Vellum
Build AI agents using plain English to do your boring tasks
Start new thread
Garry Tan

Vellum - Build AI agents using plain English to do your boring tasks

by
Y Combinator
•
Build AI agents by describing your task in plain English. Vellum turns it into a working agent you can run on a schedule, trigger via API, or use through a UI. No code, no setup; just automation you understand and control.

Add a comment

Replies

Best
Rakesh Goyal

looks 🔥 congrats on the launch!

Anita Kirkovska
Maker

@rakeshgoyal thanks Rakesh!

Theo Goldberg

Congrats to the whole team 👏👏

Anita Kirkovska
Maker
@theo_goldberg1 thank you Theo!!
Daniel Marashlian

Congrats on the launch! Looking forward to implementing this technology at @Drata

Anita Kirkovska
Maker
@danielzev excited for that!
Anvisha Pai

I've tried a LOT of agent builders, and Vellum is the only one where I've been able to do things without getting frustrated/having to write code.

Anita Kirkovska
Maker
@anvisha_pai love to hear that Anvisha!
Devreet

This is such an important unlock. Agents have been incredibly powerful for engineers, but the rest of the org has been stuck duct-taping prompts together. Making agents usable for non-technical teams is where real adoption happens. Curious how Vellum handles edge cases and process changes over time without breaking everything?

Syed Mustassim

All the best with the launch, just signed up! I am curious about voice integrations, as I did not find any integrations for telephony based agents. Is voice in your roadmap or is the focus mostly on tasks, workflows and text automations for now?

Akash Sharma
Maker

@mustassim - users end up using text to speech and speech to text models before/after Vellum for voice use cases. Primary usage at the moment is text and automations though.

Julien Avezou

This is cool! I like the simplicity but power of it. And nice production for the video :)

Akash Sharma
Maker

Thanks @avz! Let me know if you end up giving the product a shot and what your thoughts are

Sam Chen
Congrats on the launch! The automation workflow looks promising! This allow us to do daily tasks, especially useful for marketing and other fields with daily repeated tasks
Anita Kirkovska
Maker

@sam_chen1 thank you! I'm building a few different agents for marketing - lmk if you need some inspiration!

Rex

What stood out to me about Vellum is how intentionally it frames complexity instead of trying to hide or over-simplify it.

In tools that deal with structured thinking or layered workflows, it’s common to either overwhelm users or abstract things too much. Vellum feels like it’s aiming for a middle ground — making the structure visible, but not intimidating. From a UX perspective, that balance usually comes from deeply understanding where users get confused versus where they actually want control.

As a first impression, the product feels considered and mature, prioritizing clarity over flash, which makes it easier to trust and grow into over time.

xiaqianjin

This is exactly what the AI agent space needs! The ability to describe workflows in plain English and have them turn into production-ready agents is a game changer. I'm particularly impressed by the state management approach mentioned by @dvargas92495 - that's crucial for building reliable agents that can handle complex multi-step workflows.

For teams building LLM applications, having the transparency to preview each step and review past runs addresses one of the biggest pain points: trust and debuggability. Too many agent frameworks are black boxes.

Quick question: How does Vellum handle API rate limiting and retries when agents are calling external services? This is often a challenge in production agent deployments.

First
Previous
123
Next
Last