Mohit Sharma

Professional over-thinker, Tweets filled with laughs, and a sprinkle of sarcasm.

[Mohit Sharma @MohitMits]

@i_mika_el 💯golden data sets and observability is the way to go

[Mohit Sharma @MohitMits]

At #AgentCon today.

Building AI agents is becoming easy.
Building reliable AI agents is becoming the challenge.

Skills, memory, evaluation, observability, and governance are quickly becoming essential parts of the stack.

[Mohit Sharma @MohitMits]

@rohit_jsfreaky Absolutely this is where the focus needs to be

[Mohit Sharma @MohitMits]

@GaganPratapMath Gadkri ji ko airf apna ghr bharna hai inko kisi ki chinta nahi hai

[Mohit Sharma @MohitMits]

USB-C standardized how devices connect.

MCP may do the same thing for AI agents.

The real shift isn’t the protocol.

It’s standardized AI-to-tool interaction.

https://t.co/hJXqyifC6B

[Mohit Sharma @MohitMits]

CI tells you that a test failed.

A Context Engine tells you why.

Repo with real Playwright failures + AI debugging 👇
https://t.co/t8zVmd2v4z

[Mohit Sharma @MohitMits]

@corbin_braun I heard duck suck go is beat if you want to live under the hood

[Mohit Sharma @MohitMits]

Your Playwright tests aren’t flaky.

They’re context-starved.

Debugging fails because we don’t reconstruct what actually happened.

I wrote about building a Context Engine that fixes this 👇
https://t.co/76XUZOFp3D

[Mohit Sharma @MohitMits]

@ordax @elonmusk @sundarpichai @sama 😂🤣

[Mohit Sharma @MohitMits]

🤣😂 credit to @ordax

[Mohit Sharma @MohitMits]

5
🔧 Repo:
https://t.co/wF446J8bQY
AI doesn’t fail loudly.
It fades quietly.
Observability is how you catch the truth before your users do. 👁️‍🗨️

[Mohit Sharma @MohitMits]

1/
Your LLM isn’t “random.”
It’s changing in ways your tests will never catch.
Hallucinations, drift, cost spikes, slowdowns —
all happen after deployment.
Most teams never see it coming.

[Mohit Sharma @MohitMits]

4/
So I built a small, open-source LLM Observability Starter Kit + wrote a clear, beginner-friendly breakdown of how to actually monitor AI behavior.
If you’re QA, SDET, or building with AI —
this is the missing layer.

🔍 Blog:
https://t.co/HbrodSCzsD

[Mohit Sharma @MohitMits]

@dev_maims Solutioning

[Mohit Sharma @MohitMits]

@GeekyVaishnavi No doubt about that

[Mohit Sharma @MohitMits]

@ai_for_success Actually both for different work 😝

[Mohit Sharma @MohitMits]

7/
If this thread helped you, repost + follow for more on:
• AI evaluation
• LLM agents
• AI automation
• QA + SDET → AI Quality Engineer path

[Mohit Sharma @MohitMits]

LLM Evaluation is Broken - Here’s How to Fix It

1/
Most teams testing LLMs are still doing:
❌ manual prompts
❌ random test cases
❌ “looks good to me”
LLMs don’t work like normal software.
They need new testing methods.

[Mohit Sharma @MohitMits]

6/
If you’re a QA engineer, SDET, or AI dev —
LLM evaluation is the most important skill of 2025.
I wrote a full deep-dive blog covering everything:
👉 https://t.co/v4U94LzKFS