ClawLink
TL;DR
| Question | Answer |
|---|---|
| What does it do? | Your agent reads the recent posts of a public LinkedIn profile through ClawLink and groups them into the topics that person keeps coming back to. |
| Who is it for? | Salespeople, recruiters and founders preparing for a call with someone they have not met. |
| What do I connect? | Nothing. It reads public data with ClawLink's own provider. |
| What does it cost? | About $0.075 of ClawLink credit per run. New accounts get $0.50 free. |
| Does it work? | Yes. We ran it on 2026-10-03; the results are below. |
| Which agents? | OpenClaw, Hermes, Claude, Codex, ChatGPT and any MCP client connected to ClawLink. |
How do you try it?
- Set up ClawLink once. Add it to your agent from the install page. This job needs no connected app.
- Send this prompt to your agent. Click the card to copy it.
It works the same in OpenClaw, Hermes, Claude and Codex.
How does the agent do it?
The agent makes one call through ClawLink. You do not pick the tools: the agent finds them by searching ClawLink, reads their input schema and runs them.
| Step | Tool | What it does | Price |
|---|---|---|---|
| 1 | linkedindata_user_posts | Returns a public profile's recent posts with text, date and reactions. | $0.075 |
What happened when we ran it?
We sent this job through ClawLink on 2026-10-03. These are the real calls and what came back, not an example.
| Call | Input and result | Time | Cost |
|---|---|---|---|
linkedindata_user_posts | linkedin.com/in/satyanadella, 13 posts shown | 13.5 s | $0.075 |
What the data showed:
- Only 2 of the 13 posts were original: the Copilot relaunch on Sep 25 (13,049 reactions) and a post on keeping superintelligence under human control on Sep 13 (12,436 reactions, 1,002 comments).
- The other 11 were reshares with a comment: LinkedIn Hiring Assistant, Fabric IQ, a quantum computing center, new models in Foundry and a datacenter.
- The topics group into three: Copilot and agents, AI safety and control, and Microsoft's infrastructure.
How do you write the prompt?
- Paste the profile URL. linkedin.com/in/<name> is the most reliable input.
- Ask for topics with examples. "Main topics, one example post each" gives you something to mention in the meeting.
- Combine with the profile. Ask for their current role too; it is a separate, cheap call.
What can go wrong?
- This call costs more. LinkedIn post data is the most expensive data tool in this list: $0.075 per call, about 25 times a TikTok call. Run it for people you will actually meet.
- Reposts look like posts. In our run, 11 of the 13 posts were reshares of other people's posts, and their reaction counts belong to the original author. Ask the agent to separate original posts from reshares.
- It is slow. The call took 13.5 seconds. Our first attempt timed out in the client and was still charged, so do not retry in a loop.
- Company pages are different. For a company, ask for company posts; that is another tool.
How does this compare with other ways to do it?
| Option | How it works | Cost | Best for |
|---|---|---|---|
| ClawLink + your agent | One prompt, topics in the chat | $0.075 per run | Meeting prep in your agent |
| Read the profile | Scroll the activity tab | Free with a login | One person, with time |
| Sales Navigator | LinkedIn's sales product | Monthly seat | Teams that prospect all day |
Frequently asked questions
Do I need a LinkedIn account?
No. This job reads public LinkedIn data through ClawLink's own data provider, so there is nothing to connect. It runs on your ClawLink credit; every new account gets $0.50 of free credit on its first data call.
Can it post on LinkedIn for me?
Yes, but that is the LinkedIn app with your account connected. See the use case on drafting a LinkedIn post.
Does the person see that I looked?
No. The data is read without your LinkedIn account.
Does it work for any profile?
For public profiles. Profiles that limit visibility return less.
Why does it cost more than other data calls?
Our provider charges more for LinkedIn post data. ClawLink adds the same markup to every data tool.