Ventura (@getventura) deploys AI employees inside the ERPs that distributors and manufacturers already run on, starting with quoting and order processing.
Congrats on the launch, @swekol & @jackmpcollins!
https://t.co/KTnqlkaEPd
On Sunday I traveled to the middle of the desert to capture this: The ISS against our sun. What I didn't expect: the sun producing a magnificent flare at the same time
A once-in-a-lifetime shot I'm thrilled to share with you. See the uncropped shot or get the print in the reply
Spot me representing https://t.co/sX6Ai9mEHj , the only healthcare startup on the list. There should be more! Thank you @henrythe9ths and @FAL for hosting
$1M ARR per employee. $400M+ ARR combined. Almost all <5 years old, <50 employees and Profitable.
This wasn’t a YC dinner. This was the first Lean AI Leaderboard dinner 🔥
Massive thanks to @FAL ($50M+ ARR with just 22 people!) for hosting a 7-course sushi + wagyu feast at Ozumu SF — bringing together the founders behind the most efficient and fastest-growing AI startups today.
Almost everyone in this room is doing >$1M revenue per employee.
Most are profitable.
All were founded in the last 5 years.
And they’re just getting started.
@FAL@aragon_ai@higgsfield_ai@pika_labs@openart_ai@tavus@AkoolInc@hedra_labs@conversionai DevelopHealth
This is what the future of company building looks like:
AI-Native, Lean, Fast Growing and Profitable.
Next up: I’m co-hosting a Lean AI Happy Hour in SF at the end of the month with @hanstung@chelcietay Camila Katz from @notablecap
If you’re building a Lean AI Native company, drop a comment and I’ll get you an invite 👇
🤔 Where are the moats for "GPT wrappers"? After building multiple LLM-based apps used by thousands of users, here's what I've learned about creating defensible Vertical AI solutions... 🧵👇
🔬 Spent an hour diving deep into https://t.co/G9GhX9sGy2 , an LLM framework from @jackmpcollins.
And I found a similar challenge as I get with a lot of these frameworks... debugging <> abstracted control flow.
📝 Core lesson for frameworks: Take extreme care when your 'abstraction' abstracts _control flow_. When debugging AI, you need to trace everything - from prompt construction to response parsing; and many LLM frameworks don't consider this deeply enough.
🛠️ I built a calculator to test some function calling workflows. I played a lot with the various decorators and finding where and how to break the framework. Missing a return type? opaque Pydantic error. Unused prompt template parameter? No worries, it'll run. Any function can be a tool.
💭 Overall: Framework shows promise but I think there are some changes I would want to see before recommending use.
✅ What worked well:
- Clean function calling implementation
- No specialized tool decorators (just Python functions!)
- Solid type system with Pydantic
- Built-in image support that's actually usable
❌ Pain points:
- Too many overlapping concepts (prompt/chatprompt/prompt_chain)
- No validation between templates and parameters
- Observability locked to logfire; no clear way to "bring my own logging"
- Missing escape hatches for new features
💡 Recommendations:
- Simplify API - merge overlapping concepts; the conceptual weight is high given the functionality
- Add prompt template <> parameter validation to prevent incongruence
- Make observability pluggable (repeat after me: LLM observability is just observability)
- Focus on composable primitives over abstractions
After over a decade of building ML systems: frameworks should give developers control flow visibility. You'll need it at 3am debugging hallucinations in prod.
@OfficialLoganK https://t.co/aWo7MOnTKq for Python
- everything streamed for minimum latency e.g. parallel function calls get executed as they are received
- native support for @pydantic logfire / opentelemetry
- the neatest syntax, so quick to write and easy to read
Just released magentic v0.34.0 with `StreamedResponse` type which enables combination str and tool call responses. Use it for chain-of-thought reasoning or to allow the model talk and tool call simultaneously.
docs: https://t.co/N77xcjBHmA
release: https://t.co/FY1o6zN5LC
Instrumented magentic using @pydantic logfire today 🪵🔥 and it is excellent. Excited to try this out on some more complex flows
new docs page linked below