The calendar decides who to look up
The event names the guests, which is what makes this automatable at all: no list to maintain, no CRM to keep current. The agent takes the external attendees from the meeting and researches those, which is why the briefing is right even for a meeting booked an hour ago.
“Who am I meeting tomorrow, what do I know about them, and what did we last say?”
“Before my 2pm, brief me on the attendees.”
Three sources on one person
Their LinkedIn profile for who they are now, your mailbox for what was written, your messaging for what was said in passing. Each read is independent, so a provider that is unavailable costs you one source rather than the briefing — which matters when this runs automatically an hour before.
What is still open beats what happened
A summary of past exchanges is mildly useful. The question you actually need answered is what is unresolved: the quote they never responded to, the date nobody confirmed, the question you left. Ask for that explicitly, or you get a chronology instead of a briefing.
Short enough to read walking in
Anything longer than a few lines per person will not be read before a call. Say so in the prompt: three lines, who they are, what is open, one thing to mention. An agent given no length produces a page, and a page five minutes before a meeting is the same as nothing.
An hour ahead, automatically
This is the one worth scheduling: an hour before each meeting, the briefing arrives on WhatsApp or by email. Reading sends nothing, so nothing can go wrong outwardly, and the window means the information is current rather than assembled the night before.
It goes to you, never to the guest
Worth stating plainly because the workflow touches their profile and your threads with them: the output is addressed to you. Nothing is sent to the attendees, nothing is posted, and the research leaves no trace beyond what viewing a profile normally does on your account.
Common questions
Which accounts does it need?
A calendar to know the meetings, plus whichever of LinkedIn, email and messaging you want context from. More accounts means a fuller briefing.
Can it run automatically before each meeting?
Yes, on a schedule or a workflow with a window an hour ahead. Reading sends nothing, so it is safe to automate.
Does the other person see anything?
No. The briefing goes to you; profile views follow your account’s normal behaviour and nothing is sent to the attendees.
What if a provider is down?
Each read is independent, so an unavailable account costs one source rather than the whole briefing.
How LinkedIn works with Nilyo
Connection. Secure hosted sign-in (your LinkedIn credentials go to LinkedIn, never to the agent). Sales Navigator and Recruiter are detected automatically when your account has them.
What your agent can do. People and company search, profile lookup from a name or URL, your network and invitations, private conversations (classic, Sales Navigator, Recruiter inboxes), posts, comments and reactions, job postings and applicants, Recruiter projects.
Pacing and safety. About 100 actions per day per account, profile views and searches included; calls are serialized so an agent can never run LinkedIn requests in parallel.
- Profile URLs are resolved to stable profile IDs before any action.
- Invitations carry an optional note of up to 300 characters.
- Private or restricted profiles return an explicit “not accessible” result instead of a retry loop.
All LinkedIn guides
Related guides
Give Nilyo to your agent.
Paste one setup link. Your agent can guide OAuth, account connection and the first useful action.