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

Vellum Product Update | August

MCP-powered Agent Nodes, public Workflow sharing, and a new Workflow Console for easier, collaborative building.

6 min
Written by
Reviewed by
No items found.

With September starting to cool us down, Vellum is still heating up from August updates.

This month we focused on empowering our builders by integrating MCP into Agent Nodes, making all Workflows shareable, and added a brand‑new sandbox console to make building cleaner and easier than before.

With plenty more features and UX updates, let’s get into it!

MCP in Agent Node

Agent nodes used to limited to custom connections with external tools.

With MCP enabled in the Agent Node, you can now connect your Agent Node to MCP servers and Vellum will automatically discover and execute available tools.

With MCP support, Agent nodes can dynamically discover and expose every tool from a connected MCP server, eliminating the need for one-off API connectors.

This standardization cuts boilerplate integration code, ensuring agents across different workflows can reliably call the same toolset with consistent parameters and behaviors.

Workflow Console

Debugging workflows used to mean tedious clicking between nodes to piece together what happened.

To reduce this friction and make complex workflow management simpler, we’ve introduced a Workflow Console.

Workflow Console is equipped with:

  • Logs that show the chronological timeline view of workflow executions including latency
  • Panel view that shows the inputs and outputs of any executed node

This makes it far easier to debug and monitor complex Workflow executions, giving you a clear top-down view of each branch, retry, and reasoning step without clicks or extra reruns.

Workflow sharing

Sharing workflows used to only happened at the team level.

Now, you can make your workflows public to:

  • share on social media
  • embed an iframe on your website
  • share to Vellum community for others to clone and use for themselves

Every workflows ca now become a reusable assets beyond its value to your immediate team.

Workflows

Editable Code Preview Files

Previewing code used to mean running ‘vellum workflows pull’ to edit your code then doing a ‘vellum workflow push’ to update workflow code.

Now editing and previewing code can all be done in Vellum with Editable Code Preview Files.

Toggling Edit Mode enables direct edits and file modification in the Code Preview UI, giving you greater code control without using low code UI.

Workflow Canvas Collapse Toggle

Complex canvases could feel crowded, and sharing a tidy view wasn’t possible.

Now you have the option to quick collapse/expand nodes within the workflow with a toggle switch.

Updated Node Handles

Node Handles used to be too visually complex.

Node Handles now include a new plus icon, improved edge dropping, and visual states for incoming edges:

  • Nodes with 0 incoming edges
  • Nodes with 1 incoming edge
  • Nodes with 2+ incoming edges

These cleaner connection structures reduces visual noise while giving you greater visibility into workflow scaffolding at a glance.

New Model Support

We added support for:

  • OpenAI GPT‑5 family (GPT‑5, Mini, Nano) via Chat Completions and Responses APIs
  • OpenAI GPT‑OSS 120B and 20B
  • GPT‑OSS 120B on Cerebras
  • GPT‑OSS 120B and 20B on Groq
  • Anthropic Claude Opus 4.1
  • Cerebras Qwen 3 480B (Coder, Thinking, Instruct)
  • Vertex AI Gemini 2.5 Flash lite finetuned models

More options to enable you to build the most efficient workflows.

Quality of Life improvements

Updated Insert Node Panel

Finding and adding nodes within workflows used to be more manual and tedious, so we re-designed the panel to make it quicker to find and add nodes.

Key improvements include:

  • Search Bar: Quickly find specific nodes by typing their name
  • Updated Copy: Clearer, more concise descriptions for each node type
  • Smaller Cards: More compact design that fits more nodes on screen
  • Reorganized Layout: Better categorization with logical groupings
  • Nested Hierarchy: Expandable sections for Control Flow and other categories

Revamped Model Page

Our older model page included too much visual noise making it hard to find the models you wanted to manager.

We gave it a makeover with a cleaner interface that houses models by provider.

Improved Variable Detection

Previously, when you pasted prompts with {{ variable }} placeholders into Rich Text inputs, any undefined variables were treated as plain text instead of being recognized.

With this update, Vellum now automatically creates those variables and displays them as chips.

This makes it much easier to copy and paste prompts directly from your codebase or other tools without extra setup, speeding up workflow building.

See you in October!

From adding video inputs and workflow sharing to improving agent tools and the model management experience, August was all about faster iteration with deeper capabilities and smoother UX. September will bring even more exciting features to builders and collaborators alike. As always, we’d love your feedback—let us know what you think and what you’d like to see next!

ABOUT THE AUTHOR
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.

ABOUT THE reviewer

No items found.
lAST UPDATED
Sep 3, 2025
share post
Expert verified
Related Posts
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
Guides
October 6, 2025
15
A practical guide to AI automation
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

Healthcare explanations of a patient-doctor match
Summarize why a patient was matched with a specific provider.
Clinical trial matchmaker
Match patients to relevant clinical trials based on EHR.

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

Start with some of these insurance examples

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.
Agent that summarizes lengthy reports (PDF -> Summary)
Summarize all kinds of PDFs into easily digestible summaries.

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

LinkedIn Content Planning Agent
Create a 30-day Linkedin content plan based on your goals and target audience.
Competitor research agent
Scrape relevant case studies from competitors and extract ICP details.

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

Start with some of these legal examples

AI legal research agent
Comprehensive legal research memo based on research question, jurisdiction and date range.
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

PDF Data Extraction to CSV
Extract unstructured data (PDF) into a structured format (CSV).
Population health insights reporter
Combine healthcare sources and structure data for population health management.

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

Build AI agents in minutes

Competitor research agent
Scrape relevant case studies from competitors and extract ICP details.
Review Comment Generator for GitHub PRs
Generate a code review comment for a GitHub pull request.
Legal RAG chatbot
Chatbot that provides answers based on user queries and legal documents.
Clinical trial matchmaker
Match patients to relevant clinical trials based on EHR.
AI legal research agent
Comprehensive legal research memo based on research question, jurisdiction and date range.
Insurance claims automation agent
Collect and analyze claim information, assess risk and verify policy details.

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.