Protecting Your LLM Applications from Prompt Injection Attacks
- Published
- Author
- Nitturu BabaSystem Analyst
Learn practical techniques to defend against prompt injection attacks in AI applications with simple code examples.
Read moreTech Tales
Hey there! Welcome to our blog, where our team shares all things tech from cool solutions to everyday challenges to innovative ideas we're excited about. We're here to share our journey, inspire yours and have some fun along the way!
How to Read a Flame Graph in Chrome DevTools
- Published
- Author
- Syed SibtainSystem Analyst
A deep, practical guide to reading flame charts in Chrome DevTools, spotting expensive functions, and validating performance improvements.
Read moreRuby's JIT Journey: From MJIT to YJIT to ZJIT
- Published
- Author
- Sujay PrabhuSenior System Analyst
A walkthrough of Ruby’s JIT history and the design ideas behind MJIT, YJIT, and ZJIT
Read moreEvaluating LLM Agents: Confidence Through Pre-Production Testing
- Published
- Author
- Nived HariSystem Analyst
How to design practical pre-production testing for LLM systems—using datasets, evaluators, and experiments to catch regressions before shipping.
Read moreEvaluating LLM Agents: Building the Design Phase Right
- Published
- Author
- Adithya HebbarSystem Analyst
The first step to production-ready agents. Master visual debugging, trace collection, and unit testing with LangGraph Studio, LangSmith, and Vitest before moving to pre-production.
Read moreReverse Proxying over WebSockets: Building a Production-Ready Local Tunnel
- Published
- Author
- Syed SibtainSystem Analyst
A practical look at the challenges of exposing local servers to the internet, and how we built a production-ready tunneling system using WebSockets and NestJS.
Read moreGetting Started with DeepAgents: Building Structured, Long-Running AI Agents
- Published
- Author
- Nived HariSystem Analyst
A practical introduction to LangChain’s Deep Agents—exploring planning, memory, iterative workflows, subagents, and how this framework enables long-horizon AI reasoning.
Read moreOperating Kafka in Rails with Karafka: Production Architecture, Consumers, and DLQs (Part 2)
- Published
- Author
- Syed SibtainSystem Analyst
In Part 2, we dive deep into the Sync-Out pipeline—how Rails publishes events to Kafka, how our legacy adapter writes to SQL Server 2009 using TinyTDS, and how Dead-Letter Queues (DLQs) became our lifeline during production incidents. This post covers transaction management, service objects, and operational workflows for handling failures.
Read moreOperating Kafka in Rails with Karafka: Production Architecture, Consumers, and DLQs (Part 1)
- Published
- Author
- Syed SibtainSystem Analyst
This post breaks down our production architecture for event streaming in Rails using Kafka and Karafka—from designing producers and consumer flows to handling failures with DLQs and keeping warehouse databases in sync reliably.
Read moreUnderstanding the Browser's Layout Engine: Formatting Contexts, Stacking, and Compositing Explained
- Published
- Author
- Syed SibtainSystem Analyst
This blog provides a comprehensive explanation of the browser's layout engine, including formatting contexts, stacking, and compositing. It covers the key concepts and processes that enable the browser to render web pages efficiently and accurately.
Read moreShowing page 1 of 17