Field notes on data engineering and agentic systems.

Long-form essays from AK-DataGeek on cloud warehouse migrations, bitemporal modelling, Hermes Agent and Claude Code agentic workflows, and the practical tradeoffs we make in production. No fluff, no hype — just what we've learned shipping systems for regulated industries.

28 April 2026 12 min read
Agentic AI

Hermes Agent in Production Data Engineering

Self-improving agents sound like hype until they start remembering your pipeline failures, extracting reusable skills, and cutting ETL recovery from hours to minutes. A practical field report on Hermes Agent, persistent memory, MCP tools, and what actually works in production.

Hermes Agent Nous Research Agentic AI MCP
27 April 2026 14 min read
Migrations

Oracle to Snowflake Migration: A 2026 Playbook

Why Oracle migrations are accelerating in 2026, the cost-benefit reality nobody puts in slide decks, and a five-phase playbook drawn from real engagements. Plus where AI augmentation actually saves time — and where it makes things worse.

Snowflake Oracle Migration dbt Airflow
22 April 2026 12 min read
Data Modeling

Bitemporal Data Modeling for Financial Trading Systems

Backtests that look profitable in the lab and lose money in production are usually betraying one bug: point-in-time data leak. Bitemporal modelling is how we fix it. A practitioner's guide with implementations in BigQuery and Snowflake.

Bitemporal BigQuery Snowflake Trading Data Vault
18 April 2026 10 min read
Method

Why We Bet on Claude Code for Production Data Engineering

A boutique consultancy delivering enterprise-scale work with one engineer sounds like a magic trick. It isn't. Here's exactly how Claude Code, MCP servers and CLAUDE.md files reshape the economics of senior consulting — and where we still won't use AI.

Claude Code MCP Agentic AI Method