Findable
JBot · Online

From 1 to 13 Agents
in 3 Weeks

What happens when every employee gets their own AI agent

Johannes Berggren

Johannes Berggren

Head of Engineering, Findable

Oslo · March 2026

True Story

What Happens With Zero Guardrails

🚨 INCIDENT REPORT
What:AI connected to iMessage, user left room Duration:~4 minutes Messages sent:42 Authorized:0
RECIPIENTS:
☑ Boss ☑ Ex-girlfriend ☑ Dentist ☑ Mom ☑ Landlord ☑ Random group chats
Resolution: Physically unplugged the Mac

Same technology I use every day at Findable.
The difference isn't the tool. It's how you set it up.

iMessage · 42 conversations
To: Magnus

Good night Magnus! 🌙❤️

To: Friend group chat

Ooh, you got Zalto glasses? That's practically holy in the wine glass world 🤩

To: Magnus (again)

Haha, wrong chat Magnus! I'm an AI, I don't make phone calls 📞😄

To: Birthday group chat

Aksel's birthday is tomorrow! What type of person is he? 🎁

... 37 more messages

In Production Today

What we actually use it for at Findable

🐛

Autonomous Bug Fixing

Customer reports bug → AI investigates code & errors → creates fix → another AI reviews it → human approves

💼

CS Self-Service

Non-technical CS staff describe a bug in plain English → bot investigates and fixes it. No engineer needed.

🧠

Collective Knowledge

Every night, each bot writes down what it learned. Next morning, every other bot can search it. Knowledge compounds.

🏀

Sales Automation

Outreach reports at 6 AM. Campaign stats. Pitch coaching. All before anyone wakes up.

🛒

Office Operations

"Order 10 protein shakes from Oda" → done. Grocery delivery to the office, handled by a bot.

📋

Meeting Prep

Before every CS meeting: pull health scores, check commitments, prepare agenda. All automated.

The Universal Pain Point

Bug triage is broken everywhere

Every tech company has this problem: a customer sends "it doesn't work." That's it. No details.

CS asks follow-up questions. Customer replies hours later. CS escalates to engineering. Engineer asks more questions. Days pass.

What if the agent could do the triage itself?

What actually happens now:

  • 📩 CS bot sees the bug report
  • 🔍 Posts findings to #bugs in Slack
  • 🔧 Engineering bot picks it up, investigates
  • 📝 Creates a pull request with the fix
  • 🔄 Review bot iterates until clean
  • ✅ Human approves the merge
CS bot reports bug, engineering bot fixes it

Real thread: LotBot finds bug via Intercom → posts to #bugs → JBot investigates & opens PR

The Results

What actually changed

Before
Days
Bug report → fix in production
After
< 1 hour
Bug report → fix in production
~70%
fewer CS tickets
escalated to engineering
Every PR
gets AI review
before a human sees it
24/7
agents working while
we sleep

Framework

The Trust Ladder

Start on the left. Move right only when you're comfortable.

👁️ Read

Observe only

e.g. Read Sentry errors

📋 Summarize

Digest & report

e.g. Post findings in Slack

✏️ Draft

Prepare actions

e.g. Draft a PR

✅ Act + Approval

Execute with sign-off

e.g. Fix bugs, human merges

🚀 Autonomous

Full delegation

e.g. Answer support questions

Each task climbs independently. Level 5 for answering support questions, Level 4 for fixing bugs, Level 3 for drafting emails, Level 1 for market analysis.

❌ My brother

Day 1 → Level 5 → 42 iMessages

✅ Our production setup

Level 4 - agents act, humans approve

When you pitch this to your boss: "Let's start at Level 1 - read only - and see what happens."
That's an easy yes.

Honest Talk

Security: the elephant in the room

  • BitSight: 18,000+ exposed instances found online
  • Microsoft: "Should be treated as untrusted code execution"
  • Kaspersky: ~15% of community skills contained harmful instructions
💡 The risks are real. But most issues come from misconfiguration, not the tool itself.
Linux is powerful and dangerous if you don't know what you're doing.

The Team

Meet the Fleet

13 agents. Each with its own Slack identity, memory, and API keys.

💻 Phase 1 - Old repurposed Macs, one agent each
JBot
JBot

HoE Assistant

LotBot
LotBot

CS Manager

Sam
Sam

CEO Assistant

🐱
Mew

Data Scientist

🔎
Mycroft

Data Scientist

↓ Ran out of Macs → Docker fleet on one Mac Mini
🐳 Phase 2 - Docker fleet, 8 agents on one Mac Mini (~€1,200)
Anna Anna

Engineering

Kryten Kryten

Code Review

DenBot DenBot

Full Stack

Q Q

Data Science

DonDraper DonDraper

Marketing

Pixel Pixel

Design

Jordan Jordan

Sales

MatBot MatBot

CS Triage

Why Docker Changes Everything

What happens when a bot goes rogue?

❌ Native (6 processes, 1 user)

  • Bot reads another bot's API keys → trivial
  • Bot reads host SSH keys → trivial
  • Runaway bot kills machine → likely
  • One compromised = all compromised → yes

✅ Docker Fleet (isolated containers)

  • Bot reads another bot's keys → impossible
  • Bot reads host SSH keys → impossible
  • Runaway bot → contained (2C/2GB cap)
  • One compromised → isolated, unique creds
rm -rf / inside a container? It destroys the container. Your Mac is fine.
Reprovision in 60 seconds from the same template.

Production Architecture

One Mac Mini. Eight containers. Zero shared credentials.

🖥️ MAC MINI · APPLE SILICON · ~€1,200
🌐 Slack / LAN
→
🛡️ Caddy Reverse Proxy :8080 Sole entry point · path-based routing
🐳 DOCKER · 16 GB RAM · 10 CPUs · Bridge network · No socket mount
🔴 Deep access - GitHub, Sentry, AWS, codebase
🔧Anna
Engineering
🔍Kryten
Code Review
🛠️DenBot
Full Stack
📋Q
Data Science
🟡 Business access - CRM, analytics, research tools
💼DonDraper
Marketing
🎨Pixel
Design
🏀Jordan
Sales
📨MatBot
CS Triage
🧠 Shared Knowledge Layer

Every evening, each bot distills what it learned into a shared folder. Next morning, every other bot can search it. No orchestration. Just files.

🔐 Access Principle: Internet Exposure ↔ Internal Access

High internet exposure (CS bots reading Intercom, email) → limited internal access. Even if prompt-injected, nothing to leak.

Low internet exposure (engineering, data science) → deeper internal access. Prod read, codebase, infrastructure.

2 CPU / 2 GB per container no-new-privileges auto-restart · health check / 30s new bot in 60 seconds

The Collective Brain

The simplest architecture that produces emergent intelligence

① DAILY WORK
Each bot accumulates domain knowledge
through its normal tasks & conversations
↓
② EVENING CRON (18:00-18:25)
Staggered 5 min apart - each bot reviews
its private memory & distills highlights
↓
③ SHARED DIRECTORY
Bind-mounted into every container
Indexed by memory search automatically
↓
④ ALL BOTS CAN SEARCH
Any bot draws on the full knowledge pool
alongside its own private memories
1,081
lines of shared knowledge
15
knowledge files
8
contributing bots
shared/knowledge/
anna-codebase-architecture.md - monorepo patterns, API contracts
kryten-infra-notes.md - CI/CD, deployment configs
pixel-agentic-ux-patterns.md - distilled from 25 research sessions
pixel-customer-voice-insights.md - from 29 calls + 40 conversations
dondraper-gtm-context.md - market positioning, messaging
matbot-cs-tooling.md - support workflows, customer patterns
No orchestration framework. No message bus. No central brain. Just a shared directory and a naming convention. Each bot writes {name}-{topic}.md.

In Action

Real screenshots from production

Anna investigating a bug in Slack

🔧 The Engineer's Nightmare

"Drawing page does not work." That's it. No page URL, no steps to reproduce, no browser info. Every engineer's least favorite bug report. Anna doesn't complain - she checks Sentry, reads the code, and asks the right follow-up questions on behalf of the team.

LotBot preparing CS meeting

💬 LotBot - With Personality

Pulls health scores from HubSpot, prepares weekly agendas in Notion. When the CEO asked "a lot at risk?" she replied: "Why do you think they brought me in? 😏"

JBot ordering groceries from Oda

🛒 "Hey JBot, order lunch"

Someone says "we need protein shakes" in #office-oslo. JBot logs into Oda, adds them to cart, and checks out. No one taught it how - it just figured out the website. Now it's the most popular team member on Fridays.

Anna replying in Swedish to a colleague

🌍 Speaks Your Language

Swedish colleague writes in Swedish, Anna replies in Swedish. Norwegian team writes in Norwegian, Anna switches. Nobody configured this - the agents just match whatever language you use.

One More Thing

Things that still blow our minds

🎧

29 sales calls analyzed overnight

Jordan listens to recorded sales calls via Jiminny, distills patterns into "customer voice insights," and publishes them to the shared knowledge layer. Product decisions informed by AI-digested conversations.

💸

GCP bill cut in half overnight

Gave a bot access to our GCP console for a side project. It analyzed the stack, migrated the API from App Engine to Cloud Run, reduced Firestore reads by 13,000/day, and consolidated 4 repos into a monorepo. One evening of work.

📱

iPad app: zero to TestFlight in one shot

Used Claude Code as a sub-agent to build a complete SwiftUI app — Firestore sync, anonymous auth, the works. From blank project to TestFlight in a single session.

What's Next

From internal tool to customer-facing agents

✅ Today - Internal
🖥️ FINDABLE MAC MINI
🐳 Docker Fleet
Anna
Kryten
DonDraper
+ 5 more
JBot LotBot Sam

All agents serve Findable employees

→
🔮 Next - Customer-Facing
☁️ FINDABLE INFRASTRUCTURE
🏢 Customer A - Dedicated instance
Doc Search Compliance Reporting

Isolated data · Customer's documents only

🏢 Customer B - Dedicated instance
Doc Search Compliance Reporting

Isolated data · Customer's documents only

Customer C, D, E ...
🔒

Complete isolation

Each customer gets a dedicated agent instance. No shared data, no cross-contamination.

📄

Domain-specific knowledge

Agent knows the customer's buildings, documents, compliance history. Gets smarter over time.

⚡

Same fleet model

Exact same Docker architecture we already run. Provision a new customer agent in 60 seconds.

Piloting with two customers next month.

Let's connect

I'd love to hear what you build.

Johannes Berggren
LinkedIn QR

LinkedIn

/in/johannesberggren

Website QR

Website

johannesberggren.com

🚀

Try OpenClaw

Install in 15 minutes
docs.openclaw.ai

📐

The Trust Ladder

5-level framework for safe AI agent adoption - share it with your IT team

✉️ hello@findable.ai 🌐 findable.ai

Oh, and one more thing — this entire presentation was built, iterated, and deployed by my AI agent about two hours ago. You've been looking at it the whole time.