How to Reduce Hallucinations in LLM Applications
Proven ways to reduce LLM hallucinations: grounding with RAG, citations, structured output, abstention, verification checks, and evals that catch errors early.
WRITING / NOTES FROM THE FORGE
Articles
In-depth tech articles on system design, DSA, AI engineering, data engineering, and building software that lasts.
Fine-Tuning vs RAG vs Prompt Engineering: Which Should You Use?
Fine-tuning vs RAG vs prompt engineering compared: what each changes, costs, and fixes, plus a simple decision framework for choosing the right LLM approach.
Rate Limiting Algorithms Explained: Token Bucket, Sliding Window, and More
Rate limiting algorithms explained with code: token bucket, leaky bucket, fixed window, and sliding window, plus how to pick one and run it across servers.
Kafka vs RabbitMQ: Which Message Broker Should You Use?
Kafka vs RabbitMQ compared: log vs queue model, ordering, replay, routing, consumer groups, and clear guidance on which message broker fits your use case.
Prompt Injection: What It Is and How to Defend Your AI App
Prompt injection explained: direct vs indirect attacks, why no complete fix exists, and the layered defenses that limit damage in LLM apps and AI agents.
Design Patterns Every Developer Should Know (With Examples)
Design patterns every developer should know: Strategy, Factory, Observer, Decorator, Adapter, Builder, and Singleton, with TypeScript and when to skip each.
LLM Evaluation: How to Test AI Features Before Production
A practical guide to LLM evaluation: build a golden dataset, pick metrics, use LLM-as-judge carefully, and gate releases so AI features do not regress.
Docker vs Kubernetes Explained for Developers
Docker vs Kubernetes explained for developers: what each tool does, how they work together, key differences, and when you actually need a cluster at all.
CAP Theorem Explained Simply (With Real-World Examples)
CAP theorem explained simply: what consistency, availability, and partition tolerance really mean, CP vs AP with real examples, and how PACELC extends it.
Model Context Protocol (MCP) Explained With Examples
What is MCP? The Model Context Protocol explained with a real server example, message flow, tools vs resources vs prompts, transports, and security tips.
SOLID Principles Explained With TypeScript Examples
SOLID principles explained with TypeScript: what each of the five rules means, the code smell it fixes, and when applying it adds complexity you do not need.
How to Build an AI Agent: Architecture, Tools, and Guardrails
Learn how to build an AI agent step by step: the core loop, tool design, memory, and guardrails that keep an LLM agent useful, safe, and cheap in production.