Your connections, not a public search
This is not a people search: it reads the relationships your account actually has. The answer is therefore yours alone — two colleagues asking the same question get different lists — and it is the part a scraper cannot produce, because a first-degree connection is a fact about your account, not a public attribute.
“Who do I already know at Stripe?”
“Anyone in my network who used to work at this company?”
A name is not an introduction
Knowing someone appears in your connections is half the answer. The useful follow-up is how well: when you last spoke, whether there is a conversation at all, whether the last message was theirs. The agent can read the thread before you ask for a favour, which is what stops an introduction request landing after two years of silence.
Second degree is a different question
If nobody in your network is there, the next step is who could introduce you — a person you know who knows someone there. That needs the profile of the target, not just your connection list, and it is worth being explicit about: it is a search plus a read, not one lookup.
Then decide, do not send
The output of this question is a shortlist and a judgement call, not an automatic message. Asking the agent to message everyone it found is how an introduction request becomes spam to five colleagues at once. Read what it found, pick one, then ask for the draft.
Cross it with the rest
With a mailbox connected too, the better version of the question is who do I know there and what did we last say — because a connection you emailed last month is a far better route than one you added in 2019 and never spoke to.
“Who do I know at this company, and when did we last exchange anything?”
Ask before the list goes stale
Connections change jobs, and a network answer from last quarter is wrong in a way you only discover mid-conversation. The read is live rather than a cached export, so who you know at a company is true at the moment you ask — which matters most for exactly the people worth an introduction, because they are the ones who move.
Common questions
How is this different from LinkedIn search?
Search looks at the whole platform; this reads your own connections and conversations. The result is specific to your account and is exactly what a public search cannot see.
Does it see second-degree connections?
It can look up the company and its people, then compare with your network, but that is a search plus a read rather than a single lookup — and it counts against the daily action budget.
Will it message them?
Only if you ask. The natural output is a shortlist you choose from; sending to everyone found is how a request for an introduction becomes noise.
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.