Archive

RBI FREE-AI implementation notes — 26 recommendations to...

Every one of the 26 RBI FREE-AI recommendations, mapped to a specific file in a working multi-agent platform. What's ✅ done, what's 🟡 partial, what's ⚪ honest gap.

Copyright and Software

Every line of code you write is, the instant you write it, protected by copyright — automatically, with no registration required. That surprises many engineers, and its implications run deep: copyright is the legal foundation of who owns software, why you can't just copy others' code, and why software licenses (which grant permission around copyright) exist at all. Understanding copyright as it applies to code is the single most relevant piece of IP knowledge for a working engineer. (Educational, not legal advice.)

Every line of code you write is, the instant you write it, protected by copyright — automatically, no registration required. Its implications run deep: copyright is the legal foundation of who owns software, why you can't just copy others' code, and why licenses exist. It's the most relevant IP knowledge for a working engineer. (Educational, not legal advice.)

Why Go for production agentic AI

Stdlib over libraries, single binary over framework, fail-closed defaults over forgiveness. The boring-on-purpose case for choosing Go to ship a multi-agent system into a regulated environment.

Intellectual Property Overview

Intellectual property is one of the most valuable assets a technology company has — and one of the most confused topics among engineers, who often use "copyright," "patent," and "trademark" interchangeably. They're not interchangeable: they protect entirely different things, in different ways, for different durations. Getting the mental map right — four distinct types, each for a different kind of creation — is the foundation for everything about IP. (As always: educational, not legal advice.)

Intellectual property is one of the most valuable assets a tech company has — and one of the most confused topics among engineers, who use 'copyright,' 'patent,' and 'trademark' interchangeably. They're not: they protect entirely different things, in different ways. Getting the mental map right is the foundation. (Educational, not legal advice.)

BCP for AI — forced-failure drills

Fallback agents plus a CI step that replaces the primary agent with one that always errors. If the fallback doesn't produce a usable answer, the PR can't merge.

Business Entities

The first legal decision most founders face is also one of the most consequential and least understood: what kind of legal entity is your business? The choice — sole proprietorship, LLC, corporation — determines whether your personal assets are shielded when things go wrong, how you're taxed, and whether you can raise money. Getting it right early is far easier than fixing it later. (As always: this is general education, not legal or tax advice — the specifics vary by jurisdiction and situation, so consult professionals for your case.)

The first legal decision most founders face is also one of the most consequential and least understood: what kind of legal entity is your business? The choice — sole proprietorship, LLC, corporation — determines whether your personal assets are shielded, how you're taxed, and whether you can raise money. (Educational, not legal/tax advice.)

Sovereign AI is a policy, not a slide

Classification → provider allowlist. A pii-classified message can only reach a provider whose region is in the allowlist for pii. Sovereignty as a runtime gate, not a checkbox.

Why Engineers Should Understand Legal Basics

Legal issues have a way of being invisible right up until they're catastrophic — the open-source license you didn't read, the equity you didn't paper, the IP you didn't realize you'd signed away. Engineers and founders don't need to become lawyers, but a working literacy in a few legal basics prevents expensive, avoidable mistakes and tells you when you genuinely need professional help. This series builds that literacy. (An important note up front: this is general education, not legal advice — for real decisions, consult a real lawyer.)

Legal issues have a way of being invisible until they're catastrophic — the open-source license you didn't read, the equity you didn't paper, the IP you didn't realize you'd signed away. Engineers don't need to become lawyers, but a working literacy in a few legal basics prevents expensive mistakes and tells you when you need professional help. (Educational, not legal advice.)

NPCI rail routing with human-in-the-loop

UPI, IMPS, NEFT, RTGS — which rail depends on amount, urgency, and success history. A deterministic chooser with a HITL gate for high-value transactions.

Building a Great Team

Everything in this series — hiring, interviewing, onboarding, feedback, growth, retention — converges on a single goal: building a great team. A great team isn't just a collection of talented individuals; it's the right people, working well together, in an environment that lets them do their best work. This closing post pulls the threads together into the bigger picture of team-building, and returns to where the series began: because an organization is its people, building a great team is arguably the most important and highest-leverage thing any leader can do.

Everything in this series — hiring, interviewing, onboarding, feedback, growth, retention — converges on a single goal: building a great team. A great team isn't just a collection of talented individuals; it's the right people, working well together, in an environment that lets them do their best work. Because an organization is its people, this is the highest-leverage thing a leader does.

Policy as code, without the risk team having to ship code

A tiny CEL-style DSL plus a board-approved YAML file. The risk team adds a governance rule by editing a config file; engineering ships the rule by restarting the service.

Retention and Engagement

Losing a good person is one of the most expensive things that quietly happens to a team — the lost knowledge, the disruption, the months and dollars to replace them, the hit to morale — yet turnover is often treated as inevitable rather than as something you can influence. People leave for understandable reasons, most of them addressable, and keeping good people engaged and staying is far cheaper and better than constantly replacing them. Retention isn't luck; it's the result of how you treat, grow, and engage your people.

Losing a good person is one of the most expensive things that quietly happens to a team — the lost knowledge, the disruption, the months to replace them — yet turnover is often treated as inevitable rather than something you can influence. People leave for understandable, mostly addressable reasons, and keeping them engaged is far better than constantly replacing them.