AI Agent Architecture: Why Process-Level Resilience Beats Proxy Gateways
The Great AI Architecture Debate When building reliable AI agents, there are two dominant approaches. Approach A: Proxy Gateway (LiteLLM, Braintrust, …
DevOps
⚑ Report a ProblemLatest DevOps news from Tech News
All topics
agents
ai
api
architecture
automation
aws
beginners
career
cloud
database
devchallenge
devops
docker
gemma
javascript
kubernetes
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
tutorial
typescript
webdev
Building Dhrishti - Part 3: Testing on a Production Grade System
I was now done with the basic setup. However, during my time working at my startup, I have learnt to think about a project wearing multiple caps. One …
Mixture of Experts (MoE): what it actually does under the hood, and when it pays off
Mixture of Experts (MoE): what it actually does under the hood, and when it pays off You deployed a 7B model in production. Response times are fine — …
What We Learned Scanning Netflix Atlas
Clear Code Intelligence scanned a public Netflix repository: Netflix/atlas . This is not a dunk on Netflix. It is a public-code methodology test. Afte…
Prompt cache, finally typed: shipping llm-ports 0.1.0-alpha.19
TL;DR. @llm-ports 0.1.0-alpha.19 ships a typed, provider-neutral surface for prompt caching across Anthropic, OpenAI, and Gemini. One optional cacheCo…
Stop Your Agent From Replying Twice: Dedup Patterns
Ever watched an email agent reply to the same message twice? The recipient gets two near-identical responses seconds apart, screenshots them, and your…
The AI Paper That Quietly Changes How Enterprises Scale
Most enterprises are chasing “AI at scale,” but many are stuck in the same loop: flashy demos, fragile POCs, and a long list of reasons why nothing is…
System Design - 17. Service Discovery & Service Mesh: How Thousands of Services Find Each Other
Covers: Client-Side vs Server-Side Discovery, Service Registries, Service Mesh (Istio/Envoy), Kubernetes DNS The Problem That Didn't Exist in the Mono…
System Design - 15. The Saga Pattern: How Uber Books a Trip Without a Single Database Transaction
Covers: Two-Phase Commit, Saga Pattern, Choreography vs Orchestration Sagas, Compensating Transactions, Idempotency The Question That Breaks Most Micr…
Building a Permission-Gated MCP Server in Laravel (Without Opening a Backdoor)
I spent today wiring an MCP server into a Laravel app that manages a Kong API gateway. The interesting part wasn't "make the AI talk to the app" — tha…
Why I Am Building Rudhra as an Agent Operating Platform
AI agents are moving fast. Every week, new frameworks, models, tools, and patterns appear. Developers can now build agents that reason, call tools, re…
The Freebuff Paradox: Elite Code Critic, Terrible Laravel Programmer
When you're building a complex backend system—like an enterprise-grade Point of Sales (POS) API using Laravel with a Modular Monolith architecture and…
REST API Design: Building APIs That Developers Love (2026)
REST API Design: Building APIs That Developers Love (2026) A great API is one that developers enjoy using. It's intuitive, consistent, well-documented…
The end of the programmer: 26 predictions I dare you to break
Essay · June 2026 · 26 theses · 3 horizons It's not about AI replacing devs. It's about who holds power inside the software production chain — and who…
System Design - A Frontend Engineer's Deep Dive
In general, most of the discussions around System Design are backend heavy, involving Databases, Microservices , Load Balancers and what not. But in t…
System Design - 13. Message Queues Explained: Why LinkedIn Built Kafka and Changed Async Communication Forever
Message Queues Explained: Why LinkedIn Built Kafka and Changed Async Communication Forever Covers: Point-to-Point vs Pub-Sub, Kafka Internals, Deliver…
Why New Language Features Need to Target AI Agents, Not Developers
For the last 50 years, programming language evolution has had one single north star: Human Ergonomics . We design syntax sugar, optional typing, and c…
What Designing a Binary Protocol Actually Taught Me
Most developers never have to design a network protocol from scratch. You use HTTP, gRPC, WebSockets, or something else that already exists and has be…
When Four Memory Systems Hit the Same Wall
I built a knowledge graph out of my own work sessions. Hundreds of them — transcripts of me building a system with LLMs, extracted into concepts, deci…
AI Agent Memory Is Not Chat History
Most AI agent systems start with a simple idea: "Let's give the Agent Memory". At first, this usually means saving previous messages, retrieving simil…
Engineering Design Document: Reusable Observability Platform V2
A production-focused redesign of a Stage 6 LGTM observability platform, moving from a single-service Anvila monitoring setup to a reusable, secure, hi…
Most AI Control Planes Have a Single-Region Failure Domain
The cloud spent fifteen years teaching architects to think in availability zones, regional redundancy, and distributed failure domains. AI infrastruct…
Proxy, Gateway, or Poll the Usage API? Picking an Architecture for AI Cost Visibility
At some point your AI bill stops being a rounding error and someone asks the obvious question: who spent what, on which model, doing what? Answering i…
Modern Data Stack Migration — Day 1: Scaling to 8+ Companies with DRY Architecture and Chasing a $2M Discrepancy
Hello everyone! Following up on my previous post , Day 1 of my Modern Data Stack migration was an absolute rollercoaster of refactoring and deep data …
Software engineering became software architecture.
Highly opinionated, based on my personal experience dogfooding my own setup. Not a prescription. I'm scratching the surface, with a lot left to learn.…
How to Build a Real-Time Slack Agent Using Bun, Hono, and Event-Driven Orchestration
Building Slack bots is fun until you try to integrate heavy AI pipelines. If you are building an AI agent that runs sequential steps (e.g., Planning -…
Creating a MiniDex
┌──────────────────────┐ │ MiniDEXFactory │ └──────────┬───────────┘ │ createPair(tokenA, tokenB) via Yul CREATE2 │ ▼ ┌──────────────────────┐ │ MiniD…
Building Reliable RAG Pipelines: From Prototype to Production
Most teams get RAG working in a notebook over a weekend. Very few get it working reliably in production. The gap is not model quality — it is engineer…
How Does Amazon Stop Two People from Booking the Same Seat?
You're on BookMyShow or Amazon. You see 1 seat left. You click it. Someone else clicks it at the exact same moment. The Problem Imagine 1000 people ar…
MCP vs Direct API Calls — My Agent Stack Has Zero MCP Servers
The Model Context Protocol is everywhere right now. Every agent tutorial opens with "first, set up your MCP servers." And yet the agent stack running …