From Intelligence to post: write about the topics your market follows

How a watch finds your market's trends on LinkedIn and in RSS feeds, and how to turn one into a LinkedIn post to review and schedule.
Content4 min readYovanah Naiken
A radar and a trend line leading to a post being written.

A watch follows a topic in RSS feeds and on LinkedIn. It finds the useful trends and writes a synthesis that cites its sources. From a trend, you have a post draft written, you revise it, then you schedule it or publish it.

Draft for reviewLinkedIn

Sovereign cloud: three questions to ask before migrating.

Before choosing infrastructure, clarify what you want to control: your data, costs or reliance on a provider. The answers shape the project.

Your expertise makes the difference
Illustration — fictional data

Create a watch and choose its sources

A watch has a "Topic", "Keywords" and at least one source. You can also give it a "Target" so that the relevance of trends is judged against an audience. This choice is optional.

There are two kinds of sources:

  • RSS feeds. One RSS or Atom feed address per line. Each address is read once when you save, to check that it works. RSS feeds do not use LinkedIn reads.
  • LinkedIn sources. They need a connected LinkedIn account. Each source reads the posts from the past week, 20 at most per run.

The available LinkedIn sources:

SourceWhat it reads
KeywordsThe posts that contain your keywords, most relevant first.
NetworkThe same posts, limited to your connections and the people you follow.
AuthorsThe latest posts of the people or companies you follow, 10 authors at most per watch.

The "Home feed" source is planned. It is not turned on in production today.

Runs and their cost

A run reads all the sources of the watch, scores each item found and produces a report. A first run starts when the watch is created.

ActionCost
Read the RSS sources0 credits
Read the LinkedIn sources of a run5 credits, only if LinkedIn answers
Report of a run20 credits, only if signals are found
Search for a LinkedIn author to follow5 credits

The "Relaunch" button reads the sources again and produces a new report. It shows the cost before you click. The daily run relaunches the watch every night, once a day at most. It is not turned on at creation. Its maximum cost is 25 credits per day with a LinkedIn source, 20 without. One credit is worth one euro cent.

The "Intelligence" screen shows two blocks:

  • the "Synthesis": a dated report that cites its sources;
  • the "Detected trends": each trend has a relevance (high, medium, low) and a source. For a LinkedIn post, it also shows its reactions, comments and reposts at the time it was read.

You sort the trends by "Relevance" or by "Engagement". The "Cited" badge marks a trend used in the synthesis. The detail of a trend shows "What the source says", "Why it is relevant", the "Entities" mentioned, the source and the detection date.

The text of the sources is written by other people. It is extracted and summarized before it is shown or used by the AI.

From trend to post draft

From a trend, click "Suggest a post". The "Publish" screen opens with an instruction already filled in. You complete it with your expertise, then click "Generate". The draft costs 15 credits. Nothing is drafted before this click.

The draft keeps the link to its trend ("Written from the trend: …"). The trend shows the posts written from it.

To revise, write an instruction in "Revise" or click a quick instruction: "Shorter", "More direct", "End with a question", "No hashtags". Each revision costs 15 credits and adds a new version. Earlier versions are kept.

A post is at most 3,000 characters. It can carry up to 9 images, or one PDF, or one MP4 video. The preview shows where LinkedIn cuts the text with "…see more".

Schedule or publish

"Schedule" publishes the post on the chosen date and time. The post gets the status "Scheduled". "Unschedule" turns it back into a draft. The screen recommends one slot per working day at most.

"Publish on LinkedIn" publishes right away, after a confirmation. Publishing cannot be undone: the post goes out on your LinkedIn account and reaches your network. To remove a published post, delete it from LinkedIn.

Scheduling and publishing cost no credits.

Your editorial calendarExample

A week of publishing

Mon
Tue
Wed
Thu
Fri

Post preview

Sovereign cloud: three questions to ask before migrating.

Illustrative calendar · select a post

Illustration — fictional data

In practice

Take a fictional consulting firm that wants to post every week about digital sovereignty.

In the assistant, "Intelligence" tab:

Follow LinkedIn posts that mention “digital sovereignty” or “trusted cloud”.

Collection runs in the background. The trends are not immediate. Later:

Show me my trends.
Explain the first trend.

The assistant cites the source address of each trend. Then, "Publish" tab:

Draft a LinkedIn post for my Target « Mid-market CIOs » on the “trusted cloud” trend: a lessons-learned post, direct tone, no jargon.
Revise my latest draft: make it shorter and the hook more direct.

The assistant drafts and revises. It does not schedule and does not publish. Open the draft on the "Publish" screen, review it, then click "Schedule" or "Publish on LinkedIn".

Cost of this example: one watch run with a LinkedIn source, at most 25 credits; one draft, 15 credits; one revision, 15 credits. That is at most 55 credits.

Read in the guide

The guide chapters that detail what this article describes.

Intelligence
A watch follows a topic on RSS feeds and on LinkedIn.
Publish
The "Publish" screen is where you prepare and publish your LinkedIn posts.

Prepare your prospecting with the team

Book a 15-minute call with the team to see the platform on your case.
Reactions to a post turning into people's profiles.
Prospecting · Content

Turn the people who reacted to a post into qualified prospects

Import the people who reacted to a LinkedIn post found by a watch, evaluate them against a Target, then contact them.
4 min read