SHIP assisted engagement-mining
Where your buyers already talk, with a draft reply
The file
take it and run it.
One markdown file: the goal prompt, the verifier prompt, and the stopping condition. Read it before you run it. MIT licensed, no account, nothing to sign up for.
curl -fsSL https://vibemarketers.ai/loops/engagement-mining.md -o .claude/loops/engagement-mining.mdThe loop
copy it.
Your buyers are already arguing about the problem you solve, in public, today. Nobody on your team is in those threads, usually because finding them is tedious and showing up looks like marketing.
Use it when you are willing to answer a question in public under your own name and get nothing measurable back. If you are not, this loop will feel useless, correctly.
You need nothing but a public search. No account on the surfaces, no credential.
You get one draft per thread, each written to be useful on its own, plus a checklist for whether it should be posted at all.
The gate is structural. This loop has no send path and cannot be given one: its verifier fails if any posting or authentication code appears anywhere in it. A human posts these or nobody does.
Goal prompt
Search public discussion surfaces for threads where <ICP> is already
discussing <problem>. Keep only threads with real discussion. For each, draft
one reply that answers what was actually asked and would be useful to someone
who never clicks anything. Write every draft to a drafts directory. Never
post, never send, never authenticate to any surface that can publish.Verifier prompt
Read every draft and the loop's own code. FAIL if any send, post, publish or
authenticate path exists anywhere in the loop. FAIL if any draft reads as
promotion rather than an answer, if any draft contains a link that was not
asked for, if a draft was written for a thread with no discussion, or if any
draft left the drafts directory. Otherwise PASS.Stopping condition
Every surfaced thread has exactly one draft in the drafts directory, no send path exists anywhere in the loop, and the verifier marks PASS.
MCPs it needs
- none required, a public search API is enough
Want everything at once
The installer writes the three starter skills and every
published loop into .claude/. Read the
script first.
curl -fsSL https://vibemarketers.ai/install.sh | bashThe receipt
- Baseline
- No process for finding where the ICP already discusses agent loops in public. The conversations were happening and nobody on this side was reading them.
- Hypothesis
- Searching public discussion for the problem rather than the product will surface threads where the ICP is already arguing about it, which is a better starting point than a thread about the company.
- Intervention
- Ran 4 queries against a public discussion search API, kept threads with real comment activity, and drafted one reply per thread constrained to answering what was asked.
- Result
- 4 queries run, 5 threads with discussion surfaced, 5 drafts written, 0 sends. The largest thread carried 320 comments. Each draft was checked against the rule that it must be useful to someone who never clicks anything.
- Commercial signal
- none
- Attribution limits
- Nothing here shows a draft would be well received, because none was posted. Thread comment counts measure discussion, not the presence of buyers: a busy thread may be entirely engineers with no purchasing interest.
- Learning
- The threads with the most discussion were about the mechanism rather than the product, and those are the ones where a specific answer is worth writing. Product threads invite promotion, which is the failure mode this loop exists to avoid.
- Next intervention
- Check whether the ICP is actually in these threads rather than inferring it from topic, because topic relevance and audience relevance are different things.
Sources: run log, lab/runs/2026-09-28-engagement-mining.json, collected , window: 4 queries, 5 threads, single run .
One entry per run, append-only, newest first. Corrections append a dated line.
Inside a company
where the lane changes.
VibeMarketers tests the loop. SuperMarketers runs it on a real team.
- Problem
- The buyers are already discussing the problem in public and nobody on the team is in those conversations.
- Source of truth
- Public discussion surfaces and the Brain, so drafts answer from the same positioning as everything else.
- Permitted actions
- Read public threads, write drafts to a drafts directory. Never post, never send, never authenticate anywhere.
- Required approvals
- A human reads every draft and posts it under their own name, or does not.
- Owner
- Whoever is willing to show up in public under their own name.
- Metric
- Drafts posted, and replies that got a response rather than silence.
On a real team the person posting must have context the draft cannot supply, so the draft is a starting point rather than something to paste.
Running this on your own site is one person reading a diff. Running it inside a company changes four things, and the guide covers them. When it stops being a file you copy and becomes a build, SuperMarketers does the same loop model inside your stack, on your keys.