Writing
Blog
Practical writing on LLM engineering, agentic systems, MLOps, and building AI products in production.
Advisory 2.0: AI Investing Stack That Requests Its Own Tools
When Advisory first launched, the goal was to turn a generic “financial chatbot” into a modular, production-grade AI investing stack - one designed to evolve its capabilities over time . We set to evolve through a simple principle: when Advisory can’t fulfill a task to increase app performance, it can request a new tool . Over time, this creates a feedback loop where the product continuously expands what it can do - not just in markets and investing, but in product growth an
Redefining Intelligent Systems - Engineering diary
Intro: At the forefront of AI, automation, and edge intelligence, ITQuarks team is shaping how the world interacts with software, data, and systems. Our flagship portfolio is a testament to our engineering depth and innovation mindset—delivering scalable, production-ready solutions that span industries from embedded systems and financial markets to multilingual content and healthcare automation. Here’s a look at the real-world impact of our most advanced AI-driven projects.
Craft a Product: Some basic ingredients
Launching a new product at a startup often feels like landing the perseverance rover on Mars —bold, challenging, and filled with unknowns. Every founder brings their own methodology and expectations about how and when their product should be delivered, frequently clashing with the pressures from customers, boards, and financial stakeholders. These dynamics significantly influence not only the product's direction but also the team's morale, energy, and productivity.
AI Investing, Engineered: Strands Agents with MCP & ACP for Personalised Insights
Advisory turns chat into action with Strands Agents, MCP/ACP orchestration, and a hardened financial API on a Dockerized microservices stack. We route across LLMs to balance quality and cost. Personalized Firebase notifications deliver timely, noise-free alerts. Dive into the architecture, agent autonomy, and UX choices that make real-time, user-centric investing possible.
AI Agents the new stack overflow for engineers?
At ITQuarks, we’re witnessing a shift that’s rewriting how we build software: AI isn’t just a tool — it’s becoming part of the team. We actively encourage our engineers to use AI during development. Why? Because it frees them to focus on high-level thinking, creativity, and system design — not boilerplate code.
Building something with AI?
We write about the problems we solve in production. If you're working on something similar, let's talk.
Book a 25-min call