Category
8 articles on Method — written while building AI-native products, and mostly about the failures that produced no error message.
An AGENTS.md rule earns its place when you can name the specific failure it prevents. In a 79-line file, five of nine rules exist because something broke without producing an error, two because the framework changed, one is a convention and one is not about code. Rules without an incident behind them make agents measurably worse.
MIGI is a fleet of AI agents built by Suman Debnath, running since 8 July 2026 at forty to fifty agent runs a day. It has cost under five dollars in total, against published estimates of $185 to $480 a month for a comparable personal stack, because the paid model is a fallback rather than the default.
Three rules do most of the work: never let a key appear in code, keep environment files out of version control, and hold production values in the host's environment settings. Rotation is the part most people skip. Push protection catches known key formats only, so it is a net rather than a guarantee.
Running a coding agent with auto-accept enabled removes the only step that checks whether the work is the right work. The common failures are not broken code but overbuilding, quiet substitution of a different solution, and confidently finishing something nobody asked for. Keeping approval manual costs time and is what makes the output defensible.
The expensive part of building software alone is not the hours, it is the absence of correction. There is no colleague to say the approach is wrong, no review before a decision becomes permanent, and no one who knows the codebase well enough to disagree usefully. Tutorials, forums and AI assistants each replace part of that, and none of them replace disagreement.
Less syntax than expected and more operations than anyone warns you about. The gap is not writing code — an assistant does that — it is knowing where data lives, how deployment differs from a machine that works, what happens when something breaks in front of a user, and being able to read a change well enough to accept or reject it.
Research before prompting accounts for roughly ten to twenty percent of a project's duration, and generating the first working version takes less time than any other phase. The prompt is written last, after the reading, and carries context, goal and worked examples — which is what prevents confident but confused output.
A weekend produces a working version, not a finished product — those are separated by weeks of unglamorous work. What makes the weekend possible is severe scope discipline and research before the first prompt. What makes it defensible is refusing to cut the handful of things that are cheap now and expensive later.
Open to meaningful collaborations, AI-native systems, product strategy, and future-focused conversations.
“Human instinct. AI amplification.
Systemic execution.”
Suman Debnath
·Brand Marketing Leader & AI Product Builder
© 2026
This site records visit data — pages viewed, time and scroll depth, device, your IP address and the approximate location and network provider derived from it — and sends it to me privately. It also runs Google Analytics and Vercel Analytics. Full detail and how to opt out.
This site, its code and its content are © 2026 Suman Debnath. All rights reserved — none of it is open source, and copying it needs permission first. Terms of use.