What OpenClaw’s Architecture Taught Me About Building Real GenAI Systems(part 2)- The Solution

Many people think building AI agents is mostly about the LLM. In reality, most of the complexity sits in the infrastructure around it. In my previous article(https://aiforproduction.blog/2026/03/12/what-openclaws-architecture-taught-me-about-building-real-genai-systemspart-1/), I explored the architectural challenges behind building systems like OpenClaw — things like always-on infrastructure, memory management, tool execution, and concurrency. Today, I want to share what I … Continue reading What OpenClaw’s Architecture Taught Me About Building Real GenAI Systems(part 2)- The Solution →

What OpenClaw’s Architecture Taught Me About Building Real GenAI Systems(part 1)

Over the past few days, I’ve been exploring OpenClaw and trying to run parts of it locally. As someone working on production GenAI systems, I’m always curious about how different frameworks approach building AI agents that operate in real environments. What stood out while studying OpenClaw is something I keep seeing across many GenAI systems: … Continue reading What OpenClaw’s Architecture Taught Me About Building Real GenAI Systems(part 1) →

Will Jobs Exist as We Know Them? (The Big Picture)

In Part 1(https://aiforproduction.blog/2026/02/22/will-jobs-exist-as-we-knowthe-fear/) , we saw something uncomfortable. An AI agent was able to independently build a model — potentially better than a human-built solution — and even generate a GDPR compliance report. At first glance, the conclusion seems obvious: AI automates coding → developers disappear. But that assumption misses something important. Building the model … Continue reading Will Jobs Exist as We Know Them? (The Big Picture) →

Will Jobs Exist as we know?(The Fear)

This series started because of a 1–1 conversation with a reportee. One of my reportees asked me a simple question: “With everything happening in AI… should I be worried, and what will happen to jobs in 5-10 years?” It wasn’t a dramatic question. It wasn’t about headlines. It was about career, growth, and uncertainty. That … Continue reading Will Jobs Exist as we know?(The Fear) →

How to Think About AI Systems in 2026

Why GenAI, Predictive Models, and Agents Need to Work Together I’ve been working in AI since well before the GenAI wave, and one thing that has become almost annoying in the last couple of years is how quickly every problem gets thrown at an LLM—with the expectation that it will magically solve everything. It won’t. … Continue reading How to Think About AI Systems in 2026 →

Why Do Multi-Agent LLM Systems Fail? Insights from Recent Research

As GEN AI evolves, multi-agent systems (MASs) are gaining traction, yet many remain at the PoC stage. So this is where research papers and surveys help. Over the weekend, I explored their failure points and found a fascinating study worth sharing. MASs promise enhanced collaboration and problem-solving, but ensuring consistent performance gains over single-agent frameworks … Continue reading Why Do Multi-Agent LLM Systems Fail? Insights from Recent Research →

Evaluation and Experiment Tracking for LLM’s

Have you ever done text generation with an LLM and though: I wish I could track experiments and evaluate different LLM results in terms of cost, sample comparison and memory together like below? If yes this article for you. Experimentation tracking is one critical piece of model development which is very important as it helps … Continue reading Evaluation and Experiment Tracking for LLM’s →

Understanding RAG and Vector DB

For anyone in the field of AI and ML, they probably do know all of these terms. But how do you explain these to someone new. Let's try understanding this. USE CASE: Mark wants to plan a trip to Georgia in Europe and he wants to use an LLM for this. INTERACTION WITH LLM: Attempt … Continue reading Understanding RAG and Vector DB →