alt Hacker NewsLaunch HN: Plexe (YC X25) – Build production-grade ML models from prompts
Hey HN! We're Vaibhav and Marcello, founders of Plexe (https://www.plexe.ai). We create production-ready ML models from natural language descriptions. Tell Plexe what ML problem you want to solve, point it at your data, and it handles the entire pipeline from feature engineering to deployment.
Here’s a walkthrough: https://www.youtube.com/watch?v=TbOfx6UPuX4.
ML teams waste too much time on generic heavy lifting. Every project follows the same pattern: 20% understanding objectives, 60% wrangling data and engineering features, 20% experimenting with models. Most of this is formulaic but burns months of engineering time. Throwing LLMs at it isn't the answer as that just trades engineering time for compute costs and worse accuracy. Plexe automates this repetitive 80%, so your team can work faster on what actually has value.
You describe your problem in plain English ("fraud detection model for transactions" or "product embedding model for search"), connect your data (Postgres, Snowflake, S3, direct upload, etc), and then Plexe: - Analyzes data and engineers features automatically - Runs experiments across multiple architectures (logistic regression to neural nets) - Generates comprehensive evaluation reports with error analysis, robustness testing, and prioritized recommendations to provide actionable guidance - Deploys the best model with monitoring and automatic retraining
We did a Show HN for our open-source library five months ago (https://news.ycombinator.com/item?id=43906346). Since then, we've launched our commercial platform with interactive refinement, production-grade model evaluations, retraining pipeline, data connectors, analytics dashboards, and deployment for online and batch inference.
We use a multi-agent architecture where specialized agents handle different pipeline stages. Each agent focuses on its domain: data analysis, feature engineering, model selection, deployment, and so on. The platform tracks all experiments and generates exportable Python code.
Our open-source core (https://github.com/plexe-ai/plexe, Apache 2.0) remains free for local development. For the paid product, our pricing is usage-based, with a minimum top up of $10. Enterprises can self-host the entire platform. You can sign up on https://console.plexe.ai. Use promo code `LAUNCHDAY20` to get $20 to try out the platform.
We’d love to hear your thoughts on the problem and feedback on the platform!
Comments
Amazing! Great work. Congratulations on launch.
Few questions: 1. Can it work with tabular data, images, text and audio? 2. Data preprocessing code is deployed with the model? 3. Have you tested use cases when ML model was not needed? For example, you can simply go with average. I'm curious if agent can propose not to use ML in such case. 4. Do you have agent for model interpretation? 5. Are you using generic LLM or have your own LLM tuned on ML tasks?
Product seems cool. But can you help me understand if what you are doing is different from the following: > you put a prompt > Plexe glorifies that prompt into a bigger prompt with more specific instructions (augmented by schema definitions, intent and whatnot) > plug it into the provided model/LLM > .predict() gives me the output (which was heavily guardrailed by the glorified prompt in the step 2)
> Each agent focuses on its domain: data analysis, feature engineering, model selection, deployment, and so on
Sounds very practical in real-world use cases. I trained a ML model couple months ago, I think it's a good case to test this product.
In the demo, you didn’t show the process of cleaning and labeling data, does your product do that somehow, or do you still expect the user to provide that after connecting the data source.
Great product and congratulations on the launch. Who is the target user vs customer? On the surface, and I may be wrong here, this feels like a LLM layered on top of a typical AutoML structure eg: TPOT, Caret. Is that the correct mental model for a tool like this? And if so, do you see a similar problem that these tools faced in broader adoption at companies?
Problem space is very interesting. Sounds like most of the work will be the data handling which is an evergreen problem
The tool gave me advice and code to do what I asked... but when I used the "export analysis" it did NOT include the code. It was simply an overview.
It would be more useful for the export to have an option (or by default) to include everything from the session.
Interesting. Are you guys only charging for the model building using tokens or overall usage (model building, inferences, etc)?
very cool – I like how opinionated the product approach is vs. a bunch of disconnected tools for specialists to use (which seems more common for this space).
Sounds interesting! I'm trying to train a model but it's still "processing" after a bit but fine-tuning takes a while I get it. I'm having trouble understanding how it's inferring schema. I used a sample dataset and yet the sample inference curl uses a blank json?
curl -X POST "XXX/infer" \ -H "Content-Type: application/json" \ -H "x-api-key: YOUR_API_KEY" \ -d '{}'
How do I know what the inputs/outputs are for one of my models? I see I could have set the response variable manually before training but I was hoping the auto-infer would work.
Separately it'd be ideal if when I ask for models that you seem to not be able to train (I asked for an embedding model as a test) the platform would tell me it couldn't do that instead of making me choose a dataset that isn't anything to do with what I asked for.
All in all, super cool space, I can't wait to see more!
I'm a former YC founder turned investor living in Dogpatch. I'd love to chat more if you're down!