Vellum is coming to the AI Engineering World's Fair in SF. Come visit our booth and get a live demo!
Vellum Product Update | November 2024

Something special is coming, plus new models and quality of life improvements

3 min
Written by
Reviewed by:

Why are LLMs the best guests at holiday parties?

They always arrive promptly

(sorry, that was written by a human… we’re still fine-tuning him)

Something New Is Coming

💡 Before we dive in… next month we’ll launch a novel Agent & Workflow development framework. If you want maximum control over your AI system, easier debugging and  confidence shipping to production — join the waitlist here.

Sneak preview of Vellum's new SDK

Play your favorite Christmas jingle, sit back, and enjoy our November product updates. If you're more visual, check out the video below:

Updated Prompt Sandbox UI

Prompt Editor

Previously, “Input Variables” and “Scenarios” were separate panels, which added friction to experimenting quickly. We’ve consolidated these panels and polished our Prompt Sandbox page as a whole, to make them easier to use and nicer to look at.

Prompt Editor UI Updates

Comparison Mode

We’ve made updating variable names easier. Previously, if you wanted to rename your variables, you had to scroll to the top of the page— which is far from where you interact with them. Now, you can rename them inline where you set their values.

Rename variables within scenarios

Chat Mode

Previously, it was difficult to view longer outputs on a single screen (or you needed to purchase a bigger monitor). Now, you can now resize any panel and all UI elements look consistent across all modes.

Updated Chat Mode

New APIs

Prompt / Workflow Deployment Release Tags and Historical Items

You can now retrieve Release Tags associated with Prompt and Workflow Deployments, as well as Historical Deployment items. Combined, these can be useful for ensuring smooth cutovers between your application code and your deployments when deployment interfaces change.

Audio Inputs for gpt-4o-audio-preview

OpenAI recently launched gpt-4o-audio-preview, which can process audio inputs and understand pronunciation, intonation, etc., as well as produce audio outputs. We now support these capabilities through an API. Read more here.

New Models

AWS Nova Models (Micro, Lite, Pro)
LLaMa 3.1 405b via SambaNova (speed 200 t/s)
Support for GPT-4o (2024-11-20)
Claude Haiku 3.5 10-22-2024

Quality of Life Updates

Real-time Workflow Execution Monitoring

Previously, if you wanted to view the live-execution traces of Workflows, you needed to refresh the Execution Details page to see updates. Now, you can see live-updates in the UI while the Workflow runs!

Increased Test Case Concurrency

We've increased the max concurrency for Test Case runs from 12 to 36, significantly speeding up your testing cycles and allowing for more efficient use of resources.

Copy & Paste Workflow Nodes Improvements

Previously, it wasn’t possible to copy & paste Workflow Nodes while their outputs from previous executions were showing. We’ve fixed this, and improved the overall reliability of copy/paste functionality within Workflows, Subworkflows, and across Workflow Sandboxes.

We’ve also removed the “Copy of” title text on Nodes when they’re pasted— making it easier to experiment and refactor Workflows to increase their maintainability.

Persisted Sort Order for Index Pages

Previously, if you left an Index/Browse page and came back to it, you’d have to set your preferred sort orders upon return. Now, we remember this for you, making it easier find your Prompts, Workflows, and Documents when you start a new working session.

Easier Evaluation Test Case CSV Uploads

Previously, if your CSV column headers didn’t *exactly* match what your Vellum interface expected, you’d have to open your CSV, update your headers, re-attempt uploading, rinse & repeat. Now, we allow optional headers, so you can upload CSVs of Test Cases with extra fields or missing fields and start running your Evals faster. We also now allow semicolon delimiters.

Full Height for Displaying Subworkflows

Previously, Subworkflow viewing UIs weren’t using the full height of their containers. Now, you can more easily navigate, iterate, and improve on Workflows leveraging Deployed Subworkflows.

Before and after portrayal of viewing Subworkflows

That’s all for now! Stay warm this December, be present with loved ones, and celebrate all the wonderful things you’ve accomplished over the past year. We’ll see you… next year 🤯

ABOUT THE AUTHOR

ABOUT THE reviewer

Noa Flaherty
Co-founder & CTO

Noa Flaherty, CTO and co-founder at Vellum (YC W23) is helping developers to develop, deploy and evaluate LLM-powered apps. His diverse background in mechanical and software engineering, as well as marketing and business operations gives him the technical know-how and business acumen needed to bring value to nearly any aspect of startup life. Prior to founding Vellum, Noa completed his undergrad at MIT and worked at three tech startups, including roles in MLOps at DataRobot and Product Engineering at Dover.

lAST UPDATED
Dec 2, 2024
Share Post
Expert verified
Related Posts
LLM basics
September 18, 2025
7
Top 11 Low‑Code AI Workflow Automation Tools: Compared & Reviewed (2025)
All
September 16, 2025
12 min
MCP UI & The Future of Agentic Commerce
Guides
September 16, 2025
4 min
Google's AP2: A new protocol for AI agent payments
Guides
September 15, 2025
6 min
We don’t speak JSON
LLM basics
September 12, 2025
10 min
Top 13 AI Agent Builder Platforms for Enterprises in 2025
LLM basics
September 12, 2025
8 min
Top 12 AI Workflow Platforms in 2025
The Best AI Tips — Direct To Your Inbox

Latest AI news, tips, and techniques

Specific tips for Your AI use cases

No spam

Oops! Something went wrong while submitting the form.

Each issue is packed with valuable resources, tools, and insights that help us stay ahead in AI development. We've discovered strategies and frameworks that boosted our efficiency by 30%, making it a must-read for anyone in the field.

Marina Trajkovska
Head of Engineering

This is just a great newsletter. The content is so helpful, even when I’m busy I read them.

Jeremy Hicks
Solutions Architect

Experiment, Evaluate, Deploy, Repeat.

AI development doesn’t end once you've defined your system. Learn how Vellum helps you manage the entire AI development lifecycle.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Email Signup
Sorts the trigger and email categories
Come to our next webinar
Description for our webinar
New CTA
Sorts the trigger and email categories

Start with some of these healthcare examples

Personalized healthcare explanations of a patient-doctor match
An AI workflow that extracts PII data and match evidence then summarizes to the user why a patient was matched with a specific provider, highlighting factors like insurance, condition, and symptoms.
SOAP Note Generation Agent
This agentic workflow generates a structured SOAP note from a medical transcript by extracting subjective and objective information, assessing the data, and formulating a treatment plan.

Start with some of these insurance examples

Insurance claims automation agent
This workflow automates the claims adjudication process in the insurance industry. It collects and analyzes claim information, assesses risks, verifies policy details, and generates a final decision along with a comprehensive audit trail.

Start with some of these agents

Agent that summarizes lengthy reports (PDF -> Summary)
This agent summarizes a PDF document by processing its contents through the Vellum Document API and generating a user-friendly summary. It allows users to input a document ID and receive a concise summary of the document's text.
PDF Data Extraction to CSV
This agentic workflow extracts data from PDF files and converts it into structured CSV format. It processes each page of the PDF, generating separate CSV outputs for menu items, invoices, and product specifications.
Retail pricing optimizer agent
This workflow creates a retail pricing optimization tool that analyzes product data and market conditions to recommend optimal pricing strategies. It helps businesses set competitive prices while ensuring profitability and compliance with business rules.