# Nimesh Manmohanlal

> Engineering leader and software developer sharing insights on AI, architecture, and team structure.

## Navigation
- [Blog](https://nimeshjm.com/blog)
- [About](https://nimeshjm.com/about)

## Social Links
- [GitHub](https://github.com/nimeshjm)
- [LinkedIn](https://www.linkedin.com/in/nimeshmanmohanlal/)

## Key content for all ai blogs with key summary

- [Building AI into your SaaS product](https://nimeshjm.com/blog/ai-saas-product-strategy): Using AI internally is an operational call. Embedding AI in your product is commercial, legal and architectural. What that changes for what you build, what you sell, and how the business runs.
- [Agentic Context Engineering: Moving Beyond Index Bloat](https://nimeshjm.com/blog/ai-agent-skills): The industry is shifting from indexing everything to agentic context engineering with Progressive Context Disclosure and modular Agent Skills. How to build 'just-in-time' context for AI coding agents.
- [Most companies are getting no value from AI](https://nimeshjm.com/blog/ai-adoption-value-gap): AI adoption is near-universal but value creation is concentrated in a small minority. The gap between pilots and production, the risks nobody is preparing for, and what actually happens when AI-generated code hits your systems.
- [Infrastructure as Code 2.0: The Agentic Shift](https://nimeshjm.com/blog/ai-iac): Infrastructure as Code is moving to Agentic Provisioning. Why vector search fails for cloud infrastructure and how agents use graph reasoning to plan, verify, and execute cloud deployments.
- [Observability for agents: you can't debug what you can't see](https://nimeshjm.com/blog/ai-observability): AI agents are shipping code to your production systems faster than your observability can keep up. What actually breaks, what to instrument, and why logs alone won't save you.
- [Structuring engineering teams for AI first development](https://nimeshjm.com/blog/ai-engineering-team-structure): How to structure engineering teams when AI agents are part of the workforce.
- [deeveloping agents](https://nimeshjm.com/blog/ai-developing%20agents): AI agents running in production are non-deterministic by definition. Traditional APM wasn't built for this. What agentic telemetry actually looks like and how to wire it up with Honeycomb.
- [Hiring and mentoring engineers in an AI first world](https://nimeshjm.com/blog/ai-engineering-team-playbook): AI has changed what you should test in interviews, how you onboard juniors, and what mentoring actually looks like. The practical playbook for the people side of AI-first engineering.
- [AI won't fix your engineering team. It will amplify everything - good and bad.](https://nimeshjm.com/blog/ai-applied-to-software-engineering): AI productivity tools amplify what already exists in your engineering team - for better or worse. The diagnosis - what the data actually shows about AI, productivity, and the growing gap between seniors and juniors.
- [Agentic search vs vector search vs graph search: how to feed Claude the right context](https://nimeshjm.com/blog/ai-codebase-context-retrieval): Claude Code works great out of the box on greenfield projects. On brownfield codebases, the built-in search starts to hurt you. When to use native agentic search, when to add vector or graph search, and how to wire them up as MCP servers.
- [The new 3 amigos: from story kickoffs to agent orchestration](https://nimeshjm.com/blog/ai-new-3-amigos-agent-orchestration): The original 3 amigos brought product, developer and tester into the room before a story got built. AI first engineering has quietly reinstated the pattern twice over, once for humans, once for agents. Where the hard question sits is in the reviewer role.