Vivek Nair
@virtuallyvivek
Followers
633
Following
8K
Media
72
Statuses
1K
Co-founder, CTO @GentraceAI
Brooklyn, NYC
Joined January 2012
We spent the first year at @GentraceAI helping customers run traditional LLM evaluations. But we realized late last year that agents changed everything. Agents don't just generate text - they take actions, make decisions, and interact across multiple steps. Traditional
Agents are significantly more powerful than standalone LLM calls. But, debugging them is a nightmare. You can trace their reasoning and tool use, but traces get huge and are impossible to parse. To solve this, we spent the lasts several months building Gentrace for Agents,
1
3
11
Just released a 20 minute beginner tutorial making a flight tracker app with @alexcodes_ai Check it out if you're just getting started!
23
20
200
This team's progress blows me away every time I see an update.
π Introducing Alex 3.0 Hey everyone! We're so excited to release Alex 3.0. Here's what's new: - Automatically compile & fix errors π - Auto-apply code β‘ - Agentically π¦ Add SPM packages, π Search the web, run terminal commands, and review your code. - Local LLM support +
0
0
2
Repo here for instructions to install. No dependencies. No TS transpilation. Pure JS. https://t.co/seKM59Ucci
github.com
Chrome extension that adds a button to GitHub PR pages to copy the diff as Markdown - viveknair/diff-copier
0
0
0
Press β + C twice to copy to clipboard. This mimics Superhuman's behavior with copying an email thread. If you're selecting text elsewhere on the page, the extension does not activate.
1
0
0
I made a simple Chrome Extension to copy a Github PR diff into your clipboard. This makes it dead simple to understand what's changed.
1
0
1
https://t.co/FCpnoftliG works incredibly well but desperately needs a "Copy files to Markdown" button. cc @rauchg
1
0
2
Bringing it all together. You get a simplified CLI-centric workflow for context management.
0
0
0
token + ttok to get the token count of the file content in your clipboard @simonw released a project called ttok that computes the token count of output. Use the below fish function to use it to get the token count from your clipboard. https://t.co/zAKhxuURIQ
1
0
0
ripgrep (Rust-based file search) and the following fish function that formats the matched files for use with llmcat https://t.co/6LLwRDNObp
1
0
0
Three CLI modifications + tools I combine to optimize context management and stay in flow π
1
0
0
Does anybody know dev tool companies/OSS products that have started to include "get started quickly" prompts in their docs that users can copy and paste into Cursor to help with onboarding?
1
0
1
The best AI-native apps don't just integrate LLMs. They reshape the clipboard. We're entering a phase where exporting app data in LLM-readable markdown becomes table stakes. Tools like @linear get this: structured, semantic exports that unify with other unstructured data. Copy
0
0
2
Itβs wild how some of the most beautiful and expressive Unicode characters like the em dash (β) have become tells for AI-generated content. LLMs overuse them. So now if you use them, it looks artificial. A sad erosion of my personal voice.
2
1
6
Accidentally hexdumped the wrong file (a binary one) in Ghostty and the result looked... well, like art. This would have blown up my machine in Iterm. Thanks @mitchellh π and team.
1
0
4
What a night! Packed house and some of the sharpest minds in AI from Webflow, Asana, and 11x sharing how theyβre building with agents today. Big thanks to Ampersand for co-hosting and our speakers our speakers @bryantchou @rodrigodavies @prabhavjain @ezelby @patrickt010 for
2
1
7
Last week, we hosted some incredible AI builders from companies like Asana, Cribl, Block, Vanta, and Pinterest to share their stories on shipping AI apps to production. What we learned is that the road from POC to production isn't a straight path: 1. Turns out the biggest
1
1
5