— 001 / Introduction

Hi, I'm
Nadeen.

AI educator and builder. Founder of AI Build Club DC. I run workshops where people learn AI through play, curiosity, and hands-on building — and I build custom AI systems for individuals and teams ready to put it to work.

Join an event Build with me

"Great host! Knows her stuff and can lead a room of people through important discussions."

"Nadeen is awesome at building community around AI and bringing people together to learn from each other."

"Wonderfully facilitated event. I left excited, encouraged, and wanting to learn more!"

— 002 / Events

— 004 / Selected Work

Case Study

Built 4 AI agents for a two-person business. They run them without me.

RoleSolo consultant

TimelineJune 2026

StatusActive

StackClaude Code, Claude Cowork, Gmail MCP, Drive MCP, Calendar MCP

Context

Alexis and Desy run Onyx Truth, a content platform for Black professionals. Two founders, no admin team. They do everything themselves.

Goal

When Alexis reached out, she wasn't looking for anything complicated. She just wanted to stop spending her mornings on email triage, meeting follow-ups, and Mailchimp drafts. Work that needed to get done but didn't need her brain.

Approach

Before I built anything, I sat down with Alexis and mapped out what AI could handle for her business. Some tasks it could own completely. Some it could draft, with Alexis reviewing before anything went out. And a few things, like presentation design and custom graphics, just weren't AI tasks. I said that early so nobody expected something I couldn't deliver.

How it Works

We started with two agents. The daily briefing pulls Alexis's Google Drive meeting notes and calendar, puts together a structured to-do, and drops it in her inbox. The meeting follow-up agent takes a Zoom transcript and turns it into structured notes and a drafted follow-up email, with a distinction between internal co-founder calls and external meetings.

After the first two were working, we added two more. The Mailchimp agent drafts campaign copy. The scheduling agent handles calendar coordination. All four run through Claude Cowork. Alexis and Desy operate them. I built the agents, trained both of them to use them, and wrote up documentation. They can run this without me now.

Results

10hours saved / week

4agents in daily use

0dependency on me

Four agents running. A fifth scoped for when their YouTube channel launches. The work that used to eat Alexis's mornings doesn't anymore.

What I learned

Building the wrong thing confidently is worse than building nothing. Saying "this isn't an AI task" early saves everyone time. Capability transfer, not dependency, is a better consulting model.

Built a 6-agent system that runs my consulting, community, and job search in the background.

RoleSolo builder (for myself)

Timeline2025 — present

StatusActive, in daily use

StackClaude Code, Twilio, Otter.ai, MCP, Obsidian

Context

I didn't set out to build an agent system. I just kept running into the same problem: I was spending my best morning hours on logistics.

Goal

Running AI Build Club, managing consulting clients, job searching, writing, planning events. Every day started with a ritual of checking my calendar, reviewing what I owed people, and figuring out what to prioritize. By the time I had a picture of the day, half my energy was already spent.

Approach

So I started building. One agent at a time, over months. The calendar SMS briefing was first. Every morning, my phone gets a text with the day's meetings, context on who I'm talking to, and anything I should prep. Thirty seconds to read. It replaced about fifteen minutes of manually reviewing my calendar.

How it Works

The transcript pipeline came next. Raw file comes in, gets renamed by date and topic, converted to markdown, speakers labeled, summary generated, and indexed. The writing workflow reads my style guide before drafting anything. The handoff system writes a timestamped file at the end of every session so the next one picks up where I left off. Daily planning tools build and reprioritize my task list from whatever's active.

Results

15m → 30smorning calendar prep

0transcript backlog

50%faster first drafts

The agents handle the parts of my day I used to dread. What's left is the work I want to spend my time on. This is what I'd build for a team. I know because I built it for myself first.

What I learned

I built all of this for myself. But every time I walk someone through it, I watch the same thing happen. They stop thinking about what AI can't do and start thinking about what they'd want it to handle in their own day.

The bottleneck wasn't the technology. It was knowing my own workflows well enough to describe them. The agents I build for clients are better because I've been running my own for months.

Enriched 1,700 CRM contacts and built a relationship agent for meeting prep.

RoleSolo consultant

Timeline2026

StatusActive

StackClaude Code, CRM integration

Context

Kyle McAndrews runs KAM Advisory. He's spent years building relationships, and his CRM held 1,700 of them. The problem was the state of the data. Records were incomplete. Formatting was inconsistent. There was no way to ask "who do I know in fintech?" and get something useful back.

Goal

When Kyle came to me, what he wanted was basically: "Help me make this CRM useful." Before I built anything, I asked questions. What does "useful" mean for how Kyle works? How does he prep for meetings? What information does he need, and when?

Approach

The answers told me two things. First, Kyle wanted something closer to a thinking partner for relationship management. Second, that kind of intelligence layer would fall apart if the underlying data was still messy. We needed to clean the records before we could build anything smart on top of them.

How it Works

Phase 1 was enrichment. For each of the 1,700 contacts, the agent normalized formatting, filled in gaps where public data existed, and flagged records that were too incomplete to fix automatically. By the end, Kyle had a clear picture of what his CRM contained.

Phase 2 was the relationship agent. It finds warm intro paths, flags connections that have gone quiet, and helps Kyle prep for meetings with context he'd otherwise have to dig for. This only works because Phase 1 happened first. Building a relationship agent on top of messy data gives you answers you can't trust.

Results

1,700contacts enriched

70%auto-enriched

15m → 2mmeeting prep time

1,700 contacts enriched and normalized. A relationship agent in active use for meeting prep. Intro paths and dormant connections visible that weren't before.

Built a customer support AI that turns a six-hour inbox into a fifteen-minute review.

RoleSolo consultant

TimelineLate 2025

StatusCompleted

StackClaude API, n8n, RAG, vector database, Gmail

Context

Bounce Boom is a tennis coaching company running classes for around 1,000 students a week across multiple locations, with 15 coaches on staff. During peak season, customer support email was eating about six hours a week. A little over an hour every day, answering the same kinds of questions. Their inbox had no structure, so there was no easy way to see what people kept asking.

Goal

They wanted to stop losing an hour a day to email without losing the personal voice their customers expected. Two things had to happen. The inbox needed structure, and the replies needed to sound like the business owner actually wrote them.

Approach

I split the problem into two agents. A triage agent to sort and label every incoming email, and a response agent to draft the replies. The triage piece does more than tidy the inbox. By labeling each email by category, it turns the inbox into data, so the owners can see which questions come up most and rewrite their website FAQs to head them off before they ever become an email.

How it Works

The response agent is a RAG system. I built a vector database that ingests everything the agent needs to sound like Bounce Boom. Company and tennis school information, class schedules and locations, and common tennis questions like racket sizing and equipment. It also pulls from a library of sample responses for each category, so the agent answers the way the owner would.

Now they open the inbox and every email is already sorted into the right folder with a draft sitting ready to review, edit, and send. The whole workflow runs on n8n, from triage to drafted reply. The system also handles internal email from the 15 coaches. The triage agent routes those separately, and the response agent has context on the company's internal operations, so it answers staff questions as accurately as customer ones.

Results

1h → 15mdaily support email time

1,000students supported / week

2agents in daily use

Every customer email now arrives sorted and pre-drafted. The owners review and send instead of writing from scratch. And because triage labels the inbox by topic, they can finally see which questions to answer once on their website instead of a hundred times in their inbox.

What I learned

The triage agent was supposed to be the boring half of this project. It turned out to be the strategic one. Labeling every email by category gave the owners something they never had: real data on what their customers struggle with. Actually, the fastest support reply is the one you never have to write.

— 006 / Community

300+ AI Builders in DC

15 Five-Star Reviews

10 Sold Out Events

Two attendees in a candid moment at an AI Build Club event, February 2026

Wide room shot of speaker and engaged audience at an AI Build Club event, March 2026

Tight audience shot showing close engagement at an AI Build Club event, March 2026

Close-up view of attendees watching a presentation at a Product Leaders event, June 2026

Three attendees chatting in a small-group candid at an AI Build Club event, March 2026

Group of attendees seated in a lounge watching a screen at a Product Leaders event, June 2026

Three attendees at an AI Build Club event, March 2026

Wide room view of attendees at a Product Leaders event, June 2026

★★★★★

The event was highly educational as the speakers shared a wealth of knowledge for advanced AI usage.

Max Rakhimov March 2026

★★★★★

Really cool location, great people to connect with and learn from, interesting demos, good vibes & food.

Lauren Roche February 2026

★★★★★

Nadeen is truly driven by the mission to create a space for builders, thinkers, tinkerers, and visionaries to come together and engage in meaningful conversation and knowledge transfer in a way that benefits the broader community.

Aaron

★★★★★

Insightful, and engaging.

Christopher Woodyard March 2026

★★★★★

Nadeen ran a smooth, interactive, and engaging conversation at the AI Build Club DC event. She steered the conversation smoothly, kept everyone engaged and overall it was a great meetup.

Andrew

★★★★★

The event was well designed. The community was very curious and engaging.

Rudy Rocourt November 2025

★★★★★

Wonderfully facilitated event. I left excited, encouraged, and wanting to learn more!

Jaime

★★★★★

Awesome at building community around AI and bringing people together to learn from each other.

Seth

★★★★★

Great host! Knows her stuff and can lead a room of people through important discussions.

Brian

★★★★★

This was my third AI Build Club event and I look forward to attending more!

Daniel Rothman March 2026

— 007 / Work With Me

Let's Build Together.

Three ways to start.

01 Join a Workshop 02 Book a Call 03 Email Me

Hi, I'm
Nadeen.

Come build with us.

Things I've built.

Onyx Truth

My AI Operating System

KAM Advisory CRM

Bounce Boom

Let's Build Together.

Hi, I'm Nadeen.

Come build with us.

Things I've built.

Onyx Truth

My AI Operating System

KAM Advisory CRM

Bounce Boom

Let's Build Together.

Hi, I'm
Nadeen.