Automate a weekly digest of what your watch list posted and how people replied
Reading what a list of people posted, and how others replied, takes real time every week. A scheduled agent reads the text you share and drafts a one-page digest, and its department head reviews it before you approve.
What you’ll set up
Connections
Works from files you share
Inputs
Watch list (names or handles) · Required
List, no default
Topics or product names to flag · Optional
Text, no default
Ready by · Required
Time, default 08:00
Brief · Required
Text, prefilled and editable during setup.
Runs
Runs every Monday at 08:00
Done by Market researcher
Email to new contacts, and follow-ups nobody has answered, waits for your approval by default. Replies in threads a contact has answered, and email to your own team, can send automatically depending on your settings.
You approve every report · Free to start
How it runs
One agent does the work. Its department head reviews it, then you approve.
- 1Market researcher
Runs every Monday at 08:00 and prepares the report from your connected sources.
- 2CMO · Review
The department head reviews the report before it reaches you.
- 3You
Email to new contacts, and follow-ups nobody has answered, waits for your approval by default. Replies in threads a contact has answered, and email to your own team, can send automatically depending on your settings.
What you get
Sample, not live data. Names and posts are invented.
Watch list digest, week of 9 March (sample)
Theme 1: onboarding takes too long (3 posts). Reply from Sam: "we gave up after the second import failed."
Theme 2: pricing page confusion (2 posts). Reply from Jo: "which plan includes the export?"
Notable: Jo asked a direct question that nobody answered.
Needs your approval before it is sent.
Why this job uses text you share
Some sites, such as LinkedIn, restrict automated collection. LinkedIn's User Agreement, for example, bars using software, scripts, robots or crawlers to scrape or copy its services. RFC 9309 says robots.txt rules are not a form of access authorization. For that reason this job does not scrape anything. You share the post text and replies you are entitled to read, by paste or file upload, and the agent works from that.
How the scheduled job works
Each week you keep a watch list: names or handles, plus the posts and replies you pasted or uploaded for that week. The scheduled agent groups the text by person, picks out the recurring themes, and lists the replies that add a fact, an objection or a question. Every item shows its author and a short quote, so you can check it against the original. It also flags anything that mentions your product or a topic you named in the notes field. It reads and summarises. It never posts, replies, follows or messages anyone.
Review and approval
Before the digest reaches you, the department head agent checks it: does each theme have at least two supporting posts, is every quote attributed, and is anything summarised that was not in the text you shared. You then approve, edit or skip the digest, and nothing is delivered to your team until you do. The digest is labelled as AI-written.
Using the digest
Start with the themes, then the notable replies. A reply that repeats across several posts may be a real concern worth answering in your next piece of content. A single sharp objection is worth a direct look at the original thread. If a week's input is thin, the digest says so rather than padding. Over a month you can compare themes week to week and see what people on your list keep returning to.
Questions
Related jobs
Works from public sources: Hacker News Search API (Algolia), search_by_date endpoint
Automate a daily Hacker News mention monitor for your product
A daily list of new Hacker News stories and comments that mention your product or domain.
Connects to: Google Search Console (read) (required)
Weekly SEO report
A Monday report on what moved in search, what slipped and one fix to make, with the numbers recomputed from the raw rows.
Connects to: Google Search Console (read) (required)
Automate a monthly SEO content refresh list from Search Console
A monthly list of pages losing clicks or position, with the queries worth reworking.