# Connect with founders posting about AI agents

150 accounts and 300 people, 300 LinkedIn connection requests and a message to the 90 or so who accept.

Family: [LinkedIn outbound](https://www.routergrowth.com/workflows/linkedin-outbound.md) · HTML page: https://www.routergrowth.com/workflows/linkedin-ai-agents

## Give this to your agent

```text
Using RouterGrowth, run this workflow: Connect on LinkedIn with founders who posted about AI agents for sales or marketing this month, then message the ones who accept. 300 people, personalized from their posts.
Show me the price before every call, and stop after each stage with a sample of the results so I can adjust.

1. Source the accounts: company.search x 15 searches. Companies matching the industry, size and location, ten or so per search.
2. Qualify on firmographics: company.enrich x 150 companies. Headcount, industry and location to keep the accounts that fit.
3. Find the people: linkedin.search x 150 searches. People search on your connected LinkedIn account, one search per account.
4. Get the contact: linkedin.profile x 300 profiles read. Charged on a match only: a miss is free, so the estimate is a ceiling.
5. Context for the first line: web.scrape x 150 pages, social.posts x 900 posts. One page per account and a few recent posts per person, so the opener is about them.
6. Run the outreach: linkedin.invite x 300 requests, linkedin.message x 90 (30% accepted). Requests and follow-ups from your connected account, inside LinkedIn's daily limits.
7. Read the replies: linkedin.messages x 30 inbox reads. Poll the inboxes, classify replies, hand the warm ones to a human.

Budget for one run: about $8.11. Run routergrowth inspect on any capability before the first call to confirm the quote.
```

## Why this works

Founders posting about AI agents are early adopters by definition and reply to messages about the thing they just wrote.

The first line, as your agent would write it:

> Your post on running outbound with agents matches what we see. Which step still needs a human for you?

## The workflow, stage by stage

Source the accounts → Qualify on firmographics → Find the people → Get the contact → Context for the first line → Run the outreach → Read the replies

| # | Stage | Calls | Cost |
|---|---|---|---:|
| 1 | Source the accounts | `company.search` x 15 | $0.04 |
| 2 | Qualify on firmographics | `company.enrich` x 150 | $1.06 |
| 3 | Find the people | `linkedin.search` x 150 | $0.30 |
| 4 | Get the contact | `linkedin.profile` x 300 | $0.60 |
| 5 | Context for the first line | `web.scrape` x 150, `social.posts` x 900 | $2.64 |
| 6 | Run the outreach | `linkedin.invite` x 300, `linkedin.message` x 90 | $3.41 |
| 7 | Read the replies | `linkedin.messages` x 30 | $0.06 |

One run: $8.11 for 2,085 calls. Assumptions: 2 contacts per account unless the brief says otherwise, 70% email find rate, 90% verification pass, 3 emails per contact, 30% LinkedIn accept rate. Prices are the catalog's at the time this page was built; `routergrowth inspect` returns the exact quote before a call.

### Source the accounts

Companies matching the industry, size and location, ten or so per search.

### Qualify on firmographics

Headcount, industry and location to keep the accounts that fit.

### Find the people

People search on your connected LinkedIn account, one search per account.

### Get the contact

Charged on a match only: a miss is free, so the estimate is a ceiling.

### Context for the first line

One page per account and a few recent posts per person, so the opener is about them.

### Run the outreach

Requests and follow-ups from your connected account, inside LinkedIn's daily limits.

### Read the replies

Poll the inboxes, classify replies, hand the warm ones to a human.

## Run it from the command line

```bash
# RouterGrowth workflow: Connect on LinkedIn with founders who posted about AI agents for sales or marketing this m
npm install -g routergrowth && routergrowth setup

# 01 Source the accounts  (company.search x 15)
routergrowth run -c company.search -i '{"query":"<query>"}'

# 02 Qualify on firmographics  (company.enrich x 150)
routergrowth run -c company.enrich -i '{"domain":"<domain>"}'

# 03 Find the people  (linkedin.search x 150)
routergrowth run -c linkedin.search -i '{}'

# 04 Get the contact  (linkedin.profile x 300)
routergrowth run -c linkedin.profile -i '{}'

# 05 Context for the first line  (web.scrape x 150, social.posts x 900)
routergrowth run -c web.scrape -i '{"url":"<url>"}'
routergrowth run -c social.posts -i '{"platform":"<platform>","handle":"<handle>"}'

# 06 Run the outreach  (linkedin.invite x 300, linkedin.message x 90)
routergrowth run -c linkedin.invite -i '{}'
routergrowth run -c linkedin.message -i '{"text":"<text>"}'

# 07 Read the replies  (linkedin.messages x 30)
routergrowth run -c linkedin.messages -i '{}'
```

## Questions

### Can an AI agent send LinkedIn connection requests?

Yes, from your own account. You connect it once through a hosted sign-in, then linkedin.search, linkedin.invite and linkedin.message run as you, inside daily caps the platform enforces.

### How many invitations can it send a day?

Up to 30 a day per account, 20 in the first week, and 180 a week. The limit is enforced on every call, so a workflow of 300 people is spread over a couple of weeks.

### What should the connection note say?

One line about something the person posted. social.posts reads their recent posts so the agent can write a note that could only have been sent to them.

### What happens after someone accepts?

linkedin.messages shows who accepted and who replied. The agent messages the people who accepted and, in the workflows that say so, emails the ones who did not.

### What does this workflow cost to run?

About $8.11 for one run of 2,085 calls. Each call is quoted before it runs and a lookup that finds nothing is not charged, so the figure is a ceiling. There is no subscription: the run is paid from a prepaid balance.

## Related

- [Connect with marketing leaders posting about outbound results](https://www.routergrowth.com/workflows/linkedin-outbound-results.md)
- [Connect with CROs posting about building RevOps](https://www.routergrowth.com/workflows/linkedin-revops-hiring.md)
- [Connect with people who just started a sales leadership role](https://www.routergrowth.com/workflows/linkedin-new-role.md)
- [Connect with speakers at sales and marketing conferences](https://www.routergrowth.com/workflows/linkedin-event-speakers.md)
- Guide: [LinkedIn automation for AI agents: search, invite, message and read replies from one prompt](https://www.routergrowth.com/use-cases/linkedin-automation-for-ai-agents.md)
- Guide: [LinkedIn lead generation: turn competitor commenters into a qualified lead list](https://www.routergrowth.com/use-cases/competitor-commenters-to-leads.md)
- Skill: [LinkedIn outbound](https://www.routergrowth.com/skills/linkedin-outbound.md)
- Skill: [Multichannel intent outbound](https://www.routergrowth.com/skills/multichannel-intent-outbound.md)

Adjust the volumes and assumptions: https://www.routergrowth.com/free-gtm-tools/workflow-generator#q=Connect%20on%20LinkedIn%20with%20founders%20who%20posted%20about%20AI%20agents%20for%20sales%20or%20marketing%20this%20month%2C%20then%20message%20the%20ones%20who%20accept.%20300%20people%2C%20personalized%20from%20their%20posts.