Skip to main content
Emil Ingemar Karlsson — Agentic Engineer Stockholm

Stockholm, Sweden

Agentic Engineer — Data Pipelines, MCP Infrastructure & Production AI Systems

I build data pipelines that feed AI agents, MCP infrastructure that connects tools and models, and production AI systems that run autonomously — cost-effective and secure.

Selected Projects

Enterprise ML & Data Platform — 100 Jobs, 631 Tables, NLP at Scale

End-to-end data and ML platform for a global manufacturing company. 100 Databricks jobs, 631 Unity Catalog tables, support intelligence across 1.46M cases, production churn models, demand forecasting, and a 17-page Streamlit dashboard — built and operated solo over three years.

The Unnamed Roads: Production-Grade Agentic Platform on ~€35/month

A self-funded, solo-operated agentic engineering platform — LangGraph 24/7 orchestration, 5 specialized agents, LiteLLM routing across 8 models, MCPJungle gateway, pgvector memory, Langfuse observability, and a scraper fleet powering 9 live products. All running on ~€35/month.

Agentic Data Organisation with Claude

Design and implementation of an agentic data organisation with Claude coordinating analytics, data platform, pipelines, governance, and data quality.

End-to-End Analytics Platform — Databricks, Streamlit & GPT-4o

Full-stack data intelligence system for a global manufacturer. Medallion architecture on Databricks, AI-powered natural language querying, z-score anomaly detection, and 10 production dashboards covering 14 markets — shipped in 12 weeks.

Conversational Analytics Prototype - Beyond Dashboards

Interactive prototype demonstrating the future of data analytics: natural language queries, proactive insights, and zero-training data exploration. Built to show what comes after traditional dashboards.

How I Built an AI Feedback Agent That Replaces Traditional Surveys – Using n8n and GPT-4

Transform feedback collection from tedious surveys into intelligent conversations. Learn how I built an AI-powered feedback agent with n8n that asks follow-up questions, detects language automatically, and extracts structured insights – all while saving thousands on survey platforms.

Writing

What is Agentic Engineering? A Practitioner's Definition

Agentic engineering is the discipline of designing and building systems where multiple AI agents coordinate autonomously to accomplish goals — without a human triggering each step. Here's what that actually means when you build it in production.

22 artiklar på 26 dagar: sessionsdata, sökord och vad automationen faktiskt producerar

· Updated
Fyra veckor av build-in-public: 22 n8n-tutorials publicerade, 951 sessioner, 38 rankade sökord och 2 topp-10-placeringar — utan ett enda externt backlink. Här är siffrorna, utan utsmyckning.

Agentic Data Organisation: How I Set Up an AI-Driven Data Organisation with Claude

· Updated
A practical walkthrough of my agentic data organisation: roles, ownership, agent coordination, and how Claude drives decision flow across analytics, platform, and governance.

From Raw Data to Revenue Decisions: Building an End-to-End Analytics Platform

How I designed and shipped a full-stack data intelligence system for a global manufacturing company — from Databricks pipelines to AI-powered dashboards.

Building With AI Agents as Co-Workers: My Stack, My Costs, and What I Actually Learned

How I run a 7-project publishing and product studio with AI agents as co-workers — the real stack behind it: OpenClaw, n8n, LiteLLM, Coolify, and a €26/month server bill.

I Built a System That Publishes 30 Articles a Week Across 10 Projects for $0.08 Each

A detailed breakdown of OpenClaw — my self-hosted AI content automation stack running on Hetzner. How it works, what it costs, and what I got wrong the first time.

Tools I Use

n8n, LiteLLM, MCP, Coolify, Hetzner — the agentic engineering stack I use to build data pipelines, MCP infrastructure, and run 9 live projects on ~€35/month. Full details: see my toolstack.

View Full Toolstack

What I offer

Full-scope agentic engineering — infrastructure, MCP, agents, data pipelines, autonomous ops — plus a clear path to get started. Free intro call, 2 500 kr discovery, 5 500 kr starter stack, then production agents (prices in SEK).

Get started → See everything I build

Ready to build your agentic infrastructure?

I design and build the full agentic stack — or help you take the first step. Cost-effective, self-hosted, built to run autonomously.