25 Mar 2026
The verification tax
AI makes generating output almost free. But every AI output still needs checking — and checking doesn't scale with compute. The verification tax is the hidden cost most businesses ignore when deploying AI.
I'm Mitchell, a full-stack AI Software Engineer.
I design, develop and ship practical AI systems that cut manual work and improve margins. My focus: small, verifiable wins that go live fast, then scale. If you need a developer that knows what to build and why, let's talk.
22 Mar 2026
Your AI can't use what was never written down
Eighty percent of what runs your business has never been documented. AI forces that knowledge debt to come due — and the 95% pilot failure rate is the invoice.
20 Mar 2026
The Agency Gap: Why the Best AI Products Make You More Powerful, Not More Passive
80,508 people told Anthropic they want productivity from AI. When pressed on why, they described wanting their lives back. Most AI products are built for the stated need. The winners are built for the real one.
15 Mar 2026
The compound learning gap: Why your AI features are already commoditised
AI has compressed feature-building from months to days, making every AI feature you ship replicable in weeks. The companies winning with AI aren't shipping better features — they're building learning loops that compound with every user interaction.
4 Mar 2026
The Specification Gap: Why We Can't Tell AI Agents What We Actually Want
The hardest problem in agentic AI is not building capable agents — it is describing what we want them to do. Polanyi's Paradox, Goodhart's Law, and the limits of language converge to create a specification gap that no amount of engineering can close.
1 Mar 2026
The Decay Paradox: Why AI Agents Get Worse as We Trust Them More
Agentic AI systems degrade through context rot, compounding errors, and model drift — but human oversight erodes in lockstep. The widening gap between actual reliability and perceived reliability is the defining engineering challenge of autonomous systems.
Projects
- Project
- doyaken-cli
- Description
- A standalone multi-project autonomous agent CLI that delivers working code through an 8-phase pipeline. Install once, use on any project.
- Project
- lofield.fm
- Description
- Create lofi beats using natural language. Just describe what you want, and AI generates the music for you.
- Project
- launchonomy
- Description
- A system for orchestrating AI agents to complete "missions" through consensus driven decision-making and workflow automation.
- Project
- pitchplease
- Description
- A Next.js app and Agentic AI workflow for uploading a pitch deck and turning it into a AI generated video, with voiceover and narrator.
- Project
- inbox-triage-extension
- Description
- Triage your inbox with AI-powered email summaries, attachment analysis, and reply drafts - all processed locally for complete privacy.
- Project
- agentic-commerce-protocol
- Description
- RFC: Fulfilment for the Agentic Commerce Protocol - defines the fulfilment lifecycle (order confirmation, shipment, delivery, returns), agent↔merchant messages, and state transitions.
Work
- Company
- AI Product Engineer
- Role
- Start-ups / Scale-ups
- Date
- Company
- Full-stack Product Engineer
- Role
- Start-ups / Scale-ups
- Date
- Company
- UX/UI Designer / Front-end Developer
- Role
- Enterprise Technology
- Date