7 figures. 6 people. 126 agents doing the work.

AI researcher turned founder turned growth engineer. Still figuring it out, in public.

M.Sc. in deep learning. Former AI Team Lead. Published. Then I got hungry for more impact and founded The Voice Box, my AI agency.

Needed leads, so I went deep on LinkedIn: 40,000 followers in 8 months, $100K closed in 90 days. All organic.

Growth is a blend of experimentation, data, and human psychology, increasingly engineering.

Now I'm the founding growth engineer at Swan, building the first autonomous business where humans are amplified 100x.

This is where I unpack it as it happens.

Stick around.

You don't reach 7 figures with 3 people by accident.

It all comes down to 120+ AI Agents (steal them):

Swan AI has a very interesting org chart. Started at 3 people (now 6), and over 120+ AI Agents that all feed from our GTM Brain.

The connectivity is bonkers. I feel like I'm in a video game.

Well, it's Thursday and I'm in a good mood, so f*ck it (Amos Bar-Joseph forgive me) - I'm sharing every single agent we use + 33 skills, for you to copy:

→ 9 in the GTM Brain. Every call, quote, lesson and playbook, indexed and synced. Everything else feeds from it.

→ 19 LinkedIn signal agents. Every profile view, comment, reaction, connection request and DM, for the whole team. One of these turned a signal nobody watches into $230K of pipeline in 14 days.

→ 20 pipeline & deal ops. Deal health synthesis runs at 2AM, the forecast lands Sunday and Thursday at 6AM, Stripe syncs itself into the CRM.

→ 13 on the inbound desk. Every form, chatbot escalation and cal.com booking gets qualified, routed, or auto-cancelled before a human ever sees it.

→ 12 prospecting & intent radars. Job postings, funding rounds, intent surges, competitor website changes, champions switching jobs.

→ 5 on ABM & deep research. Target lists built, enriched, scored, warm-path mapped.

→ 12 in the content engine. Viral-idea mining, customer-call language, drafts, visuals, scheduling, performance readback.

→ 2 on the newsletter. Subscribers synced weekly, every reply read and routed.

→ 10 on customer success watch. Credit burn alerts, dormant trials, declining orgs, day-3 trial audits.

→ 9 in the meeting machine. Prep before every call, execution after it.

→ 15 in company ops. Partner commissions, blog to CMS, email triage.

Managing agents is... a real management job. They drift. They overlap. Some quietly stop pulling their weight. I've "fired" more agents than most managers fire people.

But every single one of these started as a task a human hated doing. 126 hated tasks, gone.

Talk about leverage.

Steal the full agentic org chart, all 126 agents in one doc: link

Bonus at the bottom of the doc: the 33 skills our team open-sourced on gtmskills.com, the actual playbooks these agents run on, every one linked and free.

Share it if you find it useful :)

Or just spin a few up: agent.getswan.com

• Ariel

The Hypothesis

One system, six people, seven figures

Started at 3 people, now 6, running on 120+ AI Agents that all feed off one GTM Brain. Nine agents alone keep it synced: every call, quote, lesson, and playbook, indexed automatically.

The Test

Build Your Own GTM Brain (Mini Version)

1/ List every place your team's institutional knowledge currently lives: call notes, deal notes, playbooks, Slack threads.

2/ Pick the single most-repeated question your team answers from memory instead of a doc.

3/ Write the answer down once, properly, somewhere everyone can find it.

4/ Next time that question comes up, point to the doc instead of re-explaining it.

That's agent #1 of your GTM Brain, even before you automate anything.

Steal the full 126-agent org chart to see how we structured ours: link

Your Data Point

If everything your team knows lived in one place, what would you build first?

Write down your team's most-repeated answer this week. Reply and tell me what it was.

Community Notes

Build your own GTM Bran here

getswan.com