Digest the sources you watch into Slack
Reads the pages you name each morning, keeps only the lines matching your brief, and posts them to Slack with their source.
What it does
The integration steps this workflow runs, in the order it first runs them.
- 1
Jina AIRead url - 2
AnthropicGenerate model response - 3
SlackSend message
How it works
Everything the template sets up, and what to fill in before the first run.
You name the pages worth watching - a vendor's changelog, a regulator's notices page, a competitor's blog, an industry index - and describe what you actually care about. Every morning this workflow reads each page, keeps only the lines that match your brief, and posts them to one Slack channel with the address they came from.
The filtering is the point, and so is what it refuses to do. Every line posted is quoted from the page word for word: a line that does not appear on the page is dropped and counted, never posted. The workflow adds no summary, no ranking and no opinion about anyone it reads about, so what lands in Slack is the source's own wording and a link, and the judgement stays yours.
Each run is bounded - it reads at most the number of sources you set and posts at most the number of lines you set - and it posts exactly one message, including on the days when nothing matched, so silence is never ambiguous. A source that cannot be read is reported by its host name only, never by the full address you entered, in case that address carries a key.
Set it up with your list of page addresses in 'sourceUrls' (separated by commas), what matters to you in 'readerBrief', and the ID of the Slack channel to post in. There is no memory between runs, so a page that says the same thing tomorrow will be quoted again tomorrow.
Start from a workflow that already works.
Add "Digest the sources you watch into Slack" to your workspace, connect its apps, and make it yours. No credit card required.
Free plan available · No credit card required
