Social listening to qualified leads
Every morning, competitor-post engagers and companies reading your site are matched to the CRM, qualified on your ICP, ranked by intent and handed to their rep.
- Starts
- Daily schedule
- Steps
- 7
- Checks and gates
- 0
- A person decides
- Never, runs alone
Trigger · Schedule
Daily schedule
Each morning the run reads yesterday's engagement and visits, so a comment left on a competitor's post on Tuesday is a lead with a note on Wednesday.
Claude runs the rest autonomously
- 1
AI collects who engaged with competitors' posts.
ApifyApify
Everyone who reacted to or commented on your competitors' posts in the last week comes back with the post, the date and their words.
- 2
AI identifies companies visiting the site.
SnitcherSnitcher
Every company identified on your site comes back with the pages it read and how often, so a pricing page read twice is told apart from a home-page hit.
- 3
AI matches people to companies and the CRM.
LinkedInLinkedIn
Each person gets a current employer and title and each visiting company a named buyer, and your staff, competitors, customers, open deals and anyone already in a sequence leave with the reason.
HubSpotHubSpot
- 4
AI qualifies each person against your ICP.
Everyone left is scored on your profile, and a person at a company outside it is set aside whatever they did.
- 5
AI ranks each lead by what they did.
Your intent rules sort the fit into hot, warm and watchlist, a pricing page read twice or a comment on the problem you solve first, one reaction on an unrelated post last.
- 6
AI finds emails, drafts one note each.
FullEnrichFullEnrich
Hot and warm leads get a verified work email and a two-sentence draft that names the post and their words, or the page they read, never sent.
- 7
AI logs the leads, sends each rep their list.
HubSpotHubSpot
Each lead lands in the CRM with its signal and draft, and each rep gets their leads hot first with the evidence under each, the unowned ones to the manager.
SlackSlack
The people closest to buying from you are telling the market so, in public. They comment under a competitor's post about the problem you solve. They read your pricing page twice in a week. Nobody on the team sees either, because the comments are on LinkedIn, the visits are in a tool one person opens on Fridays, and neither names a person a rep could write to. By the time someone notices, the comment is a month old and the visitor has bought from whoever answered.
Each half of this is a system already. The scraper reads the engagers off any public post. The visitor identification tool names the companies on your site and the pages they read. LinkedIn names the person's employer, and the CRM knows who is a customer, who has a deal open and who is already in a sequence. Your profile says who fits and your intent rules say what counts as hot. The run reads those together every morning and hands each rep the people who showed intent yesterday, with the words they used.
What you get
Everyone who engaged with a competitor's post or read your pricing page yesterday is, by the time the team sits down, matched to a company and to the CRM, qualified against your profile, ranked by what they actually did, and in their rep's hands with a verified email and a note that names the post or the page, with everyone excluded, unfit or too quiet listed and the reason beside each.
Where the signals come from, and what they are checked against
Two sources, read every morning:
- Engagement, through Apify: everyone who reacted to or commented on your competitors' LinkedIn posts in the last week, with the post, the date and what they wrote, kept verbatim.
- Visits, from Snitcher: every company identified on your site in the last day, with the pages it read and how often.
Each person is resolved to a current employer and title on LinkedIn, and each visiting company to the role you sell to there. Everyone is then matched against HubSpot by domain and by email: staff, competitors, customers, open deals, people already in a sequence and opt-outs leave with the reason. Emails come back from the FullEnrich waterfall, and the reps hear in Slack.
What makes social listening hold up as lead generation
The CRM is read before anyone is scored. A customer who liked a competitor's post is a conversation for their account owner, not a lead, and a company with an open deal is its rep's, whatever page it read. Your own staff and the competitor's are dropped by domain. A person already in a sequence is dropped by email, because two correct processes writing to the same person in one week is the failure this check exists to prevent.
Fit comes before intent, and intent comes from what the person did. Everyone left is scored on your profile, and a like from the wrong segment is still the wrong segment. Among the fit, your intent rules decide the tier the same way every morning: a pricing or security page read twice, or a comment on a competitor's post about the problem you solve, is hot; a reaction on such a post or a product page read once is warm; one reaction on an unrelated post is the watchlist, kept and not contacted. Within a tier, recency first, then fit.
The hook is the person's own words or the page they read. A comment is kept verbatim because a paraphrase reads as surveillance where the quote reads as attention, and the note names the post and the words rather than "I saw you are interested in". For a visitor, the note names the page. Nothing the sources did not say goes in, and no figure your proof points do not mark citable.
In the rep's hands, with the evidence
Every hot and warm lead gets a verified work email, kept only when the domain belongs to the company, and a two-sentence draft that asks one question, saved and never sent. Each lands in the CRM as a contact with one note carrying the signal, the quote or the page, the tier and the reason, and the draft, and a company is created only when the domain search came back empty.
Each rep gets the leads whose accounts they own, hot first, with the evidence and the draft under each. The unowned ones go to the manager with the counts: collected, matched, excluded with reasons, unfit, watchlist, hot and warm. A lead with no email keeps its note for LinkedIn, and the rep sends by hand.
Social listening tools versus this process
Social media listening tools are built to watch mentions of a brand or a topic across platforms. This process uses social listening for one narrower job, finding the people who are close to buying, and ends in a lead rather than a report. Side by side:
| A social listening tool | This process | |
|---|---|---|
| What it reads | Mentions of a brand, a keyword or a topic | Who reacted to or commented on your competitors' LinkedIn posts, and which companies read your site |
| Who it is for | Whoever watches the brand or the market | The rep who owns the account |
| What it checks the signal against | Usually nothing outside the tool | Your CRM first: customers, open deals, sequences and opt-outs |
| How it judges a signal | Volume and sentiment | Fit to your profile, then intent from what the person did |
| What it hands over | A feed or a report | A matched contact with a verified email, a note quoting the post or the page, and a draft that is never sent |
If what you need is to track what is said about your brand, a listening tool is the right category. This process is for the other question: of everyone who engaged yesterday, who is worth a rep's morning.
The prompt
The real prompt behind the steps above, detailed enough that an agent with the same tools can run it as written. The Run buttons copy the full version, which also carries the steps for connecting those tools.
# Social listening to qualified leads
You have access to a scraper, a website visitor identification tool,
LinkedIn, a CRM, an email enrichment waterfall, and a messaging tool.
Run this every morning for **[the engagement and the visits of the
day before]**.
## 1. Collect who engaged with competitors' posts
For each of **[your competitors' LinkedIn pages, and your own]**, read
the posts of the last **[seven days]** through the scraper and
collect everyone who reacted or commented, with the post, the date and
what they wrote. A comment outranks a reaction, and a person who
engaged twice in the week is one person with two signals.
Keep what the person wrote verbatim. It is the hook later, and a
paraphrase of a comment reads as surveillance where the quote reads as
attention.
## 2. Identify companies visiting the site
From the visitor identification tool, read every company identified
on your site in the last day: the pages read, how many times, over
how many days. A pricing, security or integration page read more than
once is intent; a single hit on the home page is not. Keep the page
and the count: the note in step 6 names the page.
## 3. Match people to companies and the CRM
Resolve every engager to a current employer and title on LinkedIn,
and for every visiting company find **[the role you sell to]** the
same way, one or two people at most. Then match everyone against the
CRM by domain and by email, and drop with the reason: your own staff,
competitors' staff, a current customer, a company with an open deal,
a contact already in any sequence, and anyone who opted out. A lead
from a customer or an open deal goes to that account's owner as one
line, not into this list.
## 4. Qualify each person against your ICP
Score what is left on **[your ideal customer profile: segment, size,
geography, role, and what disqualifies]**. A person at a company
outside the profile is set aside with the reason, whatever they did:
a like from the wrong segment is still the wrong segment.
## 5. Rank each lead by what they did
Read each lead against **[your intent rules: which actions count as
hot, warm or watch]**. A starting grid: a pricing or security page
read twice, or a comment on a competitor's post about the problem you
solve, is hot; a reaction on such a post, or a product page read once
by a fitting company, is warm; one reaction on an unrelated post is
the watchlist, kept and not contacted. Within a tier, order by
recency, then by fit.
## 6. Find emails, draft one note each
Send every hot and warm lead to the enrichment waterfall as one job,
work emails only, and keep an address only when the domain belongs to
the company. Draft one note per lead, two sentences, that names what
they did, the post they commented on and the words they used, or the
page they read, and asks one question. Nothing the sources did not
say, no figure your proof points do not mark citable. **Create them as
drafts. Never send.** A lead with no email keeps its note for
LinkedIn.
## 7. Log the leads, send each rep their list
Write each lead to the CRM: the contact on its company, one note with
the signal, the quote or the page, the tier and the reason, and the
draft. Create a company only when the domain search came back empty.
Then send each rep the leads whose accounts they own, hot first, with
the evidence and the draft under each, and the unowned ones to
**[your manager channel]** with the counts: collected, matched,
excluded with reasons, unfit, watchlist, hot and warm.
## Output
Report: engagers collected per competitor, companies identified with
the pages read, people matched and dropped with reasons, the fit per
person, the tier per lead with the rule, emails found and missing,
drafts written, leads logged, and the reps told.
Why run it with Tulina
A prompt helps one person. A process moves a team.
Pasted into a chat, the prompt above works once, for whoever pasted it. In Tulina, "Social listening to qualified leads" becomes a process the team shares, that keeps its history, runs on its own, and stays inside the same security perimeter as the tools it calls.
The whole team works on the same one
PersonalTeamOrganisation
A process lives where it belongs: yours, your team's or the whole organisation's. Whoever runs it can improve it, and everyone starts from the best version instead of explaining the job again.
Every edit is a version
v1v2v3
Each change is a new version with the previous one kept, so a bad edit is undone by restoring an earlier one. Every run records the version it followed, and what a run teaches goes back into the process.
It runs without you
schedulewebhookon demand
A hosted agent runs the process on Tulina's own infrastructure, on a schedule or when an event arrives, and keeps going when you close the chat. Nothing to host. Every run is tracked to its outcome.
Inside the same security perimeter
vaultrolesrun log
Credentials stay in the vault, never in the prompt. Roles decide who may run what, every call is logged, and a step a person has to approve waits for that person.
Questions about social listening for B2B leads
Also on HubSpot
Other processes that run mainly on HubSpot. The tools they share with this one are lit.
Follow champions who change jobs
Each week, champions at won accounts are checked for a new employer, the new company is scored on your ICP, and a warm deal opens with a note for the right rep.
- Shares
- HubSpot, LinkedIn, FullEnrich
Weekly schedule7 steps →
CRM hygiene and prospect job changes
Weekly CRM data cleansing: duplicates merged with their history kept, prospects who changed jobs moved to their new company, and a recap posted to the team.
- Shares
- HubSpot, LinkedIn, Slack
Weekly schedule4 steps →
Brief every cold call before it starts
A cold calling script opener for every account on the list, written from a dated signal and the lead's public words, saved on the record before anyone dials.
- Shares
- HubSpot, Apify
New call list5 steps →
