// the knowledge base

Explore everything.

Every article, writeup and note across the platform β€” filter by world, difficulty, author or tag, sort your way, and save what matters.

πŸ€– AI / ML
Advanced

Experimenting with LLM Agents (and Where They Fall Apart)

I built three small agents to understand where the capability boundary actually is. The pattern: they are brilliant at one tool call and unreliable at the fifth. Notes on what survives contact.

Sandesh BramhaneAug 22, 2026
#llm#ai-agents#experiments1 min1272
πŸ€– AI / ML
Intermediate

Evaluating RAG: A Simple Framework That Actually Works

Most RAG projects fail at 'how do I know it's good?' I built a three-layer eval framework β€” retrieval, generation, and trust β€” that I run in under an hour per experiment. Here it is.

Riya DeshpandeAug 19, 2026
#rag#evaluation#llm1 min13202
🧠 DSA & Programming
Advanced

Dynamic Programming: The 4 Patterns That Repeat

Almost every DP problem I have solved is one of four shapes. Learn to recognize the shape first, then the recurrence writes itself. With worked examples and the space-optimization moves.

Sandesh BramhaneAug 15, 2026
#dsa#dynamic-programming#algorithms1 min1602
πŸ’» Development
Intermediate

Kubernetes for Full-Stack Devs: Honest Notes

I came to Kubernetes from writing React apps, and it humbled me. The mental model in 20 minutes, the five kubectl commands I use daily, and what I'd actually recommend for most apps.

Aarav KulkarniAug 11, 2026
#kubernetes#devops#containers1 min7122
πŸ€– AI / ML
Intermediate

Building a RAG Pipeline: From Chaos to 90%+ Recall

I rebuilt the same RAG system five times. Chunking strategy, embedding choice, and reranking moved my eval recall from 41% to 93% β€” here is each change, measured.

Sandesh BramhaneAug 8, 2026
#rag#llm#embeddings1 min13442
πŸ” Cybersecurity⚠ Spoilers
Beginner

Smokey: My First TryHackMe Walkthrough

A complete, commented walkthrough of TryHackMe's Smokey room β€” the perfect first box. Enumeration, exploitation, pivoting and privilege escalation, step by step.

Sandesh BramhaneAug 2, 2026
#tryhackme#walkthrough#linux1 min10392
🧠 DSA & Programming
Intermediate

Mastering the Two-Pointer Pattern in DSA

Two pointers turns O(nΒ²) brute force into O(n) β€” when the problem is sorted or order-preserving. The three sub-patterns, the exact conditions that unlock each, and worked solutions in C++ and JS.

Sandesh BramhaneJul 28, 2026
#dsa#algorithms#arrays1 min9002
πŸ’» Development
Beginner

Docker Compose: The Patterns I Wish I Had on Day One

The Docker Compose patterns that cover 95% of real local development: multi-service apps, persistent data, healthchecks, and the debugging moves that save hours.

Aarav KulkarniJul 20, 2026
#docker#compose#devops1 min5502
πŸ” Cybersecurity
Intermediate

SQL Injection: From Zero to Exploitation

How SQL injection actually works at the query level β€” error-based, union, blind and out-of-band β€” with the exact payloads and the mental model behind them.

Sandesh BramhaneJul 18, 2026
#web-security#sql-injection#sqli1 min14042
πŸ’» Development
Intermediate

REST API Design: Notes from Building Real Backends

After shipping half a dozen APIs, these are the design decisions that survived contact with real clients β€” naming, versioning, errors, pagination, and the mistakes I keep almost making.

Sandesh BramhaneJul 5, 2026
#rest#api#backend1 min9992
πŸš€ Hackathons
Intermediate

48 Hours, One Idea: My SentryAI Hackathon Story

How we took SentryAI β€” an AI log-analysis assistant for on-call engineers β€” from a napkin sketch to a top-3 finish in 48 hours. The architecture, the cuts, and the decisions that actually decided it.

Sandesh BramhaneJul 1, 2026
#hackathon#project-breakdown#architecture1 min7632
πŸ” Cybersecurity
Intermediate

OWASP Top 10 (2021) β€” What I Actually Test

The OWASP Top 10 is a list, not a methodology. Here is how I turn each category into concrete, repeatable testing steps during a web assessment.

Sandesh BramhaneJun 25, 2026
#owasp#web-security#pentesting1 min12482