Nadia Eldeib

This looks great! Sharing with the Harvard in Tech London community.

P.S. Feedback on our new site welcome. I'm still iterating!

As a product-focused founder formerly limited to product management and never being able to effectively help developers create production-quality code, being able to pair with Claude is transformative.

Pairing with Claude Code to Rebuild My Startup’s Website Adventures using AI agents, especially Claude Code, and MCP Servers

Full post 👇
blog.nseldeib.com/p/pairing-wi...

"APPROVED - Ship It!" 🚀

Set myself a challenge: rebuild the @codeyam.bsky.social
website from Figma designs using AI coding agents.

Claude Code CLI acted as:
→ Programming pair
→ PR reviewer
→ Pseudo-CTO

From Prompts to (Almost) Production: Choosing the Right AI Tools for a Startup Website Refresh Testing editors, CLIs, and MCP servers to see how far AI workflows can go in real-world development to rebuild our startup’s website

From Prompts to (Almost) Production: Choosing the Right AI Tools for a Startup Website Refresh: blog.nseldeib.com/p/from-promp...

AI workflows aren’t just for prototypes.

I rebuilt parts of the @codeyam.bsky.social website using an agentic coding workflow...and it is almost production-ready.

Curious: would you trust AI-generated code in your own projects if humans reviewed it first?

Full thoughts below👇

Immediately called out the cheek cuteness when my partner started using your app. The details are (pun intended) delightfully cheeky 🍑

Creating Software Without Writing Code: Testing AI “Vibe Coding” Tools Can you build a real, functional web app with nothing but natural language prompts?

We ran an experiment: can AI tools build real, functional software from a natural language prompt?

The result: a deep dive across 7 “vibe coding” tools, from v0 to Lovable to Figma Make.

All built something, but not always what we expected.

👉 Full write-up here → blog.codeyam.com/p/creating-s...

On Learning How to Build Software in the AI Era, With and Without Coding Despite working at software companies for over a decade, I held roles where I often looked at code but rarely touched it.

Been diving into how AI is reshaping software development.
Not just faster code, but better feedback loops, more intuitive tooling, and sometimes strange bugs.

Wrote a piece on what I’ve been learning through CS50, vibe coding tools, and building in the in-between. open.substack.com/pub/nseldeib...

Tony Stark isn’t the same Iron Man without JARVIS!

What channels have worked best for your user research? Always looking to improve our approach.

#UserResearch #StartupLife #ProductDevelopment

This is the exact process we're using as we refine how we describe our software simulation tools at @codeyam.bsky.social . Hope it saves you some headaches!

I've shared our complete playbook including:

- How to define who you actually need to talk to
- Where to find these people without expensive tools
- Our actual screening survey and email templates
- Tips for catching people who try to game your screening (it happens more than you'd think!)

Just published a practical guide to recruiting quality user research participants when you're bootstrapping the process 🔍

At CodeYam, we've learned that talking to the wrong people = useless data, no matter how good your questions are.

Read on: nseldeib.substack.com/p/finding-re...

If you're a founder friend, you know that for years I've been obsessed with leveraging qualitative user research to create faster feedback loops to improve learning velocity and iteration, especially in the earliest stages.

👇 Introducing a new series on this:
nseldeib.substack.com/p/build-fast...

Listening to Tubes: A Journey to the Center of the Internet by Andrew Blum and am struck by how much of the internet's history (and present!) is in suburban Virginia, where I grew up.

As a kid, I had no idea. Is this taught now? I would've loved to learn about the internet's creation and evolution.

Paid usability interviews with professional software developers and engineering managers, founders, and technical leaders on April 23rd & 25th, and beyond We are scheduling 60-minute 1:1 usability interviews to be conducted virtually/remotely over Zoom on April 23rd and 25th and potentially at a later date. This study is an opportunity to provide feed...

Hey #startup folks — I’m Nadia, CEO & co-founder of CodeYam. We’re building something new for developers and running 1:1 usability interviews on April 23 & 25 (and beyond).

Sign up: forms.gle/rjUe3YzKxjkf...

Update: this meetup was a blast!

Pictured: @nathenharvey.bsky.social facilitating an epic live coffee discussion on AI, DORA for the cloud, velocity vs quality, measurability of AI’s impact on software development and more!

Will folks be at the @dora.dev meetup at Google Cloud Next today? Hoping to join and meet some familiar-from-Meets faces!

As a founder wrestling with the speed v. quality tradeoff, I'm fascinated by AI tools promising both. Our product designer tested four AI-native tools to redesign our @codeyam.bsky.social site.

The result: impressive speed, but real limitations.

Read her findings: blog.codeyam.com/p/testing-th...

This is why we're building CodeYam - to deconstruct software projects into individual functions, demonstrate their behavior through simulations, and make it easier to validate, discuss, and modify complex code with AI assistance.

This is why tooling is crucial. The right tools dramatically simplify collaboration by letting you isolate specific components of complex systems for focused discussion.

There are two primary approaches to this challenge: iteration and tools.

Iteration provides tremendous value by breaking tasks into smaller components and validating results at each stage.
But this approach comes at a cost - you must invest time validating AI's output, which undermines efficiency.

When you describe a task to AI, it makes assumptions based on its training data. Ask it to write JS tests? It defaults to Jest, even when explicitly told not to.

This pattern repeats across all communication. It's impossible to provide sufficiently detailed specifications for complex ideas.

No matter how good AI becomes, one fundamental challenge persists: communication.

Despite significant AI progress, effectively communicating with LLMs remains a significant and under-appreciated problem that will hold back AI's value.

blog.codeyam.com/p/ai-cant-re...

This is crazy, egregious, beyond the pale. Musk has legitimate influence and power and is pushing to jail a political opponent. A prominent senator. This is as anti-democratic as it gets.

AI-first Software Development and the Evolution of Developer Experience and Enterprise Software Lessons from Boldstart Founder Summit 2025

Wrote up some thoughts from 2025 Founder Summit: nseldeib.substack.com/p/ai-first-s...

Spent two days with the Boldstart community in Miami talking AI-native software development.

We're not just changing what we build, but HOW we build. Everyone's using AI tools, DX is evolving rapidly, and we're seeing early signs of a B2A (business-to-agent) future emerging.

Founder FAQs: How did I decide to become a founder? Goal: greater transparency in hopes that sharing my experience supports other founders, aspiring founders, and the founder-curious.

Did I always know I wanted to become a founder?

I get asked this question all the time.

Today, I shared the journey that led me from to the @southparkcommons.bsky.social Founder Fellowship and creating CodeYam with my co-founder Jared.

Read it here: nseldeib.substack.com/p/founder-fa...