https://www.harshrastogi.tech/ Writing by Harsh Rastogi, AI Product Engineer at Modelia, on shipping AI to production: Claude and Claude Code, AI agents, MCP, LLM cost, generative AI and full-stack engineering. 2026-10-04T03:30:00.000Z Harsh Rastogi https://www.harshrastogi.tech/about https://www.harshrastogi.tech/android-chrome-512x512.png https://www.harshrastogi.tech/og/harsh-rastogi-studio-card.jpg © 2026 Harsh Rastogi https://www.harshrastogi.tech/blog/spacexai-typescript-sdk-grok-xai-official-sdk-guide 2026-10-04T03:30:00.000Z 2026-10-04T03:30:00.000Z

SpaceXAI's experimental TypeScript SDK for Grok: install, streaming, X search, web search, code execution, remote MCP, video, voice and production gotchas.

https://www.harshrastogi.tech/blog/code-from-your-car-claude-code-carplay 2026-10-04T03:30:00.000Z 2026-10-04T03:30:00.000Z

I built carcode, an open-source way to code from your car: say "Hey Siri, Jarvis" and Claude Code reviews PRs and ships code over Apple CarPlay.

https://www.harshrastogi.tech/blog/claude-fable-5-back-export-controls-lifted 2026-07-01T03:30:00.000Z 2026-07-02T03:30:00.000Z

On June 30, 2026 the US lifted the export controls it placed on Claude Fable 5 and Mythos 5, and Fable 5 came back online globally on July 1. Here's the full timeline, what changed under the hood — a 99%+ bypass classifier, refusals, and fallback billing — and what developers need to do to ship on claude-fable-5.

https://www.harshrastogi.tech/blog/facebook-instagram-down-global-outage-june-12-2026 2026-06-12T03:30:00.000Z 2026-06-12T03:30:00.000Z

A widespread outage hit Facebook, Instagram, and Messenger on June 12, 2026, with users across the US, Europe, Asia, and the Middle East reporting blank feeds, forced logouts, and 'query error' messages. Here's what's confirmed, what isn't, and what engineers can learn from Meta's outage history.

https://www.harshrastogi.tech/ai-pulse/2026-06-frontier-models-mcp-everywhere 2026-06-12T03:30:00.000Z 2026-06-12T03:30:00.000Z

Anthropic ships Claude Fable 5, Google readies Gemini 3.5 Pro, Microsoft builds its own coding models, MCP moves to the Linux Foundation, and AI video becomes the default for e-commerce content.

https://www.harshrastogi.tech/blog/claude-opus-4-8-release-features-benchmarks-pricing 2026-05-29T03:30:00.000Z 2026-05-29T03:30:00.000Z

Anthropic shipped Claude Opus 4.8 on May 28, 2026. SWE-Bench Pro jumps from 64.3% to 69.2%, Fast Mode runs 2.5× faster at 3× lower cost, and Dynamic Workflows lets Claude Code orchestrate hundreds of subagents. Here's the full developer breakdown.

https://www.harshrastogi.tech/blog/gemini-cli-shutdown-antigravity-migration-guide 2026-05-27T03:30:00.000Z 2026-05-27T03:30:00.000Z

Google's Gemini CLI shuts down June 18, 2026. A practical, step-by-step migration guide to Antigravity CLI with before/after code, env vars, auth, and CI fixes — done in 15 minutes.

https://www.harshrastogi.tech/blog/claude-mythos-project-glasswing-zero-day-vulnerabilities 2026-05-27T03:30:00.000Z 2026-05-27T03:30:00.000Z

Anthropic's unreleased Claude Mythos model uncovered 10,000+ zero-day vulnerabilities in a month through Project Glasswing. What AI-powered vulnerability discovery means for developers, dependency security, and the future of cybersecurity in 2026.

https://www.harshrastogi.tech/blog/github-supply-chain-breach-npm-pip-security-audit 2026-05-26T03:30:00.000Z 2026-05-26T03:30:00.000Z

GitHub disclosed a supply chain breach this week exposing internal code and customer data. I audited Modelia's dependency tree right after — here's what I found, what you should check, and the patching playbook for 2026.

https://www.harshrastogi.tech/blog/big-tech-ai-spending-layoffs-junior-mid-engineers-2026 2026-05-25T03:30:00.000Z 2026-05-25T03:30:00.000Z

Meta, Amazon, Microsoft and Google are spending record amounts on AI infrastructure while cutting 170,000 jobs in 2026. A grounded, honest read on what this actually means for engineers 1–3 years into their career.

https://www.harshrastogi.tech/blog/model-context-protocol-mcp-developer-guide-production 2026-05-24T03:30:00.000Z 2026-05-24T03:30:00.000Z

A hands-on guide to production MCP servers beyond hello-world: real code, auth, tool registration and observability, from an AI Product Engineer at Modelia.

https://www.harshrastogi.tech/blog/ai-writing-60-percent-code-2026-what-actually-happens-developers 2026-05-23T03:30:00.000Z 2026-05-23T03:30:00.000Z

Gartner says 60% of code will be AI-written by end of 2026. Stack Overflow says 84% of developers use AI but only 29% trust it. I've shipped production systems with AI daily for 18 months — here's what's real, what's hype, and what changes for your job.

https://www.harshrastogi.tech/blog/shopify-ai-self-review-app-store-submissions 2026-04-26T03:30:00.000Z 2026-04-26T03:30:00.000Z

Shopify's new AI self-review checks your app for App Store compliance before you submit. How it works, what it flags and how to pass review on the first try.

https://www.harshrastogi.tech/blog/claude-opus-4-7-release-developer-guide 2026-04-19T03:30:00.000Z 2026-04-19T03:30:00.000Z

Anthropic released Claude Opus 4.7 on April 16, 2026. A hands-on look at what changed, how it compares to Opus 4.6, the new xhigh effort level and task budgets, and what the Project Glasswing safeguards mean for production AI systems.

https://www.harshrastogi.tech/blog/building-agentic-ai-systems-real-world-patterns 2026-03-15T03:30:00.000Z 2026-03-15T03:30:00.000Z

How I built autonomous AI agents at Asynq and Modelia that reason, plan and run multi-step tasks: tool use, memory, orchestration and production guardrails.

https://www.harshrastogi.tech/blog/anthropic-claude-agentic-workflows-production 2026-03-10T03:30:00.000Z 2026-03-10T03:30:00.000Z

How we use Anthropic's Claude API to power agentic workflows at Modelia.ai — from tool use and extended thinking to structured outputs and multi-turn agents. Practical patterns for building reliable AI agents with Claude.

https://www.harshrastogi.tech/blog/agentic-ai-error-recovery-observability-patterns 2026-03-05T03:30:00.000Z 2026-03-05T03:30:00.000Z

Lessons from running agentic AI systems at scale — how we handle failures, monitor agent behavior, manage costs, and scale from single agents to multi-agent pipelines at Modelia.ai and Asynq.ai.

https://www.harshrastogi.tech/blog/building-scalable-microservices-nodejs-trpc 2025-01-15T03:30:00.000Z 2026-03-01T03:30:00.000Z

Type-safe microservices with tRPC, Prisma and Node.js: patterns from Asynq and Modelia's studio platform that delivered a 40% performance gain.

https://www.harshrastogi.tech/blog/optimizing-postgresql-queries-prisma-orm 2025-01-08T03:30:00.000Z 2026-02-15T03:30:00.000Z

Learn techniques to improve database performance by 40%. Real-world examples from production systems at Asynq.ai and Modelia.ai handling millions of requests daily.

https://www.harshrastogi.tech/blog/react-performance-optimization-2025 2025-01-02T03:30:00.000Z 2026-01-15T03:30:00.000Z

Modern strategies to build blazing-fast React applications. From code splitting to memo patterns, real techniques from building EduFly and GyanSathi LMS.

https://www.harshrastogi.tech/blog/docker-best-practices-fullstack-applications 2024-12-20T03:30:00.000Z 2026-01-10T03:30:00.000Z

From development to production: containerization strategies that ensure consistency, security, and scalability. Lessons from deploying EduFly on AWS.

https://www.harshrastogi.tech/blog/nextjs-14-app-router-complete-guide 2024-12-12T03:30:00.000Z 2024-12-12T03:30:00.000Z

Master the new App Router, Server Components, and data fetching patterns. Everything you need to build production-ready Next.js applications.

https://www.harshrastogi.tech/blog/lessons-building-software-indian-defence 2024-11-25T03:30:00.000Z 2026-03-01T03:30:00.000Z

Insights from building frontend interfaces at Bharat Electronics Limited (BEL) for the Indian Airforce — rigorous processes, reliability, documentation, and the weight of critical systems.

https://www.harshrastogi.tech/blog/redis-caching-strategies-high-performance-apis 2024-11-15T03:30:00.000Z 2024-11-15T03:30:00.000Z

Implementing effective caching patterns that reduced our API response times by 60% at Asynq.ai. Learn cache invalidation, TTL strategies, and common pitfalls.

https://www.harshrastogi.tech/blog/typescript-advanced-patterns-production 2024-11-05T03:30:00.000Z 2024-11-05T03:30:00.000Z

Go beyond basics with discriminated unions, template literals, and conditional types. Real patterns from enterprise codebases at Modelia.ai.

https://www.harshrastogi.tech/blog/aws-architecture-startup-scale 2024-10-20T03:30:00.000Z 2024-10-20T03:30:00.000Z

Cost-effective cloud architecture that grows with your startup. How I architected EduFly to serve 15K+ users on AWS with 99.9% uptime.

https://www.harshrastogi.tech/blog/ci-cd-github-actions-complete-setup 2024-10-10T03:30:00.000Z 2024-10-10T03:30:00.000Z

Automate your deployment pipeline from testing to production. Real workflows from EduFly, Asynq.ai, and Modelia.ai deployments.