Enterprises keep adopting coding agents the way they once adopted IDEs: one vendor UI, one permission model, one audit story. That breaks the moment the same agent has to sit behind a CI gate, an internal portal, and an engineering org that will not standardize on a single desktop app.

The Agent Client Protocol (ACP) is the seam that lets you reverse that dependency. Own a client control plane — sessions, modes, permissions, audit — and treat the agent as a swappable stdio backend. Go is a strong language for that plane: process supervision, typed JSON-RPC, and concurrent session fan-out are boring Go problems, not demo glue.

The harder question, which I take up below: how much coupling does that actually remove? Less than the protocol marketing implies — and the remainder is why the client plane has to carry the policy.

I have spent the last few months reading source code of real coding agents — not the model, the scaffolding around it. What I found surprised me: the most interesting engineering is not the brain; it is the nervous system.

This post is what I learned from that source-code dive. We look at the code that wraps the model—the control loops, concurrency primitives, state management, and event plumbing—to understand what makes a coding agent usable in production. Building a coding agent is not just about calling an API; it is a distributed systems problem. You have to manage long-running state, coordinate multiple sub-agents, and ensure that a thought process that takes 30 seconds does not freeze your entire environment. The runtime that wires these pieces together is what separates a demo from a production-grade agent.

AI agents can generate hundreds of lines of correct, well-tested code. They cannot tell you whether it's the right code — and vibe coding is quietly accumulating the kind of reliability debt you won't see until an incident.

I spent a lot of months during 2025 doing what most engineers were doing: throwing prompts at Claude or Windsurf's Cascade, reviewing the output, tweaking, repeating. It felt productive. Until the day I tried to add a feature to a codebase I'd largely handed off to AI agents, and realized I had no real mental model of what had been built. The code was clean. The tests passed. But I couldn't confidently explain why it worked the way it did — and as someone responsible for reliability at scale, that's not a position I can afford to be in.

That experience pushed me toward spec-driven development (SDD), and it's genuinely changed how I work with AI agents. This post is my attempt to document what I've learned — the what, the why, and a real example of how I've applied it.

Vishal Gandhi How Open Standardized protocols like the Anthropic Model Context Protocol (MCP) can transform enterprise AI integration from a complex matrix of custom connections to a more manageable ecosystem that accelerates innovation and reduces technical debt.

In today's data-driven world, Business Intelligence (BI) has become indispensable for organizations seeking to gain insights from their data. Traditionally, BI solutions have been associated with hefty price tags and complex implementations. However, the landscape is rapidly changing with the emergence of open-source BI solutions that are flexible in adoption, run on commodity hardware, integrate with multiple existing data sources, and leverage a code-first approach. This shift is not only making BI more accessible but also more flexible, innovative, and powerful than ever before. Open source BI solutions are democratizing data analytics, allowing organizations of all sizes to harness the power of their data. Furthermore, the integration of cutting-edge, in-memory database technologies like DuckDB is supercharging these solutions. DuckDB's ability to process large datasets with lightning speed, coupled with its low memory footprint and seamless integration capabilities, is enabling real-time analytics and complex data manipulations that were once the domain of expensive, enterprise-grade systems. This powerful combination of open-source BI tools and efficient in-memory databases is truly revolutionizing the way organizations approach data analysis, making sophisticated BI capabilities accessible and affordable for businesses of all sizes.

The world of API development tools is experiencing a major shift, fueled by new technologies and changing developer preferences. In this blog post, I dive into the dynamic ecosystem of API clients, highlighting well-known names like Postman and Insomnia, alongside innovative open-source alternates such as Bruno and HURL. We'll explore how these developments are impacting enterprise IT strategies, boosting developer productivity, and enhancing overall business agility.

Introduction​

Starting a career as a software developer in the fast-paced and ever-evolving IT industry can be both exciting and challenging. To thrive in this field, it is essential to equip yourself with the right skills, tools, and technologies. In this article, we will highlight key areas of focus that will help you establish a solid foundation as a software developer.

Open Source is a great way to learn and contribute to the community. With a nearly endless array of open source projects available to consume and contribute to these days, Need some inspiration? Whether you’re new to the world of open source, are gearing up for Open Source in the new year, or just want to see what other folks are excited about, check out a few of my favorite open source projects i discovered during 2022. 

Documentation is the most critical activity of any product development. The engineer and user experience improve when there is up-to-date Documentation. Most often, in organizations and products, Documentation is an afterthought, and this is not a good practice. If we want more engineers to contribute to the product, Documentation should be considered as code and part of the product development. Engineers should be encouraged to write Documentation before writing the source code.

Introduction to REST API​

REST (Representational State Transfer) is an architectural style for building distributed systems. A Web API conforms to the REST architectural style, called RESTful Web API.

REST APIs are stateless, client-server, cacheable, layered systems designed around resources. The set of resources is known as the REST API's resource model