Agentic Security & Governance

Insights

AI Agents are being developed to read and respond to emails on our behalf, chat on messaging apps, browse the internet, and even make purchases. This means that, with permission, they can access our financial accounts and personal information. When using such agents, we must be cognizant of the agent’s intent and the permissions we grant it to perform actions. When producing AI agents, we need to monitor for external threats that can sabotage them by injecting malicious prompts.

Why Model Context Protocol Matters: Building Real-World Workflows

Insights

When large language models (LLMs) first became accessible, most of our interactions with them were bound within a single prompt-response cycle. You asked, they answered. But as developers began embedding AI into real systems (IDE copilot etc.), it became clear that prompts alone couldn’t sustain meaningful workflows. AI needed context, memory, and the ability to act, not just chat. That’s where the Model Context Protocol (MCP) enters the picture (to solve the context and ability needs).  

Prompt ≠ Purpose: Why Goal-Directed Behavior in Agentic AI Demands More Than Just Good Prompts

Insights

Imagine this: you ask a generative AI tool to “summarize last quarter’s procurement activity for compliance reporting.” Within seconds, it produces a well-structured summary, complete with headings and bullet points. So far, so good. Next, you instruct it to email the report to the compliance officer, attach the raw data for audit purposes, and log the interaction in your internal documentation system. Here’s where the system begins to falter. It doesn’t remember which procurement dataset it used in the first step. It requires you to re-specify the compliance officer’s details, the file format, the logging protocol, and the context all over again. 

What is Vibe Coding?

Insights

Vibe coding isn’t an official term. It’s more of a coding mindset. Vibe coding is a programming approach that leverages AI tools to create code based on natural language descriptions of desired functionality. In this method of developing code, we rely heavily on autocomplete, AI coding assistants like GitHub Copilot or ChatGPT or various AI Coding Editing tools, and use existing code examples, all while making decisions based on intuition rather than structured instruction.