Automate a daily Hacker News mention monitor for your product

Mentions on Hacker News are easy to miss because you only see them when you search. A scheduled agent queries the public search API for your product name and domain each day and drafts a digest that its department head reviews and you approve.

What you’ll set up

Connections

Works from public sources: Hacker News Search API (Algolia), search_by_date endpoint

Upgrades

Digest delivery (channel or inbox)

Delivers the approved digest to your channel or inbox.

Inputs

Product names and domains to watch · Required

List, no default

Minimum points for stories · Optional

Number, default 1

Ready by · Required

Time, default 08:00

Brief · Required

Text, prefilled and editable during setup.

Runs

Runs every day at 08:00

Done by Market researcher

You approve before anything goes out.

Set up this job

You approve every report · Free to start

How it runs

One agent does the work. Its department head reviews it, then you approve.

  1. 1Market researcher

    Runs daily at 08:00 and prepares the report from your connected sources.

  2. 2CMO · Review

    The department head reviews the report before it reaches you.

  3. 3You

    You approve before anything goes out.

What you get

Sample, not live dataSample daily mention digest (Sample, not live data)

Sample, not live data. The product, authors and counts are invented.

Hacker News mentions for "exampleapp", Tuesday (sample)

2 new mentions, 1 story and 1 comment.

TypeWherePointsCommentsSummary
Story"Ask HN: tools for invoice reminders?"1812Two commenters name exampleapp
CommentThread on bookkeepingn/an/aReports a bug with CSV import

Worth a look (needs your approval)

  1. Read the bug report; reply from your own account if you choose.

Why mentions get missed

A thread on Hacker News can rise and fall in a day. If your product is named in a comment, the author rarely tells you. The useful moments are small: a user reports a bug in public, a buyer asks for alternatives, a competitor is compared with you. Checking by hand works for a week and then stops, because the search is dull and the payoff is irregular. A daily digest makes the check cheap to keep.

How the scheduled job works

You add the job with your product name and domain. Each day a scheduled agent calls the public Hacker News search endpoint sorted by date, searching stories and comments separately through the tags filter, limited to items created since the previous run. Results carry a title or text, url, author, points, comment count and creation time where they apply. The agent keeps items that really contain your name or domain, drops repeats from earlier days, and records points and discussion size so you can see which threads matter. It reads and reports, and posts nothing.

Review and approval

The CMO agent, as department head, reviews the digest before it goes out: are the matches real, is a story kept apart from a comment, is any suggested action reasonable. Then you approve, edit or skip it, and nothing is sent until you do. Run it for two weeks and compare the digest with a manual search so you know it misses nothing you care about.

What to do with a mention

Most mentions need nothing, and a few need a careful human reply. A bug report deserves a fix and, if you choose, a short public answer from your own account. A comparison thread shows how buyers describe the problem, which is useful for your own copy. Hacker News guidelines ask people not to use the site primarily for promotion, so the digest is for listening, not for planning campaigns. Keep terms specific, because short product names match unrelated stories, and tighten the list whenever a digest fills with noise.

Questions

Start with one report

Set up this job

You approve every report · Free to start