Data, AI and technology.
AI changed how fast things get built. It didn't change what's worth building.
I've worked through every layer of that shift — data platforms and ML in production, AI automation and agents that run real workflows — always alongside the business side. The steps below are that path. The longer write-up is From BI reports to agents.
Governed lakehouse platforms, pipelines and ML that the business actually uses — from source systems to decisions.
AI wired into real workflows, and agents that run them with scoped tools, approvals, evals and cost control.
Founding products and shaping platform investment: the conversations that decide what's worth building before anything gets built.
Working on right now
Now
Business
Failure-priced ROI and spend policies per agent role. The business case stays part of the build.
Failure-priced ROINow
Agents
Cost control and guardrails so autonomy stays cheap, scoped, and accountable.
Guardrails in practiceNow
Agents
Who agents can reach, and a log of what they did — access control and tracing as a first-class area.
Company OSNow
Agents
Building learning and memory so context accumulates, and routing so the right model is used for each job.
Model routing notes2024–now
Data
SHL, NHL and more: scrapers, DuckDB/MotherDuck, and an automated publishing loop — same data-craft discipline applied to the game.
Hockey Analytics caseSpring 2026
ML & GenAI
Streamlit on Databricks, with GPT-4o turning questions into validated SQL and narrative answers, built with Claude and Codex.
AI analytics platform2026
Agents
Ran agent organisations with roles, kanban and approval gates. The lessons became a leaner pipeline: GitHub as source of truth, a planning → execution handshake, and cost-aware routing.
Company OS learnings2026
Data
Conference notes on analytics as club infrastructure — pipelines and process over one-off dashboards.
LINHAC report2026
Data
52 team-seasons: returning-core share correlates with points%; coaching changes barely move the club level.
Method note2025–26
Agents
LangGraph, LiteLLM routing (fast models for cheap work, stronger models for hard work), scoped tools, memory and tracing, self-hosted.
Production agent platform2025
ML & GenAI
Natural-language questions against live data with embeddings and scoped context.
AI analytics platform2025
Agents
The model reads the repo, uses local context, implements and ships from the editor.
Cursor profile2025
Data
Data engineering work connected straight into Databricks, BigQuery and Azure, so it runs faster and costs less to operate.
Analytics platform case2025–26
Agents
Quality gates and human approval before anything ships or spends.
Eval fixture notes2025
Agents
Connected the editor to analytics, research and tools through MCP, then built MCP servers so agents could work against scoped data.
MCP development workflow2025
Automation
A structured message becomes a deployed article through n8n, GitHub and Netlify.
AI automation in productionJul 2024
Automation
Translation pipelines to all global languages via the OpenAI API, using GPT-4o mini shortly after its launch.
AI automation in production2023
ML & GenAI
Became my default for data work soon after its release in March 2023.
2023–26
Data
100 production jobs and 600+ governed Unity Catalog tables on Azure Databricks, with a Bronze → Silver → Gold model across 20+ source systems.
Enterprise data platform2023–25
ML & GenAI
Topic modelling across 1.46M+ support cases, churn and demand-forecasting models, all tracked in MLflow.
Enterprise data platform2023–24
Automation
Models wired into n8n and Zapier, so prompts became reusable flows.
Feedback agent case2023–24
Automation
Ask, paste, test, refine: building full sites and applications in conversation.
30 Nov 2022
ML & GenAI
Used from day one for analysis, writing and code.
2021–23
Business
Product analytics, 1,470 survey responses and 30 customer visits guided platform investment across many markets.
B2B decision case2019–22
Data
Web scraping, Zapier and RPA: automating collection and processes before language models entered the work.
2019–21
Data
As a BI consultant at XLENT: scoped and delivered Power BI across client assignments. GDPR and security work made trust part of every report.
2019
Data
Delivery dashboard over Microsoft Planner exports for standups and prioritisation across many boards — agile follow-up without opening every plan.
2019
Data
Power BI + SQL on ServiceNow: from reactive ticket closing to pattern detection, early intervention and a clearer view of support performance.
Related ops case2018
Data
At TietoEVRY: ServiceNow history into SQL datasets and a Power BI dashboard for recurring incidents, resolution trends and earlier intervention — not just retrospective SLAs.
Operations analytics case2017
Data
Lean Django marketplace in Jönköping: restaurants published surplus food in a short window; customers browsed and collected take-away.
Early products2016
Data
Django event and ticket admin with sales tracking for small organisers. Early full-stack product work: Sketch → Bootstrap → Django.
Early products2016–17
Business
Digital ticketing and a food-waste marketplace MVP: cheap to run, hard to change behaviour. Product lessons that still shape what I treat as worth building.
Early products2016
Business
Sketch and InVision quizzes for engagement and lead-gen. User tests showed no real demand — stopped before build. Knowing what not to ship.
2015–16
Data
TUVA shipped with Mixpanel and Google Analytics. Behaviour data shaped product decisions from launch — analytics was never a later add-on.
TUVA case study2014–16
Business
From Swift prototype to 10,000 users in three weeks, with behavioural data from launch.
TUVA case studyI build across the stack, and the breadth is the point: data platforms, AI automation and agents, and the product decisions that decide what gets built. Founded TUVA; ran governed lakehouse and ML in production; operate agent systems through The Unnamed Road AB. Based in Stockholm.