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

Vellum Product Update | April 2025

We have a bunch of quality-of-life upgrades including protected tags, smoother Workflows, and more!

3 min
Written by
Reviewed by
No items found.

It’s spring cleaning season and we delivered - with a bunch of quality-of-life upgrades including protected tags, smoother Workflows, and bringing back some fan-favourite features, April’s updates will be sure to spark joy ✨

🆕 Key New Features

Protected Release Tags

Last month, we introduced Deployment Release Reviews to help you provide reviews on Prompts and Workflows after hitting deploy. This month, we’re adding to it with Protected Release Tags — a feature which will enforce Releases marked as “protected” to have at least one approval from a Reviewer and have zero outstanding change requests - beforeit can be assigned to a Prompt / Deployment. Useful for anyone working in critical/sensitive deployments that need more rigorous approvals before going live.

Just mark a tag as protected in the UI or API.

Dynamic Model Selection for Inline Prompts

You asked and we listened - inline prompts now accept expression inputs to represent the Model invoked in the Prompt. Previously, you were only able to statically select a model for a given Prompt Node - but now, you can use expression inputs to dynamically reference a model from an upstream Node or Workflow Input.

Inline Prompt Nodes just got a major power-up.

So if you’re looking to A/B testing models, route between cost tiers, or looking to make changes to adapt to user preference, this is a great feature for you.

Ports on Workflow Nodes

All Workflow Nodes now support Ports! Ports act as a connector to Nodes that use branching logic and conditional execution to determine which Nodes to execute next in the workflow. Before, you had to use a separate Conditional Node to set up branching logic in your workflow. Now, every node has a “Ports” attribute that controls which path to take next, so you can simplify the number of nodes in your workflow to deliver the functionality you want.

This makes it easier to parse how data flows through your Workflow, making it easier to visually see what happens next and what logic was applied.

Grouping a Selection into a New Subworkflow Node

You can now select multiple Nodes and instantly group them into a new Subworkflow - and all existing connections will be maintained. You can even drag Nodes into existing Subworkflows, to keep things modular and tidy.

Useful as you build increasingly more complex systems to keep everything neat and tidy.

Add Node on Edge

Previously, the only way to add a Node was to drag and drop a new Node from the Nodes Panel. Now - you can now click any edge between nodes to insert a new node right into the middle of your flow. A Node selection menu will appear, allowing you to choose the type of Node and the new Node will be connected to the edge.

Building and refactoring Workflows is now much faster — especially during prototyping.

Non-Streaming Prompt Nodes

Prompt Nodes now let you choose between streaming and non-streaming execution. Non-streaming mode is ideal when parallelism matters — like with workflows that host Map Nodes.

Streaming and non-streaming options.

Test Suite Run Progress

Track live progress as your evaluation runs — just hover over the indicator to see how many test cases are done and how many are still moving along so you can keep tabs on progress.

See the progress of an evaluation report run while it’s actively running.

Run From Node Re-enabled for SDK-Enabled Workflows

We brought back the fan-favorite Run From Node feature for SDK-enabled Workflows! Pick up execution right from any Node using a previous execution (just like before) and hit the play button which will use the “State” saved from the previous execution to run the Workflow from that point going forward. Use this feature to directly see the difference in any change that you’ve made from a specific Node onwards.

To invoke a Workflow starting from a Node, click the mini play button on the Node when a previous execution is loaded.

Sandbox Cost Tracking for Workflows

You can now see how much your Subworkflows are costing — right inside the Workflow Sandbox. After a run, we’ll show you the total cost of everything triggered by your Subworkflow and Deployment Subworkflow Nodes.

This is an aggregate sum of total costs for your workflow invoked by your Subworkflow Nodes.

🧠 Model & API Support

  • Llama 4 models from Meta
    • Fireworks AI: Llama 4 Scout, Llama 4 Maverick
    • Groq: Llama 4 Scout, Llama 4 Maverick 17B Instruct
  • GPT-4.1 via OpenAI
    • GPT-4.1
    • GPT-4.1 (2025-04-14) Snapshot
    • GPT-4.1 Mini + Snapshot
    • GPT-4.1 Nano + Snapshot
  • xAI Models
  • OpenAI’s newest
    • o3
    • o4 Mini
    • Grok 3 Beta
    • Grok 3 Fast Beta
    • Grok 3 Mini Beta
    • Grok 3 Mini Fast Beta

That’s all for April - we’ll back next month with a bunch of freshly cooked updates for you, but till then happy building!

See the full changelog here: https://docs.vellum.ai/changelog/2025/2025-04

ABOUT THE AUTHOR
Sharon Toh
Product and Growth Marketing

Sharon brings a background in product marketing and a proven ability to help SaaS companies achieve remarkable growth. With a well-established history of crafting strategies that resonate with audiences, she’s passionate about bridging the gap between cutting-edge AI solutions and the people who need them most. As part of Vellum's GTM team, Sharon focuses on connecting businesses and people with the right solutions that deliver impact, making advanced technology accessible and effective.

ABOUT THE reviewer

No items found.
lAST UPDATED
May 1, 2025
share post
Expert verified
Related Posts
Guides
October 21, 2025
15 min
AI transformation playbook
LLM basics
October 20, 2025
8 min
The Top Enterprise AI Automation Platforms (Guide)
LLM basics
October 10, 2025
7 min
The Best AI Workflow Builders for Automating Business Processes
LLM basics
October 7, 2025
8 min
The Complete Guide to No‑Code AI Workflow Automation Tools
All
October 6, 2025
6 min
OpenAI's Agent Builder Explained
Product Updates
October 1, 2025
7
Vellum Product Update | September
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.
Build AI agents in minutes with Vellum
Build agents that take on the busywork and free up hundreds of hours. No coding needed, just start creating.

General CTA component, Use {{general-cta}}

Build AI agents in minutes with Vellum
Build agents that take on the busywork and free up hundreds of hours. No coding needed, just start creating.

General CTA component  [For enterprise], Use {{general-cta-enterprise}}

The best AI agent platform for enterprises
Production-grade rigor in one platform: prompt builder, agent sandbox, and built-in evals and monitoring so your whole org can go AI native.

[Dynamic] Ebook CTA component using the Ebook CMS filtered by name of ebook.
Use {{ebook-cta}} and add a Ebook reference in the article

Thank you!
Your submission has been received!
Oops! Something went wrong while submitting the form.
Button Text

LLM leaderboard CTA component. Use {{llm-cta}}

Check our LLM leaderboard
Compare all open-source and proprietary model across different tasks like coding, math, reasoning and others.

Case study CTA component (ROI)

40% cost reduction on AI investment
Learn how Drata’s team uses Vellum and moves fast with AI initiatives, without sacrificing accuracy and security.

Case study CTA component (cutting eng overhead) = {{coursemojo-cta}}

6+ months on engineering time saved
Learn how CourseMojo uses Vellum to enable their domain experts to collaborate on AI initiatives, reaching 10x of business growth without expanding the engineering team.

Case study CTA component (Time to value) = {{time-cta}}

100x faster time to deployment for AI agents
See how RelyHealth uses Vellum to deliver hundreds of custom healthcare agents with the speed customers expect and the reliability healthcare demands.

[Dynamic] Guide CTA component using Blog Post CMS, filtering on Guides’ names

100x faster time to deployment for AI agents
See how RelyHealth uses Vellum to deliver hundreds of custom healthcare agents with the speed customers expect and the reliability healthcare demands.
New CTA
Sorts the trigger and email categories

Dynamic template box for healthcare, Use {{healthcare}}

Start with some of these healthcare examples

SOAP Note Generation Agent
Extract subjective and objective info, assess and output a treatment plan.
Population health insights reporter
Combine healthcare sources and structure data for population health management.

Dynamic template box for insurance, Use {{insurance}}

Start with some of these insurance examples

Agent that summarizes lengthy reports (PDF -> Summary)
Summarize all kinds of PDFs into easily digestible summaries.
AI agent for claims review
Review healthcare claims, detect anomalies and benchmark pricing.
Insurance claims automation agent
Collect and analyze claim information, assess risk and verify policy details.

Dynamic template box for eCommerce, Use {{ecommerce}}

Start with some of these eCommerce examples

E-commerce shopping agent
Check order status, manage shopping carts and process returns.

Dynamic template box for Marketing, Use {{marketing}}

Start with some of these marketing examples

ReAct agent for web search and page scraping
Gather information from the internet and provide responses with embedded citations.
LinkedIn Content Planning Agent
Create a 30-day Linkedin content plan based on your goals and target audience.

Dynamic template box for Sales, Use {{sales}}

Start with some of these sales examples

Research agent for sales demos
Company research based on Linkedin and public data as a prep for sales demo.

Dynamic template box for Legal, Use {{legal}}

Start with some of these legal examples

Legal RAG chatbot
Chatbot that provides answers based on user queries and legal documents.
Legal document processing agent
Process long and complex legal documents and generate legal research memorandum.

Dynamic template box for Supply Chain/Logistics, Use {{supply}}

Start with some of these supply chain examples

Risk assessment agent for supply chain operations
Comprehensive risk assessment for suppliers based on various data inputs.

Dynamic template box for Edtech, Use {{edtech}}

Start with some of these edtech examples

Turn LinkedIn Posts into Articles and Push to Notion
Convert your best Linkedin posts into long form content.

Dynamic template box for Compliance, Use {{compliance}}

Start with some of these compliance examples

No items found.

Dynamic template box for Customer Support, Use {{customer}}

Start with some of these customer support examples

Trust Center RAG Chatbot
Read from a vector database, and instantly answer questions about your security policies.
Q&A RAG Chatbot with Cohere reranking

Template box, 2 random templates, Use {{templates}}

Start with some of these agents

Prior authorization navigator
Automate the prior authorization process for medical claims.
Turn LinkedIn Posts into Articles and Push to Notion
Convert your best Linkedin posts into long form content.

Template box, 6 random templates, Use {{templates-plus}}

Build AI agents in minutes

Research agent for sales demos
Company research based on Linkedin and public data as a prep for sales demo.
Legal document processing agent
Process long and complex legal documents and generate legal research memorandum.
Insurance claims automation agent
Collect and analyze claim information, assess risk and verify policy details.
Turn LinkedIn Posts into Articles and Push to Notion
Convert your best Linkedin posts into long form content.
Synthetic Dataset Generator
Generate a synthetic dataset for testing your AI engineered logic.
Healthcare explanations of a patient-doctor match
Summarize why a patient was matched with a specific provider.

Build AI agents in minutes for

{{industry_name}}

Clinical trial matchmaker
Match patients to relevant clinical trials based on EHR.
Prior authorization navigator
Automate the prior authorization process for medical claims.
Population health insights reporter
Combine healthcare sources and structure data for population health management.
Legal document processing agent
Process long and complex legal documents and generate legal research memorandum.
Legal contract review AI agent
Asses legal contracts and check for required classes, asses risk and generate report.
Legal RAG chatbot
Chatbot that provides answers based on user queries and legal documents.

Case study results overview (usually added at top of case study)

What we did:

1-click

This is some text inside of a div block.

28,000+

Separate vector databases managed per tenant.

100+

Real-world eval tests run before every release.