Mahmoud El Magdoub

AI is eating the world and I'm quite hungry.

[Aly Moursy @alymoursy]

Seeing @openai emails signing up for your product is one of those moments that gives you a little extra motivation as a founder.

Even if it means absolutely nothing.

[Mahmoud El Magdoub @Magdoub]

Yasser is setting the bar high 🔥

[Yasser @yasser_elsaid_]

We just crossed $10M in ARR at @Chatbase! 🎉 🎉

And today, we're launching Chatbase as the full harness for customer-facing AI agents.

Similar to how Claude code is a harness for coding agents, Chatbase is the harness for customer experience agents.

That means we give the model the context, tools, workflows, guardrails, and human-in-the-loop systems to be the best ambassador for your brand.

It's going beyond just solving issues and is giving your customers the best experiences across every channel.

This is a milestone I have been thinking about and obsessed with since day 1, and I am super excited to bring my vision for customer facing agents to life with Chatbase.

Thank you to every one of our customers and to the amazing Chatbase team for getting us here!

Next stop: $100M ARR

[Mahmoud El Magdoub @Magdoub]

@getsleekio @uAghazadae That's super smart. I love the experience

[Mahmoud El Magdoub @Magdoub]

Great move from Notion. All software companies should do the same

[Notion Developers @NotionDevs]

Introducing: the Notion Developer Platform

New building blocks that help you (and your coding agents) sync any data source, build any tool, and orchestrate any agent.

Follow along 👇 https://t.co/wxZDYxBrqK

[Mahmoud El Magdoub @Magdoub]

@meag_han_c this clawd intro vid is 🔥
The public demands more

[Mahmoud El Magdoub @Magdoub]

@skeptrune Loved your session! thanks Nick

[Mahmoud El Magdoub @Magdoub]

@trq212 dropping gems at Code with Claude 💎

[Mahmoud El Magdoub @Magdoub]

@AnthropicAI prepping for the first developer event for Claude Code.

[Mahmoud El Magdoub @Magdoub]

If you're attending the Code with Claude. Here's the Agenda in one image

@ClaudeDevs

[Mahmoud El Magdoub @Magdoub]

@yasser_elsaid_ ContrarianMaxxing 👏

[Mahmoud El Magdoub @Magdoub]

https://t.co/tUckD4VflI

[Ali Abouelatta @abouelatta_ali]

I hated how bad agents are at design

I hated how Codex can't access Mobbin

So I created Lazyweb

- 257k+ screens (apps/web)
- 6 opinionated design research skills
- 1 MCP (Claude/Codex)

100% Free...AI native...no rate limits...no subscriptions..

Enjoy (and tell a friend) 🫡

[Mahmoud El Magdoub @Magdoub]

@abouelatta_ali Wow!

[Mahmoud El Magdoub @Magdoub]

@AbdoMobayad The best

[Mahmoud El Magdoub @Magdoub]

@trq212 Thanks Thariq! The doc don't work well if I open the assistant, the nav breaks.

[Mahmoud El Magdoub @Magdoub]

Writing = Thinking

[DAN KOE @thedankoe]

You need to write more.

Without AI. Without templates. Without knowing what you're writing about. Just you, an idea, and enough time to do the difficult cognitive work necessary to reach true understanding. If you don't, your ability to think will drastically decline.

[Mahmoud El Magdoub @Magdoub]

I’ve been trying this setup, it’s extremely helpful. Specially when you are joining a new project/company

With time the agent becomes much smarter than you because it knows all the context

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[Mahmoud El Magdoub @Magdoub]

That’s a great trend

[Tony Fadell @tfadell]

Most tech companies break out product management and product marketing into two separate roles: Product management defines the product and gets it built. Product marketing wires the messaging- the facts you want to communicate to customers- and gets the product sold. But from my experience that's a grievous mistake. Those are, and should aways be, one job.

There should be no separation between what the product will be and how it will be explained- the story has to be utterly cohesive from the beginning. Your messaging is your product. The story you're telling shapes the thing you're making.

I learned story telling from Steve Jobs. I learned product management from Greg Joswiak. Joz, a fellow Wolverine, Michigander, and overall great person, has been at Apple since he left Ann Arbor in 1986 and has run product marketing for decades. And his superpower- the superpower of every truly great product manager- is empathy. He doesn't just understand the customer. He becomes the customer.

So when Joz stepped into the world with his next-gen iPod to test it out, he fiddled with it like a beginner. He set aside all the tech specs- except one: battery life.

The numbers were empty without customers, the facts meaningless without context.

And, that's why product management has to own the messaging. The spec shows the features, the details of how a product will work, but the messaging predicts people's concerns and finds way to mitigate them.

- #BUILD Chapter 5.5 The Point of PMs

[Mahmoud El Magdoub @Magdoub]

@ahmdelemam هى نقاشة من زمان 😁

[Mahmoud El Magdoub @Magdoub]

I was very big on plan mode in claudecode. Tried living without it today and it has been a much better experience!

Sometimes we are trapped in our own thinking

[Peter Steinberger 🦞 @steipete]

I never use plan mode.

The main reason this was added to codex is for claude-pilled people who struggle with changing their habits.

just talk with your agent.