FMKTech / Engineering journal
Original experiments and practical guides to AI agents, integrations, and modernizing legacy software.
AI is a reason to revisit the build-versus-buy decision. Replace the ERP, SaaS and spreadsheets holding you back with software you control.
A 3D game built through parallel agents, the contract and review workflow behind it, and playable comparisons showing what changed when we made the art direction explicit.
Use Skills to package a repeatable method and MCP to connect the required tools. Keep execution, access, and verification explicit.
A practical workflow for improving an existing system: map the business rules, give coding agents focused context, and replace one part at a time without losing control.
How to use a coding loop for bounded implementation work, with explicit acceptance checks, spending limits, and a handoff when progress stops.
A practical threat model for agents with access to business systems: constrain tools, protect data, separate approvals, and test the boundaries outside the prompt.
From a fixed workflow to an autonomous loop: how to choose an architecture, define its boundaries, and evaluate the result beyond a convincing demo.
A practical guide to choosing an automation project, deciding how much autonomy it needs, and measuring whether it improves the way your business works.
What Model Context Protocol standardizes, what your application still needs to enforce, and how to design a useful first integration.