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

Vellum Product Update | September 2023

September is full of enhancements to Workflows, Security, Support, and more!

Written by
Reviewed by
No items found.

Welcome to another Vellum product update! September brings a wide variety of enhancements across most of Vellum, but had a special focus on Workflows, Security, and Support. Let’s dig in!

Workflow Sandboxes

We released Workflows last month to help you quickly prototype, deploy, and manage complex chains of LLM calls and the business logic that tie them together. The reception has been amazing and we’ve already been pushed by many of you to make Workflows even more powerful.

API Nodes

You can now make HTTP requests as part of a Workflow using the new “API Node.” API Nodes are critical for building agents, or for integrating more deeply with your own application. For example, maybe you need fetch data about a user through an authenticated API that you host and then feed the response into a Prompt for use by an LLM.

Renaming Workflow Scenarios

Scenarios are used to define example sets of input variable values that represent the types of inputs you might see in production. You can swap between scenarios to manually test how changes to your Workflow effect its outputs for that Scenario.

You can now rename Scenarios so that you can easily tell which case each Scenario represents.

Workflow Deployments

You can deploy a Workflow so that you can invoke complex chains of LLM Prompts with a single API call to Vellum, with all the monitoring, versioning, and scaling benefits that you’re used to with Vellum Prompt Deployments.

Now, we’re bringing more and more features from Prompt Deployments to Workflow Deployments.

Save Execution as Scenario

Once you’ve integrated a Workflow Deployment with your application, Vellum will track all requests made against it – their inputs, outputs, latency, etc. Now, if you spot an edge case, you can save it as a Scenario to your Workflow Sandbox so that you can iterate on your Workflow until it outputs what you expect.

Supplying Actuals

Just like you can “supply actuals” to a Prompt Deployment to capture end-user feedback, you can now do the same for Workflow Deployments. You’re able to supply a quality score (between 0.0 - 1.0) for each Output within the Workflow, as well as a “Desired Output” representing what you wish the output had been.

You can do this either manually from the UI.

Or programmatically via the API (which is particularly useful for capturing feedback directly from your end users).

Displaying Errors

You can now see when errors occur in production on individual Workflow Deployment Executions, as well as a description of the error.

Security

Security and data privacy is treated with the utmost of care within Vellum. We continue to invest in making Vellum an enterprise-ready solution for building AI applications.

Secret Management + Auth Headers

You can now define “Secrets” in one central place in Vellum (e.g. API keys, service tokens, etc.) and then dynamically reference them elsewhere in Vellum. These secret values are securely encrypted and stored using Google Cloud Platform’s KMS service.

You might then use these Secrets as authorization header values in API Nodes within Workflows and in Webhook Evaluation Metrics within Test Suites.

HMAC Signatures

You can now provide a secret token that can be used to verify that outgoing API requests are in fact coming from Vellum. This is especially helpful if you’re standing up endpoints for use by API Nodes or Webhook Evaluation Metrics and want to ensure no one is trying to maliciously impersonate Vellum.

Deployments

Prompt Deployments got some UI/UX love this month.

Filters, Column Visibility, and Refresh

There are now visual indicators when the Completions table of a Prompt Deployment has hidden columns and/or has filters applied. As a result, it’s also easy to update column visibility and filter criteria. You can also now refresh the table’s data with the new “Refresh” button.

Prevent Deletion of Deployments Used in Workflows

Every Prompt Node within a Workflow Deployment is backed by a Prompt Deployment. We now show a warning when you try to delete a Prompt Deployment that’s still in use by a Workflow Deployment.

API

Retrieve Document Index

There is now an officially supported API (in Beta state) to retrieve a Document Index by it’s ID/Name. This is useful if you’re programmatically creating indexes and want to check to see if one already exists prior to creating it.

Support

We’ve made a big push this past month to get the help you need while using Vellum. We can’t claim it’s perfect yet, so please always feel free to reach out to us on Slack, Discord, or email us at support@vellum.ai!

New Help Docs

We have a brand new Help Docs site thanks to our friends at Fern. You can expect richer documentation and tighter integration with our API Docs over the coming months.

In-App Support via Pylon

You can now chat with us directly within the Vellum application thanks to our friends at Pylon. If you’re a Vellum customer with a shared Slack channel with us, then these messages will sync and carry over to the channel.

Conclusion

And that’s a wrap! Thanks as always to all of you who help push us to build a better product and become a better business every month.

We have exciting plans for October – stayed tuned!

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
Oct 2, 2023
share post
Expert verified
Related Posts
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
LLM basics
September 25, 2025
8 min
Top Low-code AI Agent Platforms for Product Managers
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.
SOAP Note Generation Agent
Extract subjective and objective info, assess and output a treatment plan.

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

Competitor research agent
Scrape relevant case studies from competitors and extract ICP details.
ReAct agent for web search and page scraping
Gather information from the internet and provide responses with embedded citations.

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

Start with some of these legal examples

PDF Data Extraction to CSV
Extract unstructured data (PDF) into a structured format (CSV).
AI legal research agent
Comprehensive legal research memo based on research question, jurisdiction and date range.

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

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.
Trust Center RAG Chatbot
Read from a vector database, and instantly answer questions about your security policies.
Turn LinkedIn Posts into Articles and Push to Notion
Convert your best Linkedin posts into long form content.
LinkedIn Content Planning Agent
Create a 30-day Linkedin content plan based on your goals and target audience.
Prior authorization navigator
Automate the prior authorization process for medical claims.
E-commerce shopping agent
Check order status, manage shopping carts and process returns.

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.