LLM Inference Optimization: What Actually Makes Your Model Fast

Posted on Sat 18 April 2026 in GenAI • Tagged with LLM, Inference, Optimization, Quantization, KV Cache, Speculative Decoding, Flash Attention

When you send a prompt to an LLM, three layers shape how fast you get a response: the hardware (GPUs, TPUs, LPUs), the model size and architecture, and the inference engine strategies sitting on top. Most of the latency battle is fought at that third layer — and the core problem …


Continue reading

PromptTemplate Explained for 10 year old

Posted on Fri 17 April 2026 in GenAI Basics • Tagged with langchain, prompt-engineering, beginner, kactii

PromptTemplate is one of those ideas that sounds technical but is actually something you already understand from everyday life. Here are three ways to see it clearly.

Cookie Cutter 🍪

The Shape — A star-shaped cookie cutter that never changes. You press it into any dough and get the same star, every …


Continue reading

Six Terms You Must Know Before Building Agentic AI Systems

Posted on Fri 17 April 2026 in GenAI • Tagged with Agentic AI, MCP, RAG, Multi-Agent, Memory, Agent Architecture

If you are shipping agentic systems in 2026 and these six terms are fuzzy, you are building on sand. This is the foundational vocabulary — not hype, not vendor marketing, just the concepts that actually show up when you are designing, debugging, or scaling an agent pipeline.

The Six Terms

Model …


Continue reading

The Great Password Dilemma

Posted on Fri 17 April 2026 in Engineering Stories • Tagged with passwords, encoding, human-computer gap, security, UX

We encode information every single day — and we almost never think about it.

A student called me to get her account unlocked. She dictated her password over the phone: apple1234. I typed it in. Login failed. We went back and forth, both confused. Then she clarified: she meant appleOne2Three4.

Same …


Continue reading

AgentLegatus — Terraform for AI Agents

Posted on Wed 15 April 2026 in Agents • Tagged with agentlegatus, multi-agent, llm, open-source, orchestration, python, langgraph, vendor-agnostic

The multi-agent space is fracturing fast. Teams pick LangGraph one quarter, switch to CrewAI the next, then discover Google ADK or AWS Strands and wonder if they should migrate again. Every switch costs weeks — ripping out abstractions, rewriting orchestration logic, re-testing state management. This is the exact problem Terraform solved …


Continue reading

Git Upstream Demystified — --set-upstream, Aliases, and Shell Functions

Posted on Wed 15 April 2026 in DevTools • Tagged with git, terminal, shell, zsh, productivity

If you've ever wondered what --set-upstream really means in Git — or why it isn't just called --set-remote — this post breaks it down, along with practical tricks to explore Git options faster.

Core Concepts

--set-upstream vs --set-remote — "remote" in Git already refers to the server (like origin), so naming it --set-remote …


Continue reading

GitHub Spec Kit: A Practical Introduction to Spec-Driven Development

Posted on Tue 14 April 2026 in GenAI • Tagged with GenAI, LLM, SpecKit, GitHub, SDD, AIcoding, Copilot, AgentDev

"The issue isn't the coding agent's coding ability, but our approach.
We treat coding agents like search engines when we should be treating them
more like literal-minded pair programmers."

— Den Delimarsky, GitHub Principal Product Manager


The Problem With Vibe Coding

If you've used an AI coding assistant, you've experienced vibe …


Continue reading

Agentic System Design Concepts - Patterns Every AI Engineer Should Know

Posted on Sat 11 April 2026 in GenAI • Tagged with GenAI, AI-agents, LLM, agentic-systems, design-patterns, reliability

Building reliable AI agents isn't just about picking the right model — it's about the patterns you wire around it. Here's a concise reference of 15 agentic system design concepts worth knowing. Two lines each — just enough to understand what they do and why they matter.

Resilience & Failure Isolation

Agent Circuit …


Continue reading

Every Claude Code Concept You Need to Know

Posted on Sat 11 April 2026 in GenAI • Tagged with GenAI, Claude-Code, LLM, agents, developer-tools, local-AI

Claude Code is not a chatbot. It lives in your terminal, reads your actual files, writes code, runs commands, and executes multi-step workflows — all with your permission. Here are 30 concepts you need to understand it properly. No fluff, no hand-holding.

The 30 Concepts

1. The Terminal — Claude Code doesn't …


Continue reading

Missing ZIP Option in Windows Right-Click Menu — Here's How to Fix It

Posted on Sat 11 April 2026 in Windows • Tagged with Windows, tips, context-menu, troubleshooting, productivity

The classic "Send to → Compressed (zipped) folder" option sometimes disappears from the Windows right-click context menu. Here's what causes it and how to get it back in under two minutes.

What Happened

Windows ships with a built-in ZIP shell extension handled by zipfldr.dll. When third-party tools like Git, VLC …


Continue reading