---
title: "Tirth Gajjar (@tirthgajjar) | Hashnode"
description: "Founder of BigCircle (https://bigcircle.ai). We build production AI systems with governance built in. Read the latest articles by Tirth Gajjar on Hashnode."
url: "https://hashnode.com/@tirthgajjar"
---

@tirthgajjar

# Tirth Gajjar

@tirthgajjar · Gandhinagar, India · Joined October 2026

Founder of BigCircle (https://bigcircle.ai). We build production AI systems with governance built in.

[Website](https://bigcircle.ai/)

### [How MCP authorization works and what it leaves to you](https://bigcircle.hashnode.dev/mcp-authorization?utm_source=hashnode&utm_medium=feed)

How MCP authorization works under OAuth 2.1, why the agent should never hold the key, and where to check, mint and audit each tool call.

27 min read · [bigcircle.hashnode.dev](https://bigcircle.hashnode.dev/mcp-authorization?utm_source=hashnode&utm_medium=feed)

[6h ago](https://hashnode.com/posts/mcp-authorization/6afb4fcc72cd4471be30c944)

### [Human in the loop AI agents and when a person must approve](https://bigcircle.hashnode.dev/human-in-the-loop-ai-agents?utm_source=hashnode&utm_medium=feed)

Which AI agent writes need a person to approve them, what the approver should see, where to enforce it, and how to retire approval one action at a time.

17 min read · [bigcircle.hashnode.dev](https://bigcircle.hashnode.dev/human-in-the-loop-ai-agents?utm_source=hashnode&utm_medium=feed)

[2d ago](https://hashnode.com/posts/human-in-the-loop-ai-agents/6af8ad9f705ef84fe121d7d0)

### [How LLM inference works and how to optimize it](https://bigcircle.hashnode.dev/how-llm-inference-works-and-how-to-optimize-it?utm_source=hashnode&utm_medium=feed)

LLM inference runs in two phases: prefill reads the prompt, decode writes the answer. What to measure, cache and change for faster, cheaper inference.

13 min read · [bigcircle.hashnode.dev](https://bigcircle.hashnode.dev/how-llm-inference-works-and-how-to-optimize-it?utm_source=hashnode&utm_medium=feed)

[4d ago](https://hashnode.com/posts/how-llm-inference-works-and-how-to-optimize-it/6af6094e3fffe9b4b1f19140)

### [How to set AI agent permissions and access control](https://bigcircle.hashnode.dev/ai-agent-permissions?utm_source=hashnode&utm_medium=feed)

Set AI agent permissions one action at a time: give each change its own tool, check authorization in code, and keep credentials away from the model.

16 min read · [bigcircle.hashnode.dev](https://bigcircle.hashnode.dev/ai-agent-permissions?utm_source=hashnode&utm_medium=feed)

[6d ago](https://hashnode.com/posts/ai-agent-permissions/6af36646ac8a74b48d923677)

### [Why RAG systems fail in production](https://bigcircle.hashnode.dev/why-rag-systems-fail-in-production?utm_source=hashnode&utm_medium=feed)

RAG in production usually fails quietly: the answer sounds right, cites a nearby passage, and misses the fact the user needed.

33 min read · [bigcircle.hashnode.dev](https://bigcircle.hashnode.dev/why-rag-systems-fail-in-production?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/why-rag-systems-fail-in-production/6af0c3a11184f6164c2fd94d) [Nov 8](https://hashnode.com/posts/why-rag-systems-fail-in-production/6af0c3a11184f6164c2fd94d)
