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

Vellum Product Update | October

Native integrations, Agent Builder Threads, and upgrades that make agent building faster than ever in Vellum.

7 min
Written by
Reviewed by
No items found.

The only thing we’re more thankful for than coding agents this November is everything our engineers shipped to Vellum in October.

This month’s updates make building in Vellum faster and smoother than ever, with big improvements to Agent Builder including native integrations, auto-generated agent tools, and better deployment visibility.

We’ve got plenty more improvements packed in, so let’s dive right in!

New Features

Native Integrations

Vellum now has 35+ native integrations and counting! What used to require a fragmented Composio setup or manual API configuration can now be done directly in Vellum.

Authenticate and manage third‑party integrations directly in the platform to use them inside Agent and Custom Nodes.

These native integrations let you seamlessly connect your agents to your everyday tools like Slack, Notion, HubSpot, and Airtable, so your Workflows can send messages, fetch data, or update records without any manual setup.

You can set up your integrations by interacting with Agent Builder, or manually by Settings > Integrations.

Agent Builder Threads

Agent Builder Threads are now generally available!

Threads save and organize your conversations in Agent Builder, so you can leave and come back to previous conversations without losing progress or create multiple threads to separate different ideas or tests.

These threads make it easy to stay organized in Agent Builder. You can keep one thread focused on debugging a Workflow while using another to iterate on a new agent, each with its own conversation history you can pick up anytime.

Agent Builder Improvements

Agent Builder Generates Agent Nodes with Integration Tools

Agent Builder can now automatically create Agent Nodes with the right integration tools when you ask it to use integrations in your Workflow. It configures the required tools and API calls for you, so you can go from intent to a callable node in one step.

If a native integration isn’t supported yet, Agent Builder can still generate a functional custom tool using Python, Agent handoffs, Inline Subworkflows, or version-controlled Deployed Subworkflows.

This makes it lightening fast to use Agent Builder to integrate your necessary tools and data systems and build complex automation without needing to manually configure tools or write custom code for every tool call.

Documents and Document Index Improvements

Managing files and indexes while building agents is no longer disconnected from the Workflow sandbox.

Agent Builder now includes superior document handling, letting you to create and view files in Document Indexes without leaving your build.

This makes it easier to design, debug, and refine document retrieval steps without leaving your Workflow sandbox.

Say you’re building a RAG support agent that needs to reference onboarding guides or help articles, you can now upload those documents, create a Document Index, and connect it to your Workflow all from Agent Builder.

Deployment Node Support

Agent Builder now supports Prompt Deployment Nodes and Workflow Deployment Nodes, letting you add version-controlled Prompts and Workflows directly into the builds you create.

This makes it easy to use Agent Builder to integrate tested releases and build more advanced systems without leaving your Workflow.

For example, if you’ve already deployed a Workflow that handles lead qualification, you can ask Agent Builder to use that deployment inside a new Workflow for outreach. It will automatically reference the version-controlled Workflow, so you can reuse trusted logic without rebuilding it from scratch.

Feature & Product Improvements

Release Page Artifacts

Each Workflow Deployment Release now includes a view of the exact code representation behind that release, the same code your CLI pulls and production runs.

This lets you inspect what’s actually deployed, line by line, so you can confirm changes, debug issues, and trust that what’s live matches what you built.

For example, if a Workflow starts returning unexpected outputs after deployment, you can open its release page and view the exact code representation for that version to quickly compare it with previous releases, spot what changed, and debug without switching between your CLI and the UI.

Simplified Deployment URLs

Deployment URLs have been simplified by using only the Deployment ID or name in the link.

Before: /workflow-sandboxes/<sandbox-id>/deployments/<deployment-id>

After: /workflow-deployments/<deployment-id>

This makes it easier to reference deployments from your external systems and link back to Vellum. This also gives you the ability to use a deployment’s name instead of its ID to keep URLs cleaner and more readable.

Not to panic, older links will continue to work and automatically redirect.

Settings Revamp

Models, integrations, and personal settings are no longer spread across different pages. The Settings Menu has been revamped and moved intuitively under your profile icon in the top right.

Models and integrations now live under Settings, while your personal profile and preferences have moved to the avatar menu.

This makes navigation simpler and setup faster, so you can manage your workspace and personal settings all in one place.

New Model Support

OpenAI

  • GPT‑5 Pro Modes
    • GPT 5 Pro
    • GPT 5 Pro (2025-10-06)

Anthropic

  • Claude Haiku 4.5

That’s a wrap for October.

Agent Builder really leveled up this month. It’s now faster at understanding what you need, smarter about how it builds, and more connected to the tools you already use. Jump back into Vellum, try the new flow, and see how much smoother it feels to bring your agents to life. Please reach out with any feedback, we’d love to hear it!

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
Nicolas Zeeb
Technical Content Lead

Nick is Vellum’s technical content lead, writing about practical ways to use both voice and text-based agents at work. He has hands-on experience automating repetitive workflows so teams can focus on higher-value work.

No items found.
lAST UPDATED
Nov 5, 2025
share post
Expert verified
Related Posts
All
November 3, 2025
6 min
I’m done building AI agents
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
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

Population health insights reporter
Combine healthcare sources and structure data for population health management.
Healthcare explanations of a patient-doctor match
Summarize why a patient was matched with a specific provider.

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

Start with some of these insurance examples

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.
AI agent for claims review
Review healthcare claims, detect anomalies and benchmark pricing.

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 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

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

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

Start with some of these agents

Review Comment Generator for GitHub PRs
Generate a code review comment for a GitHub pull request.
Trust Center RAG Chatbot
Read from a vector database, and instantly answer questions about your security policies.

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

Build AI agents in minutes

ReAct agent for web search and page scraping
Gather information from the internet and provide responses with embedded citations.
Healthcare explanations of a patient-doctor match
Summarize why a patient was matched with a specific provider.
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.
Trust Center RAG Chatbot
Read from a vector database, and instantly answer questions about your security policies.
AI agent for claims review
Review healthcare claims, detect anomalies and benchmark pricing.

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.