connections by name, company, or job title.

Get the full profile for one of the user's LinkedIn connections: work history, education, skills, and their About summary.

Ask a free-form question about the user's LinkedIn connections that the other tools can't express: aggregates and rankings ('which companies do I know the most people at?'), date ranges ('who did I connect with in 2023?'), location filters ('my connections in Boston'), or several conditions at once ('founders in New York I connected with this year').

Ask a question about the user's LinkedIn invitations — the requests they sent and received.

Overview of the user's imported LinkedIn data: how many connections, invitations and messages they have, when it was last imported, and the companies they know the most people at.

The user's own LinkedIn posts with engagement numbers (reactions, likes, comments, shares): newest first by default, their earliest with sort='oldest', or their best-performing with sort='top'.

The user's LinkedIn post analytics from LinkedIn's own API (their connected account) — impressions, unique members reached, reactions, comments, and reshares.

Overview of the user's imported LinkedIn messages (DMs): how many messages and conversations they have, the date range covered, and how many they sent versus received.

The people the user has exchanged the most LinkedIn messages with, most-messaged first, with how many messages and when they last spoke.

Search public LinkedIn posts by keywords and store the results in the user's brain automatically — do not re-save them with graph tools.

The raw material for an engagement analysis of the user's most recent LinkedIn posts: per-post stats, a sample of the actual comments left on them (who said what), and the LinkedIn headlines of everyone who engaged.

People in the user's network who have moved to a different company since we last looked, newest first, with where they were and where they are now.

Send a short text message (iMessage/SMS) to the user's own phone — the number they verified on the iMessage integration.

Turn the recurring emails YouSpot itself sends the user off or back on, when they ask to stop getting one, unsubscribe, or resume it.

List the Obsidian vaults the user has synced into their Second Brain: note counts, the folders each vault holds, its most-used tags, and when it last synced.

Search the notes synced from the user's Obsidian vault, by keyword and by meaning, and get back where each one lives in the vault with an excerpt around the match.

Browse the user's synced Obsidian notes without a search term — most recently changed first, optionally within one vault, one folder, or one tag.

Read one note from the user's Obsidian vault in full: its markdown, frontmatter, tags, the notes and brain objects its wikilinks point at, and the notes that link back to it.

Update the user's own profile fields when they ask: timezone, name, headline, company website, LinkedIn URL or X handle.

Search for companies by describing them in plain English — the same engine behind the ProspectFinder app.

Search the Slack messages saved to the user's brain — by keyword and by meaning — newest first.

The saved messages of one Slack thread, oldest first: the parent and every reply the brain holds.

The Slack channels and DMs the user's brain knows about, per connected workspace, with whether each one is being saved (ingest) and how many messages are stored.

Post a message to a Slack channel or DM as YouSpot, optionally as a reply in a thread.

Add an emoji reaction (by name, e.g.

The user's own tweets, newest first, from their connected X (Twitter) accounts — text, engagement metrics (likes, replies, retweets, impressions), date, and link.

The posts the user bookmarked on X (Twitter), newest first — author @handle, text, date, engagement, and link, plus an author_counts rollup of how often each author appears across ALL their bookmarks (use it directly for questions like 'whose posts do I bookmark most?').

Live profile stats for the user's connected X (Twitter) accounts — name, @handle, follower count, following count, and total tweets, fresh from the X API.

Accounts the user follows on X (Twitter), from the synced follow graph — name, @handle, and bio.

Search recent public posts on X (Twitter) by keywords — the X API covers roughly the last week.

Fetch and read the content of one public web page by URL — use when the user asks what a page or article says, or you need to read a prospect's or company's own site before a conversation.

Search the open web and get back titles, URLs and snippets.

Search YouSpot's public pages and developer docs.

Read one public page in full, as markdown.

Every public page that can be read, with its title and one-line description.

What this user should deal with right now, computed from their sent mail, their calendar and their LinkedIn export: people who went quiet after real correspondence, people they are meeting this week, who they write to most, invitations nobody answered, and the shape of their network.

The Linear issues completed in one Monday-to-Sunday week (Eastern time), last week by default, that have not been announced in a changelog and do not carry the no-changelog label.

Research one specific company in depth — the same engine behind the CompanyResearch.ai app.

Recent news and hiring movement for companies the user already knows, several at once, split into what is new since the last check and what was already reported.

Look up the public registration (WHOIS) record for a website domain: who registered it, which registrar holds it, when it was created and last updated, when it expires, its nameservers, and its registry status codes.

Estimate what a domain name is worth (the /domainvalue appraisal): an estimated market value in dollars with the signals behind it — comparable sales, marketplace listings, an appraisal model, SEO data.

Read the content of a file the user uploaded — use this when the answer may live in a document in their Second Brain: schedules, itineraries, contracts, exports, scans.

Search the user's connected Gmail mailboxes and return matching messages, newest first — from, to, subject, date, and a short snippet of the body.

Fetch one Gmail message by its id from the user's connected mailbox, including the full plain-text body (rare header-only connections get headers and the snippet instead).

List the labels in the user's connected Gmail mailboxes — system labels (INBOX, STARRED, ...) and the user's own labels, with their ids.

List events from the user's connected Google Calendar, ordered by start time — summary, start/end, location, organizer, attendees and their RSVP status, and a meeting link when there is one.

List the calendars in the user's connected Google account(s) — name, id, whether it's the primary, and the user's access role.

List objects in the user's graph, newest first, with counts by type.

Get one object from the user's graph, with the objects connected to it (its edges, e.g.

Search the user's graph by matching a term against object names and descriptions — plus semantic matching over text-bearing objects (notes, facts, posts, links, files, emails), so a search finds what the user means, not just exact words.

How two objects in the user's graph are connected: the shortest chain of real relationships between them, up to 3 hops, e.g.

The objects in the user's graph directly connected to BOTH of two given objects — mutual contacts between two people, shared people between two companies.

The objects in the user's graph closest in MEANING to one object — nearest neighbours by stored embedding, so it finds related notes, facts, links, files, and posts even when no words match.

Read back objects a skill wrote earlier, filtered precisely.

People the user has not written to in a while, quietest first, with the date of the last thing they sent.

Who introduced the people in the user's graph, aggregated per introducer, so a skill can see which relationships actually produce work rather than which are warm.

Query the user's HubSpot contacts — the people synced from the HubSpot portals they've connected.

Query the user's HubSpot companies — the companies synced from the HubSpot portals they've connected.

Overview of the user's synced HubSpot data: which portals they have connected, how many contacts and companies came from each, and when each was last synced.

Look up a person or company in the user's connected HubSpot CRM, live, by email address, domain, or name.

Read one internal email that arrived at tickets@, by the intake_id named in the triggering event.

What the user has connected, and what they could connect.

The URL that starts connecting one integration, for surfaces that cannot render a card (Slack, SMS, email).

Read an invoice PDF the user uploaded and return its fields: supplier, invoice number, dates, currency, subtotal, tax, total, PO number, payment terms, and every line item.

The open Linear projects and the area labels an issue may carry, with their descriptions, plus the rules: the category label (Bug, Feature, Improvement; a question gets none) and the from-email provenance are set for you; you choose at most one project and up to two area labels, copying names exactly, and null or none is the common right answer.

Find issues that may already track the same work.

One issue by identifier (YOU-142): title, description, state, labels, project and url.

Search the user's own LinkedIn connections by name, company, or job title.

Get the full profile for one of the user's LinkedIn connections: work history, education, skills, and their About summary.

Ask a free-form question about the user's LinkedIn connections that the other tools can't express: aggregates and rankings ('which companies do I know the most people at?'), date ranges ('who did I connect with in 2023?'), location filters ('my connections in Boston'), or several conditions at once ('founders in New York I connected with this year').

Ask a question about the user's LinkedIn invitations — the requests they sent and received.

Overview of the user's imported LinkedIn data: how many connections, invitations and messages they have, when it was last imported, and the companies they know the most people at.

The user's own LinkedIn posts with engagement numbers (reactions, likes, comments, shares): newest first by default, their earliest with sort='oldest', or their best-performing with sort='top'.

The user's LinkedIn post analytics from LinkedIn's own API (their connected account) — impressions, unique members reached, reactions, comments, and reshares.

Overview of the user's imported LinkedIn messages (DMs): how many messages and conversations they have, the date range covered, and how many they sent versus received.

The people the user has exchanged the most LinkedIn messages with, most-messaged first, with how many messages and when they last spoke.

Search public LinkedIn posts by keywords and store the results in the user's brain automatically — do not re-save them with graph tools.

The raw material for an engagement analysis of the user's most recent LinkedIn posts: per-post stats, a sample of the actual comments left on them (who said what), and the LinkedIn headlines of everyone who engaged.

People in the user's network who have moved to a different company since we last looked, newest first, with where they were and where they are now.

Send a short text message (iMessage/SMS) to the user's own phone — the number they verified on the iMessage integration.

List the Obsidian vaults the user has synced into their Second Brain: note counts, the folders each vault holds, its most-used tags, and when it last synced.

Search the notes synced from the user's Obsidian vault, by keyword and by meaning, and get back where each one lives in the vault with an excerpt around the match.

Browse the user's synced Obsidian notes without a search term — most recently changed first, optionally within one vault, one folder, or one tag.

Read one note from the user's Obsidian vault in full: its markdown, frontmatter, tags, the notes and brain objects its wikilinks point at, and the notes that link back to it.

Search for companies by describing them in plain English — the same engine behind the ProspectFinder app.

Search the Slack messages saved to the user's brain — by keyword and by meaning — newest first.

The saved messages of one Slack thread, oldest first: the parent and every reply the brain holds.

The Slack channels and DMs the user's brain knows about, per connected workspace, with whether each one is being saved (ingest) and how many messages are stored.

The user's own tweets, newest first, from their connected X (Twitter) accounts — text, engagement metrics (likes, replies, retweets, impressions), date, and link.

The posts the user bookmarked on X (Twitter), newest first — author @handle, text, date, engagement, and link, plus an author_counts rollup of how often each author appears across ALL their bookmarks (use it directly for questions like 'whose posts do I bookmark most?').

Live profile stats for the user's connected X (Twitter) accounts — name, @handle, follower count, following count, and total tweets, fresh from the X API.

Accounts the user follows on X (Twitter), from the synced follow graph — name, @handle, and bio.

Search recent public posts on X (Twitter) by keywords — the X API covers roughly the last week.

Fetch and read the content of one public web page by URL — use when the user asks what a page or article says, or you need to read a prospect's or company's own site before a conversation.

Search the open web and get back titles, URLs and snippets.

What this user should deal with right now, computed from their sent mail, their calendar and their LinkedIn export: people who went quiet after real correspondence, people they are meeting this week, who they write to most, invitations nobody answered, and the shape of their network.

The Linear issues completed in one Monday-to-Sunday week (Eastern time), last week by default, that have not been announced in a changelog and do not carry the no-changelog label.

Save the week's changelog draft for an editor to review and publish.

Research one specific company in depth — the same engine behind the CompanyResearch.ai app.

Recent news and hiring movement for companies the user already knows, several at once, split into what is new since the last check and what was already reported.

Look up the public registration (WHOIS) record for a website domain: who registered it, which registrar holds it, when it was created and last updated, when it expires, its nameservers, and its registry status codes.

Estimate what a domain name is worth (the /domainvalue appraisal): an estimated market value in dollars with the signals behind it — comparable sales, marketplace listings, an appraisal model, SEO data.

Send an email to the signed-in user at their own account email address.

Read the content of a file the user uploaded — use this when the answer may live in a document in their Second Brain: schedules, itineraries, contracts, exports, scans.

Download a file from a public http(s) URL and store it in the user's Second Brain as a file object — use when the user shares a direct link to a PDF, image, spreadsheet, or other file and asks to save, download, or keep it.

Import every contact or company from a file the user uploaded — a CSV or spreadsheet export, a .vcf of contacts, or a zip.

Search the user's connected Gmail mailboxes and return matching messages, newest first — from, to, subject, date, and a short snippet of the body.

Fetch one Gmail message by its id from the user's connected mailbox, including the full plain-text body (rare header-only connections get headers and the snippet instead).

List the labels in the user's connected Gmail mailboxes — system labels (INBOX, STARRED, ...) and the user's own labels, with their ids.

Create a DRAFT email in the user's connected Gmail mailbox, addressed to anyone — 'draft an email to jane@acme.com about X'.

Archive one Gmail message — it leaves the inbox but stays in All Mail, fully recoverable.

List events from the user's connected Google Calendar, ordered by start time — summary, start/end, location, organizer, attendees and their RSVP status, and a meeting link when there is one.

List the calendars in the user's connected Google account(s) — name, id, whether it's the primary, and the user's access role.

Prepare or queue one calendar event through the shared suggestion service.

Update one Google Calendar event — change its title (summary), description, location, or start/end times.

List objects in the user's graph, newest first, with counts by type.

Get one object from the user's graph, with the objects connected to it (its edges, e.g.

Rename or re-describe an object in the user's graph, or set any of its type-specific fields: a contact's phone, email, headline or location, a company's funding stage, and so on.

Search the user's graph by matching a term against object names and descriptions — plus semantic matching over text-bearing objects (notes, facts, posts, links, files, emails), so a search finds what the user means, not just exact words.

Create a new object in the user's graph.

Set up a standing search the user wants watched — 'track LinkedIn posts that mention hubspot', 'track tweets mentioning @dharmesh', 'watch acme.com/pricing for changes'.

Connect two objects in the user's graph with a directed edge — e.g.

Delete an object from the user's graph.

Delete EVERY object of one type from the user's graph, however many there are: what to reach for when they ask to clear out a whole category ('delete all my HubSpot contacts') rather than one record.

Record one dated touchpoint with someone in the user's graph — an email exchanged, a call, a meeting, a LinkedIn touch, or a manually noted contact — so 'when did I last talk to them?' has an answer.

Merge two duplicate records in the user's graph into one — person or company only.

Permanently delete one object from the user's graph, along with every connection touching it.

Delete one connection between two objects in the user's graph — the edge from_object_id -> to_object_id of the given connection_type, nothing else; both objects stay.

How two objects in the user's graph are connected: the shortest chain of real relationships between them, up to 3 hops, e.g.

The objects in the user's graph directly connected to BOTH of two given objects — mutual contacts between two people, shared people between two companies.

The objects in the user's graph closest in MEANING to one object — nearest neighbours by stored embedding, so it finds related notes, facts, links, files, and posts even when no words match.

Set a dated follow-up about an object in the user's graph — 'follow up with Jane in March'.

Read back objects a skill wrote earlier, filtered precisely.

People the user has not written to in a while, quietest first, with the date of the last thing they sent.

Who introduced the people in the user's graph, aggregated per introducer, so a skill can see which relationships actually produce work rather than which are warm.

Query the user's HubSpot contacts — the people synced from the HubSpot portals they've connected.

Query the user's HubSpot companies — the companies synced from the HubSpot portals they've connected.

Overview of the user's synced HubSpot data: which portals they have connected, how many contacts and companies came from each, and when each was last synced.

Look up a person or company in the user's connected HubSpot CRM, live, by email address, domain, or name.

Read one internal email that arrived at tickets@, by the intake_id named in the triggering event.

Record what became of an intake email when nothing goes to Linear: `skipped_fyi` for a real message that is not work (a heads-up, a thank-you, a status note, a receipt), `skipped_noise` for automated mail that slipped through, `needs_review` when you cannot decide or a Linear tool kept failing.

Answer the teammate who sent an email to the tickets address directly, threaded onto their message: one or two plain sentences naming the issue you filed or added their email to, with its link.

What the user has connected, and what they could connect.

The URL that starts connecting one integration, for surfaces that cannot render a card (Slack, SMS, email).

Disconnect one connected account.

Read an invoice PDF the user uploaded and return its fields: supplier, invoice number, dates, currency, subtotal, tax, total, PO number, payment terms, and every line item.

The open Linear projects and the area labels an issue may carry, with their descriptions, plus the rules: the category label (Bug, Feature, Improvement; a question gets none) and the from-email provenance are set for you; you choose at most one project and up to two area labels, copying names exactly, and null or none is the common right answer.

Find issues that may already track the same work.

One issue by identifier (YOU-142): title, description, state, labels, project and url.

File the email behind intake_id as a new Linear issue.

The email behind intake_id is the same work an existing issue already tracks: add its new evidence to that issue as a comment, attributed to the person who wrote in, and link the email to the issue.

Mark two issues as related (or one as a duplicate of the other) so triage sees them together.

Search the user's own LinkedIn connections by name, company, or job title.

Get the full profile for one of the user's LinkedIn connections: work history, education, skills, and their About summary.

Ask a free-form question about the user's LinkedIn connections that the other tools can't express: aggregates and rankings ('which companies do I know the most people at?'), date ranges ('who did I connect with in 2023?'), location filters ('my connections in Boston'), or several conditions at once ('founders in New York I connected with this year').

Ask a question about the user's LinkedIn invitations — the requests they sent and received.

Overview of the user's imported LinkedIn data: how many connections, invitations and messages they have, when it was last imported, and the companies they know the most people at.

The user's own LinkedIn posts with engagement numbers (reactions, likes, comments, shares): newest first by default, their earliest with sort='oldest', or their best-performing with sort='top'.

The user's LinkedIn post analytics from LinkedIn's own API (their connected account) — impressions, unique members reached, reactions, comments, and reshares.

Overview of the user's imported LinkedIn messages (DMs): how many messages and conversations they have, the date range covered, and how many they sent versus received.

The people the user has exchanged the most LinkedIn messages with, most-messaged first, with how many messages and when they last spoke.

Search public LinkedIn posts by keywords and store the results in the user's brain automatically — do not re-save them with graph tools.

The raw material for an engagement analysis of the user's most recent LinkedIn posts: per-post stats, a sample of the actual comments left on them (who said what), and the LinkedIn headlines of everyone who engaged.

People in the user's network who have moved to a different company since we last looked, newest first, with where they were and where they are now.

Send a short text message (iMessage/SMS) to the user's own phone — the number they verified on the iMessage integration.

Turn the recurring emails YouSpot itself sends the user off or back on, when they ask to stop getting one, unsubscribe, or resume it.

List the Obsidian vaults the user has synced into their Second Brain: note counts, the folders each vault holds, its most-used tags, and when it last synced.

Search the notes synced from the user's Obsidian vault, by keyword and by meaning, and get back where each one lives in the vault with an excerpt around the match.

Browse the user's synced Obsidian notes without a search term — most recently changed first, optionally within one vault, one folder, or one tag.

Read one note from the user's Obsidian vault in full: its markdown, frontmatter, tags, the notes and brain objects its wikilinks point at, and the notes that link back to it.

Update the user's own profile fields when they ask: timezone, name, headline, company website, LinkedIn URL or X handle.

Search for companies by describing them in plain English — the same engine behind the ProspectFinder app.

Search the Slack messages saved to the user's brain — by keyword and by meaning — newest first.

The saved messages of one Slack thread, oldest first: the parent and every reply the brain holds.

The Slack channels and DMs the user's brain knows about, per connected workspace, with whether each one is being saved (ingest) and how many messages are stored.

Post a message to a Slack channel or DM as YouSpot, optionally as a reply in a thread.

Add an emoji reaction (by name, e.g.

The user's own tweets, newest first, from their connected X (Twitter) accounts — text, engagement metrics (likes, replies, retweets, impressions), date, and link.

The posts the user bookmarked on X (Twitter), newest first — author @handle, text, date, engagement, and link, plus an author_counts rollup of how often each author appears across ALL their bookmarks (use it directly for questions like 'whose posts do I bookmark most?').

Live profile stats for the user's connected X (Twitter) accounts — name, @handle, follower count, following count, and total tweets, fresh from the X API.

Accounts the user follows on X (Twitter), from the synced follow graph — name, @handle, and bio.

Search recent public posts on X (Twitter) by keywords — the X API covers roughly the last week.

Fetch and read the content of one public web page by URL — use when the user asks what a page or article says, or you need to read a prospect's or company's own site before a conversation.

Search the open web and get back titles, URLs and snippets.