Intro When you are building Gen AI applications where the users are not interacting with the model (backend agentic AI applications or triggering a LLM through api), then you are more or less star...

Intro When building generative AI applications—especially customer-facing ones like chatbots—content safety aren’t optional. They’re essential. Large language models (LLMs) are powerful, but they’...

This is a quick note to myself for future use cases. Often times, when devloping locally, i tend to point to a local MLFlow instance and then when deploying to upper environments, its redirected to...

Intro Building generative AI applications introduces unique challenges—challenges we didn’t have to think about when building regular, non-AI software applications (remember those? 🙂). One challeng...

Intro My career has fluctuated between software and data as primary focus areas, with infrastructure and DevSecOps as secondary strengths. While there may be more formal definitions of LLM evaluat...

Intro When you’re building modern software systems—especially anything powered by generative or agentic AI—observability quickly becomes one of the most important non-functional areas to get right ...

Intro You’ve built an agentic AI app. It may query your database, pull reports and so on - bottom line…it works. But take a step back and reflect, your agent has its own credentials. It’s connecti...

Intro Before implementing agents, teams should first deploy simple RAG to establish a baseline for comparison. One of the reasons is, if you are cost conscious, then RAG is the more deterministic L...

MCP The MCP protocol is a common language that lets AI apps and external tools communicate smoothly. Just like a browser uses HTTP to talk to websites, the MCP protocol lets an AI—such as ChatGPT,...

The Challenge Building a compelling generative AI demo is relatively straightforward in 2025. But taking that demo and transforming it into a production-ready, enterprise-grade system? That’s wher...