Research one company on LinkedIn, using one prompt
Last updated 2026-09-01 · Tested on a real LinkedIn account
Short answer
Build a research brief on one company, and diff it against last quarter's. You ask in plain English. Your AI assistant runs the LinkedIn CLI for you, so you never type a command yourself.
What do I actually type?
This one sentence. That is the whole thing.
“Refresh the account briefs for the twenty accounts in `qbr-q3.txt`. Keep last quarter's file for each. Write this quarter's alongside it as `briefs/<account>-2026Q3.md`. Three short paragraphs per file: buying committee shape, current hiring in the platform function, and last-fifteen-day activity from the named champion. Nothing from the About page, no follower counts, no news older than a month.”
How does it work, step by step?
Paste these one at a time. Each one is written in normal English — no command names, no flags.
We gave these exact prompts to a real AI assistant and wrote down every command it ran. It chose 5 commands: list-linkedin-accounts, search-people-v2, search-jobs, get-latest-posts, search-companies. Nobody told it which ones to use.
“Refresh the account briefs for the twenty accounts in `qbr-q3.txt`. Keep last quarter's file for each. Write this quarter's alongside it as `briefs/<account>-2026Q3.md`. Three short paragraphs per file: buying committee shape, current hiring in the platform function, and last-fifteen-day activity from the named champion. Nothing from the About page, no follower counts, no news older than a month.”
One sentence, twenty accounts. Underneath, the assistant is running about five profile reads and a jobs search per account. The output is written to disk, dated in the filename, with no chat-window artefact.
your assistant picks this“Diff each brief against last quarter's version. For each account, list what is new, what has gone away, and what is unchanged. Rank the twenty by how much moved.”
That is a question a chat window cannot answer without being handed both files. Given the folder, the assistant can. And the ranking is what turns a folder into a QBR agenda: the accounts that moved most are the ones that get discussed first.
your assistant picks this“For the five that moved most, tell me what the movement means and what the CSM should raise in the account plan. Cite the line in which brief you inferred that from.”
The citation clause is the load-bearing one. A brief with sources can be checked; one without them is a rumour with good formatting. Ask the assistant to attribute its conclusions to specific lines in specific files and it stops filling the gaps from general knowledge.
your assistant picks thisWhat it printed when we ran it
Not a mock-up. This is the actual run: the assistant was given the prompts above and nothing else, and these are the 5 distinct commands it chose from the catalogue. It ran read-only on a real LinkedIn account — nothing was sent, posted or invited.
Can I make it run on its own?
Yes. Add one more sentence and it keeps happening without you. This is the part a chat window cannot do — a saved job runs on the days you are busy.
“Do this every quarter, seven days before the QBR. And every fortnight in between, refresh only the hiring paragraph and the champion-activity paragraph — leave the committee shape alone unless something explicitly changed.”
How many LinkedIn actions does this use?
LinkedIn limits how much any account can do in a day. These are the real numbers, and your assistant checks what is left before it starts.
- Profile views: 120 a day, reset at midnight UTC. About five profile reads per account — the champion and four members of the committee — so twenty accounts is a hundred reads. A third of the daily budget is forty. A hundred is not a third; it is most of the budget, and it needs a day of its own.
- Searches: 1,000 calls a day, per search type, billed per page fetched. Twenty accounts spend about a hundred and twenty. Nowhere near the cap.
Watch it instead
4 minutes
Common questions
- What if a brief came back on the wrong company?
- Common with subsidiaries, regional pages and companies renamed after an acquisition. Ask which company page it resolved to first, correct the input file, and re-run just that account.
- What if every champion shows no activity?
- LinkedIn's recent-activity window is fifteen days. If your entire named champion list has been silent for two weeks, the pattern is the list. you have named a set of champions who do not use LinkedIn, and the workflow is telling you so.
- What if it ran out of profile views mid-sweep?
- Ask what it completed, refresh the missing accounts tomorrow, and keep the files for the ones it wrote. Do not restart the whole sweep. the completed files cost budget that would otherwise be spent re-reading pages you already have.
- What if a brief looks impressive but has nothing new in it?
- The assistant filled the gap from general knowledge rather than from the account. Ask for citations. every line has to point at a source. and the padding disappears.
- How many LinkedIn actions does research one company use up?
- Profile views: 120 a day, reset at midnight UTC. About five profile reads per account — the champion and four members of the committee — so twenty accounts is a hundred reads. A third of the daily budget is forty. A hundred is not a third; it is most of the budget, and it needs a day of its own.
How do I set this up?
Once, and it takes about four minutes. After this you only write sentences.
$ npm install -g @connectsafely/cli$ export CONNECTSAFELY_API_KEY=...$ csly list-linkedin-accounts$ export CONNECTSAFELY_ACCOUNT_ID=...$ csly skill installThe package is @connectsafely/cli on npm. You need Node 20 or newer.
Then start your chat with this line, so your assistant uses the CLI instead of trying to open LinkedIn itself and hitting a login page:
“Use the ConnectSafely CLI (csly) for anything that touches LinkedIn. Run csly commands to see what exists, and csly schema before calling one. Don't guess a command name.”
Other things you can do
Try this on your own LinkedIn account
From $10 a month, on the LinkedIn account you already use, with zero ban risk.