ahmadawais.com
⌘ CEO & Founder CHAI.new with Langbase.com // @Google Devs Advisory Board // Award-winning @GitHub Star // Ex VP DX Rapid / Quoted by @SatyaNadella "awesome example for devs" // Creator of BaseAI.dev
140 posts
3,292 followers
72 following
Regular Contributor
Active Commenter
comment in response to
post
Sign up here
lu.ma/h46wrf19
comment in response to
post
Woot woot. How’s your experience been with Chai.new — we are shipping public agents and shareable forkable community agents.
comment in response to
post
This is what I have been advising a lot of new builders building AI agents with Chai.new by Langbase.
If you want to build a great AI agent, take it step by step instead of trying to one shot a huge system in one go.
comment in response to
post
Big congrats to @langbase.com on launching chai.new — go from concept to custom agent in seconds not days. I’ve been beta testing and am convinced it’ll change how we build AI-backed apps.
comment in response to
post
Also btw have you tried chai.new yet?
comment in response to
post
And I’m here for it.
comment in response to
post
With the launch of Chai, we have seen tens of thousands of new AI agents being vibe-coded both by builders and expert developers.
Everyone is seeing a huge productivity gain here. From builders to developers to product managers everyone is building agents like never before.
comment in response to
post
There’s a huge amount of grey area between what’s vibe-coded and what’s AI-assisted coding. Do both.
Both btw are much better than the drag-and-drop BS no code and low code alternatives.
comment in response to
post
It’s like when Tailwind first came out, as someone who always wrote CSS from scratch it took me a while to see how Tailwind was not a framework but like an API for CSS.
I think we are in that phase of vibe coding where a lot of people judge it by the cover.
comment in response to
post
From today, anyone on your team can vibe code an AI agent with Chai. And every agent comes with a UI.
Personal apps 🤝 personal agents at scale!!
Start today at
↳ chai.new
comment in response to
post
We've seen how products like GitHub, Vercel and Supabase have changed how we build apps.
Now, we're doing the same for AI.
Making it accessible to every builder, every developer, not just ML experts.
comment in response to
post
3. Why now?
The foundation models are ready.
The tools are maturing.
But the glue that connects everything is still missing.
LLMs are evolving fast—like, literally every week. New standards pop up (looking at you, MCP), and APIs change faster than you can keep track.
comment in response to
post
The result?
Most AI agent projects never make it to production.
Those that do require constant maintenance and lack the reliability users expect. (new LLMs every week)
AI agents should be composable, reliable, and production-ready from day one. (minute one?)
comment in response to
post
2. What problem are we solving?
Every company is trying to build AI agents, but the infrastructure is missing. Takes too long. It's too expensive. Hire MLEs?
Teams are reinventing the wheel, building brittle systems that break in production + can't scale with their needs.
comment in response to
post
Chai removes all the complexity of:
• LLM orchestration (unified API)
• Tool integration (deployment and scale)
• Memory (long term memory Auto RAG)
• Deploy agents, and scale to millions
• Langbase processes 100M+/mo agent runs
comment in response to
post
With Chai, what used to take days/weeks — now only takes minutes.
From idea → agent → deployed!!
We wanted to make it super easy for everyone to building their AI agents.
People spend weeks wiring together LLMs, tools, and memory systems just to get something basic working.
comment in response to
post
1. Why are we doing this?
Everyone is building an AI agent today, but it's hard.
Cursor, perplexity, v0, chai, lovable, bolt — what do they all have in common?
They weren’t built on AI frameworks—they're built using primitives optimized for speed, scale, and flexibility.
comment in response to
post
Chai is built on AI primitives by Langbase:
• Agents - for reasoning and planning
• Tools - for taking actions in the world
• Memory - for human-like context & learning
• Workflows - for orchestrating complex tasks
All with type safety and production reliability.
comment in response to
post
Chai vibe coded a mini Perplexity for me 🤯
Unbelievably good. Can't wait to see what y'all will build. Our beta testers had multiple 🤯🤯🤯 moments.
Let's go! 👊
comment in response to
post
Vibe coded a Receipt OCR Agent
Give this agent a receipt image and it can analyze whatever you want in it.
Woohoo! 🥳🥳🥳
comment in response to
post
Watch me vibe code several AI agents in this video
- An AI agent to chat with pdf
- Agent that finds a lunch spot near me
- Bed time story maker agent by DT
- AI email agent that can summarize, analyze, and generate a response
Chai is beta right now, oh it's super powerful.
comment in response to
post
Shades of Purple. Let’s go!!!!
comment in response to
post
P.S. We just published the eight most common AI Agent Architectures that can help you build the most simple and complicated AI agents, WITHOUT using any bogus frameworks. AI primitives for building full-stack AI agents.
Check 'em out here
↳ langbase.com/agents
comment in response to
post
Building a memory agent will be the most impactful thing you'll do this week, give it a try, don't sleep on this — happy to answer any questions y'all have.
👇 Dive deeper into Langbase Memory Agents
langbase.com/docs/memory
comment in response to
post
How to create a Memory Agent?
Reference memory agent architecture
↳ langbase.com/docs/exampl...
Quickstart with API or AI Studio
↳ langbase.com/docs/memory...
(7/7)
comment in response to
post
Memory agents are the best way to reduce LLM hallucinations to almost zero. Our frontier research in making RAG easy to build, deploy, and scale has helped both startups and enterprises build phenomenal agents.
(6/7)
comment in response to
post
I'm a hundred percent sure — you'll love using Memory Agents by @LangbaseInc, especially how simple it is to use them with our API or AI Studio.
↳ langbase.com/docs/memory
(5/7)
comment in response to
post
How do Memory Agents work?
1. Upload your data
2. Ask questions
3. Get relevant chunks
4. Use any LLM with Memory agents
We do it all. We got a vector DB in it 30-50x cheaper than the competition. Managed RAG has never been this easy.
(4/7)
comment in response to
post
Memory Agents = LLMs augmented with memory (long-term)
(3/7)
comment in response to
post
Memory is the universal constraint of every LLM.
LLMs don't know much about your business or are stuck in the past.
(2/7)
comment in response to
post
www.youtube.com/live/ZAiPNS...
comment in response to
post
Let’s go!!! 🤜🤛
comment in response to
post
Thank you bro!!
comment in response to
post
What should we ship in 2025 to help you build and scale AI agents?
comment in response to
post
We'd love to have you build your next AI agent and its neural architecture with Langbase memory and pipe agents.
Start with our docs: langbase.com/docs
comment in response to
post
Langbase is leading the AI agents market landscape.
x.com/LangbaseInc...
comment in response to
post
Shipped a whole lot every week!!
x.com/MrAhmadAwai...