nitishagar's comments

On: AI coding assistant is writing tests that protect bugs

[nitishagar]

Is AI writing tests that protect bugs? Why TDD and Hexagonal Architecture are the only ways to ground AI-generated code.

On: SoberAI – Open-source Lighthouse for AI agent readiness

[nitishagar]

I built SoberAI because I kept seeing the same problem: AI crawlers (GPTBot, ClaudeBot, PerplexityBot) don't execute JavaScript. Your React SPA is literally a blank page to them. There was no tool to audit for this — so I made one. SoberAI is an Electron app that scores your site 0-100 across four categories: SSR readiness, Schema.org coverage, semantic HTML structure, and content extractability. It renders your page twice with Playwright (JS on vs off) and diffs the content. LLM-powered recommendations are optional (Ollama local or OpenAI). One command: npm install && npm run electron:dev No accounts. No telemetry. MIT licensed. ~3K lines of JS. Docs: https://nitishagar.github.io/sober-ai Would love feedback on the scoring methodology and what auditors to add next.

On: The Most Important Code You're Not Reviewing

[nitishagar]

I wrote about "Agentic Debt" and the new OWASP LLM07:2025 classification. The industry is finally converging on a standard: Prompts are not secrets or config.

On: AI agents can cut MTTR by 40%

[nitishagar]

Slash incident response time by 40%. Explore multi-agent patterns and RAG strategies used by Netflix, Uber, and Microsoft to automate Ops.

On: Engineering Reliability: A Framework for Evaluation-Driven Prompt Design

[nitishagar]

LLM agents break deterministic tests. Evaluation-Driven Design helps teams reduce hallucinations.

On: Rethinking scale: How small AI models could redefine impac

[nitishagar]

The AI revolution just flipped: small AI models could redefine impact while using 70x LESS energy and costing 1,000x LESS to deploy.

In my new article I explore why compact AI might be the future.

On: The Microservices Pattern for AI

[nitishagar]

"Orchestration Outperforms Monolithic Agents"

I try to dive into how Salesforce BOLAA system can help you build efficient and reliable systems cheaper.

On: The New 10x Engineer: A Practical Guide to AI-Assisted Coding

[nitishagar]

The myth of the 10x engineer is becoming a reality, but the engineer isn’t human. It’s an AI agent, and your job is to become its conductor.

On: MCP Servers vs. AI Agents: Are We Overthinking Our AI Infrastructure?

[nitishagar]

Building in AI? Decide if you're shipping the "picks & shovels" (MCP server platform) or the "gold" (AI Agent) – your strategy depends on it! #AI #ProductStrategy #MCP #AIAgents #TechInnovation

On: Accessibility Ally: How Agentic AI can Proactively Enable Digital Inclusion

[nitishagar]

Discover how Agentic AI is shifting digital accessibility from reactive fixes to proactive, built-in inclusion for everyone.