Only 12 seats

Build YOUR Own AI TEAM

In 3 sessions, you'll have a real AI team running in your business. Hands-on. No coding. Sessions held in person at Midskeppsgatan 6, Plus Park City, Stockholm.

Dates

10, 17 and 24 OCT

3 hours per session

Location

Stockholm

Early Bird

3,985 SEK

Save 1,000 SEK

Duration

9 Hours

Reserve your seat See what you'll build

Bootcamp is held in English

Javid Valiyev

Founder in Genaition

Connect with Javid

Workshops

180

Attendees

What You Will Build

4-agent AI system
that runs autonomously.

In 3 sessions, you deploy a multi-agent AI system, one orchestrator and four agents. Every action coordinated, traceable, and defined by you.

One orchestrator → four specialist agents

The Brain

Orchestrator Agent

Receives every incoming trigger: email, schedule, or event
Asks Claude which agent should handle it, then delegates accordingly

Reply Agent

Reads every new email and classifies its intent
Sends a reply in your style within your defined rules

Follow-Up Agent

Checks the database and identifies what should be done
Decides: who to contact, when, and how often

Outreach Agent

Initiates outreach to new or cold contacts based on your criteria
Personalises each message and logs every send to the decision log

Performance Agent

Routes risky or high-value cases to a human for review
Monitors and reports the quality of every AI decision across all agents

Tech Stack

Your tech stack

Every tool was chosen for a reason. The right one for non-technical founders.

AI Reasoning Layer

Claude Sonnet 4.6

Why not GPT-4? Fewer hallucinated decisions. Handles long system prompts reliably critical when agents send emails.

Orchestration Layer

n8n

Why n8n? n8n runs on infrastructure you control, no task limits, no surprise pricing, no outages you didn't cause. More reliable, fully yours.

Data Layer

Airtable

Why Airtable? Every AI decision is logged and readable. See every state change without touching code.

Your AI Mechanic

Claude Code

Why it matters: When your agent behaves unexpectedly, describe the problem in plain English. Claude Code diagnoses and fixes it, no developer needed.

Fully deployed and running live by session 3

Live Scenario

HOW IT WORKS

Incoming email · Lead: Erik Lindström

"We're interested, but the price feels a bit high for us right now. Also, we're not sure whether we can move forward with implementation this month."

Signals detected by Claude AI

✓ Interest ⚠ Price objection ◷ Timing hesitation

ORCHESTRATOR DECISION

Standard lead

Draft a measured reply. Acknowledge price concern, don't push. Move conversation forward.

Agent Output · Inbound Reply Agent

"Hi Erik! Totally understand on timing, no rush this month. On pricing, I'm happy to walk through options. Want to jump on a quick call?"

→ Auto-send

High-value lead

Route to human review. Message is sensitive and worth personal attention.

→ Human review

If they go quiet

System tracks state. Suggests follow-up at the right time, no blind nudging.

→ State tracked

Who It's For

Built for operators
and founders

This is for you if this sounds familiar:

→ You run your leads and conversations through your inbox
→ You want AI assistance, but you want to stay in control
→ You've lost deals because a follow-up was late or missed entirely
→ You're tired of manually replying, following up, and tracking threads

You don't need to
code.
You need to think
in systems.

What to bring Just your laptop and your curiosity!

How It Works

3 days. Build-first.

Each session produces a working component. No passive learning—you ship something every session. One in-person build session (3 hours). 9 hours in-person total across 3 Saturdays (Oct 10, 17 & 24), plus 1 hour of individual practice per session.

Day 1

Day 1 · Oct 10

System Design & Decision Logic

Before you build anything, you define the rules. What the AI sends. What it escalates. What it ignores. No guessing later.

Day 2

Day 2 · Oct 17

Build the Inbound Reply Agent

Your inbox goes live. Real emails come in. The agent reads, classifies, and replies in your tone, within your rules.

Day 3

Day 3 · Oct 24

Follow-Up Agent + Test, Harden, Deploy

Missed follow-ups kill deals. This session you build the follow-up agent, break the system before the real world does, and deploy to your actual inbox.

From our workshops

See the room

7 workshops · 180+ attendees

Stockholm · March 2026

Stockholm · DEC 2025

Göteborg · SEP 2025

← Scroll to see more →

Apply

Your AI system.
Running live.
In 3 days.

Small cohort In-person 3 days Plus Park City OCT 10-24, 2026

0:00

Limited seats

4,985 SEK

3,985 SEK

Save 1,000 SEK

VIP in-person support throughout
24/7 Slack access to ask questions
Guiding materials included
Post-lab Slack support

Reserve your seat

Secure your spot today.

What people say

4.5

Average rating

See all reviews on Trustpilot ↗

Came in skeptical, left with a working agent in my inbox. By hour two I'd built the send loop myself. Not following along. Actually doing it.

Valentina FermanelliStatistics ConsultantWorkshop · Göteborg · 2025

When the agent read an email and sent a draft back for my review, it finally clicked. I'd been trying to understand ReAct for months.

Sara SvenssonFounderWorkshop · Stockholm · 2026

Structured and hands-on from start to finish. I left with a working AI agent, no theory, no waiting. First time it actually felt real in my business.

Joey SorelFreelancerWorkshop · Stockholm · 2026

Your instructor

Javid Valiyev

Founder · Genaition

5+ years AI 150+ trained

Javid builds Applied AI and teaches people and businesses how to implement them without needing a developer. His workshops are known for being hands-on, structured, and beginner-safe. You don't leave without a working system.

"You don't leave without a working system. That's the rule."

FAQ

Questions

Current price is 3,985 SEK. No payment plan currently, but if timing is an issue reach out directly on Slack or email before applying.

Most participants spend under 150 SEK/month after the lab, n8n is self-hosted (free), Claude API is pay-as-you-use (~5–20 USD/month for typical usage), and Airtable's free tier covers most cases. During the lab itself, costs are minimal.

No. This is not blind automation. The AI classifies and drafts, but your system's rules, state, and escalation policy determine what actually happens. You define the boundaries; the system respects them.

9 hours in-person total — one 3-hour session across 3 Saturdays (Oct 10, 17 & 24). Plan for 1 additional hour of individual practice per session to test and iterate on what you built. Intensive and focused, no filler.

You leave with a working, deployed system connected to your own inbox, not a demo. You also get an architecture document and operating model you can maintain and adapt after the lab ends.

n8n (self-hosted via Docker) as the workflow orchestrator, Claude Sonnet 4.6 by Anthropic for AI reasoning and system-prompt logic, Airtable for state and the Decision Log, and Gmail via OAuth for email. All tools are visual-first and locally runnable before deployment.

Both. Individuals are welcome, and small teams (2–3 people) can join together and build a system tailored to their own business context.

Yes, especially if you already use AI tools. Most people use AI in a reactive, shallow way. This lab teaches you to design systems with clear decision logic, state, and auditability. That's a different skill entirely.

Build YOUR Own AI TEAM

See the systemin action

4-agent AI systemthat runs autonomously.

Your tech stack

Built for operatorsand founders

3 days. Build-first.

See the room

Your AI system.Running live.In 3 days.

Javid Valiyev

Questions

See the system
in action

4-agent AI system
that runs autonomously.

Built for operators
and founders

Your AI system.
Running live.
In 3 days.