all_things_agentic

About

sumit@allthingsagentic.org (sumit) — Sun, 10 May 2026 00:00:00 +0000

Hello, my name is Sumit Gaur.

I am a senior backend developer. I have worked on applications that ranged from small services to petabyte-scale systems, mostly building and maintaining low-latency Java microservices. Along the way I have led small and medium-sized teams across geographies.

For the last two years, I’ve moved most of my attention to LLMs, exploring agentic development, RAG, and AIOps. This is where I keep notes on what I run into.

Why Your Agent Goes In Circles?

sumit@allthingsagentic.org (sumit) — Sun, 10 May 2026 00:00:00 +0000

The first time I shipped an agent into something that resembled production, it called the same tool 17 times. Same name, slightly different arguments each call. The token meter was a slot machine. The Teams channel filled up with retries before anyone noticed. The final answer, when it eventually arrived, was the same answer the second tool call had already produced.

A week earlier I had watched the opposite failure with the opposite agent: one tool call, then a confident final answer, even though the task obviously needed three more. Same missing thing, both times. Neither agent had a working loop.

Memory: Why Your Agent Forgets You?

sumit@allthingsagentic.org (sumit) — Sat, 02 May 2026 00:00:00 +0000

A model I was pairing with last week told me, in turn 5, that my project was a Hugo site and the file I was looking at was a content post. By turn 50 it cheerfully suggested I check the package.json for the build script. There is no package.json. There never was. Hugo is Go. I had told it twice already. The conversation had just gotten long enough that those turns fell off the front of the context window, and from the model’s perspective they had never happened.

Tools: How Agents Perform Actions?

sumit@allthingsagentic.org (sumit) — Wed, 08 Apr 2026 00:00:00 +0000

A model recently told me, with full confidence, that the failing test in the PR I’d pasted “looks like a flaky CI issue, probably retry.” I asked how it could tell. It admitted that it had not actually read the test. It had read the file path, recognised the word flaky in the surrounding chat, and made a guess.

It knew the next move was to read the test. It just didn’t have a way to.

How agents actually reason?

sumit@allthingsagentic.org (sumit) — Mon, 30 Mar 2026 00:00:00 +0000

I once asked a model “is 1219 prime?” and got a confident, wrong “yes.” I asked the same model the same question with one extra line in the system prompt, think step by step before you answer, and watched it walk through trial division up to $\sqrt{1219}$ and arrive at the right answer. Same weights, same question, different output, because the second prompt made room for the model to do the work in tokens before committing to an answer.

What even is an AI agent?

sumit@allthingsagentic.org (sumit) — Thu, 12 Mar 2026 00:00:00 +0000

I asked a chatbot how much I’d spent on coffee this month. It said it didn’t have access to my bank statements, but offered to walk me through how to estimate it.

Then I gave the same question to a small script that could read my email, find Starbucks receipts, sum them up, check whether $137 was high or low compared to the last six months, and reply with a number. Both used the same underlying model. One felt like a tool. The other felt like an employee.