/lm.png
Fractional CTO for Hardware-Enabled SaaS & Operations
Helping founders ensure their technology can handle the chaos of real-world operations.
I connect Physical and Digital Assets to deliver Business Outcomes.

This app should feel like…

That is not my style of communicating; I prefer strict, technical requirements. Recently, I helped someone build and deploy a web application. That person had zero interest in the technical aspects of any of that. Our conversation with my agentic development team focused on users’ feelings and impressions, not technical requirements and security concerns. My agents “somehow understood” the intent and iterated following the unconventional guidance. After some time, the app started to take shape and was nothing I’d expected.

Project Discovery Workflow

Source code is structured and easy to validate. How can you validate meeting notes and test commercial analysis? During my recent workshop, I found that Project Managers were more interested in AI agents than the Developers in the room. The reason became obvious: with a little help, PMs can improve their effectiveness in several distinct areas. The problem Software development is relatively easy to automate, but project management is more versatile and requires a different approach.

Maintain your focus; use boring solutions.

The local dim sensor failed to provide proper readings; there was no way to calibrate it or fix it otherwise. Since that was a stationary installation, I used the following workaround: 1️⃣ For those specific GPS coordinates, I created a lookup file containing sunrise and sunset timestamps for every day of the year. 2️⃣ I used UTC timestamps to avoid issues with daylight saving time updates. 3️⃣ When an event was detected, a simple script calculated the day/night-time value and enriched the AI agent’s input.

As awkward as it sounds, I'm my first customer.

In order to scale my single-person enterprise, I had to create an agentic development department. I’ve been working on this idea for a few months, overcoming various ups and downs (including software and hardware limitations). This setup was intended as my internal tooling to support daily development activities. My goal was to automate the commercial-grade software development, testing, and auditing process. I still manually review the final code changes, but I am not involved in iterative development.

Create AI that controls your AI, keeping it effective yet aligned.

The Problem Statement It rarely happens that an AI agent decides to drop the database to “recover space”. But if your agent gets too creative, how can you prevent it from doing harm? To truly leverage the potential of AI agents, we need to grant them significant autonomy. I’ve been experimenting with various approaches, and my agents went the “wrong path” more than once. Typically, those incidents were harmless (my test agents run on a dedicated, isolated server).

Blueprint to securely plug AI agents into any business process inside your organization.

The Problem Statement I wanted my agent to help me manage my emails, but I do not want it to be proactive and send emails in my name (which it did during my initial research phase). AI tried to spam potential customers - not what I wanted!!! Unfortunately, the default Gmail API is not very selective - the modification access also allows sending emails. The Implementation GPT5.5 suggested building a custom MCP extension to add extra guardrails.