Today, we’re excited to release AI Apps: customizable UIs that let teams share and run AI workflows as apps in Vellum.
Before, running Workflows outside of Vellum required developers to wire up API calls from external applications or tools.
AI apps eliminates this barrier by letting you test, iterate, and interact with deployed Workflows directly through the AI App interface in Vellum.
Now you and your team can quickly test Workflows with an interface, then roll them out as powerful automations across the org.
👉 Try AI Apps now or book a call to see how others have built a library of AI apps for their whole organization to use.
Why we need an interface for AI workflows
While the old way of testing Workflows in Vellum through firing off API requests or relying on external tools worked for developers, it left non-technical teammates behind.
AI Apps changes this by providing a streamlined, first-class interface for your whole team to run and iterate on Workflows. You can now seamlessly involve all stakeholders and domain experts to test and run Workflows with an interface that's easy to use and interact with.
Equally important, the AI apps you can build with Vellum can easily adapt to different contexts. Teams can build their own library of agent artifacts and share them across the organization. Workflows can now double as powerful internal productivity AI automations tool that can be used across your whole org through the AI Apps UI.
AI Apps further enable technical and non-technical teams through:
Reduced engineering overhead: No more wiring API calls just to test an AI workflow
Faster iteration cycles: Everyone can validate ideas via the UI
Organization wide adoption: Anyone can build and share agent artifacts
Stakeholder alignment: Test can share interactive demos that decision makers can try themselves
How AI Apps works
Vellum automatically analyzes your workflow and generates an AI App UI for your deployed Workflow. In this UI, you'll see all the required input fields that match your Workflow’s parameters, text inputs, numerical values, file uploads, and other data types..
When you hit Run, Vellum calls the same APIs your production environment does, and the results are streamed in realtime. The result is an interactive and simple to use AI app, that was built in a fraction of second.
Key capabilities
Intuitive input interface: Input forms are auto-generated to match your Workflow, including text fields, numbers, file uploads, and more.
Real-time execution: Run Workflows with production-level reliability and watch outputs stream back as they’re generated.
Interactive testing flow: Edit inputs and re-run executions as many times as needed in the same session.
Seamless access points: Open an AI App from the Share Workflow modal or directly from your Deployments overview.
Feature overview
Capabilities
What It Does
Why It Helps
Auto-generated App Interface
Vellum auto-generates clean fields for text, numbers, file uploads, and more.
Anyone can test a Workflow without writing code or setting up API calls.
Real-Time Execution
Runs Workflows with production reliability and streams output as it’s generated.
Validates behavior instantly and mirrors what happens in production.
Interactive Testing Flow
Edit inputs and re-run executions within the same session.
Speeds up iteration cycles and makes debugging frictionless.
Seamless Access Points
Launch AI Apps from the Share Workflow modal or the Deployments overview page.
Quick entry for both developers and non-technical teammates.
Production-Grade Accuracy
Executes against the same Vellum APIs that power live integrations.
Ensures results match real-world execution, not mock data.
Collaboration Ready
Share the AI App UI link with teammates and stakeholders.
Makes testing and demos accessible across your organization.
How to access AI Apps
There are two ways to open an AI App in Vellum:
1. Share Workflow Button – From any deployed Workflow, click the Share button to reveal both the AI App link and traditional read-only options.
2. Deployments Overview – Visit the Deployments page and open the AI App directly from the Workflow card.
Now, everyone can build their AI apps
We built AI Apps to help everyone on your team to become AI native, faster. The powerful Workflows you create in Vellum shouldn’t be gated by engineering’s bandwidth, they should be accessible and usable across the whole org. This is a step forward to help the organizations using Vellum to become truly AI-native.
Developers can rapidly test logic changes, fine-tune prompts, and debug without juggling API calls or external apps
Product, Ops & Business teams can validate automations against real data, ensuring processes run smoothly before they go live.
Leaders & Stakeholders can interact with Workflows firsthand, gaining clarity and confidence in how AI is shaping business operations.
Internal teams can use AI Apps as powerful AI tools for day-to-day work, without needing a custom UI or API integration.
AI Apps are just the beginning of making Workflows accessible across every corner of your organization. We’re excited to keep building on this foundation, and can’t wait to see how your teams put AI Apps to work.
AI Apps are interactive, no-code interfaces automatically generated for any deployed Workflow in Vellum. They let you run, test, and share Workflows directly in the platform without needing custom code or external tools.
2. How do AI Apps differ from using the API directly?
While the API gives developers full control for integrations, AI Apps provide a ready-made interface for testing, demos, and everyday internal use. Both hit the same production-grade APIs under the hood, so results are identical.
3. Who can use AI Apps inside my organization?
You can enable anyone in your org with access to your Workflow’s App with a sharable link. This makes Workflow testing and usage collaborative instead of developer-only.
4. Can AI Apps be shared outside of my organization?
Yes, you can share any AI App through the AI App link. Fetch the link by pressing the “Share” button in Workflows or the AI App link present in the deployments window.
5. What types of inputs are supported in AI Apps?
AI Apps support any input available in your workflow. It auto-generates input fields based on your Workflow to make it easy to populate input fields and replicate production conditions when testing.
6. How do AI Apps support internal tooling?
Teams can internally use AI Apps as powerful AI agents or automations for all sorts of tasks like document analysis, reporting, content generation, etc. This avoids the need to build a custom UI or integrate with another system just to use the Workflow.
7. Do AI Apps cost extra to use?
No. Running a Workflow through an AI App consumes the same credits/resources as running it through the API. There are no additional fees for using the AI App interface itself.
8. How do I get started with AI Apps today?
Simply deploy a Workflow in Vellum. From the Deployments page or the Share button in Workflows, use the link to open the AI App. You’ll instantly see a ready-to-use interface.
Today, we’re excited to release AI Apps: customizable UIs that let teams share and run AI workflows as apps in Vellum.
Before, running Workflows outside of Vellum required developers to wire up API calls from external applications or tools.
AI apps eliminates this barrier by letting you test, iterate, and interact with deployed Workflows directly through the AI App interface in Vellum.
Now you and your team can quickly test Workflows with an interface, then roll them out as powerful automations across the org.
👉 Try AI Apps now or book a call to see how others have built a library of AI apps for their whole organization to use.
Why we need an interface for AI workflows
While the old way of testing Workflows in Vellum through firing off API requests or relying on external tools worked for developers, it left non-technical teammates behind.
AI Apps changes this by providing a streamlined, first-class interface for your whole team to run and iterate on Workflows. You can now seamlessly involve all stakeholders and domain experts to test and run Workflows with an interface that's easy to use and interact with.
Equally important, the AI apps you can build with Vellum can easily adapt to different contexts. Teams can build their own library of agent artifacts and share them across the organization. Workflows can now double as powerful internal productivity AI automations tool that can be used across your whole org through the AI Apps UI.
AI Apps further enable technical and non-technical teams through:
Reduced engineering overhead: No more wiring API calls just to test an AI workflow
Faster iteration cycles: Everyone can validate ideas via the UI
Organization wide adoption: Anyone can build and share agent artifacts
Stakeholder alignment: Test can share interactive demos that decision makers can try themselves
How AI Apps works
Vellum automatically analyzes your workflow and generates an AI App UI for your deployed Workflow. In this UI, you'll see all the required input fields that match your Workflow’s parameters, text inputs, numerical values, file uploads, and other data types..
When you hit Run, Vellum calls the same APIs your production environment does, and the results are streamed in realtime. The result is an interactive and simple to use AI app, that was built in a fraction of second.
Key capabilities
Intuitive input interface: Input forms are auto-generated to match your Workflow, including text fields, numbers, file uploads, and more.
Real-time execution: Run Workflows with production-level reliability and watch outputs stream back as they’re generated.
Interactive testing flow: Edit inputs and re-run executions as many times as needed in the same session.
Seamless access points: Open an AI App from the Share Workflow modal or directly from your Deployments overview.
Feature overview
Capabilities
What It Does
Why It Helps
Auto-generated App Interface
Vellum auto-generates clean fields for text, numbers, file uploads, and more.
Anyone can test a Workflow without writing code or setting up API calls.
Real-Time Execution
Runs Workflows with production reliability and streams output as it’s generated.
Validates behavior instantly and mirrors what happens in production.
Interactive Testing Flow
Edit inputs and re-run executions within the same session.
Speeds up iteration cycles and makes debugging frictionless.
Seamless Access Points
Launch AI Apps from the Share Workflow modal or the Deployments overview page.
Quick entry for both developers and non-technical teammates.
Production-Grade Accuracy
Executes against the same Vellum APIs that power live integrations.
Ensures results match real-world execution, not mock data.
Collaboration Ready
Share the AI App UI link with teammates and stakeholders.
Makes testing and demos accessible across your organization.
How to access AI Apps
There are two ways to open an AI App in Vellum:
1. Share Workflow Button – From any deployed Workflow, click the Share button to reveal both the AI App link and traditional read-only options.
2. Deployments Overview – Visit the Deployments page and open the AI App directly from the Workflow card.
Now, everyone can build their AI apps
We built AI Apps to help everyone on your team to become AI native, faster. The powerful Workflows you create in Vellum shouldn’t be gated by engineering’s bandwidth, they should be accessible and usable across the whole org. This is a step forward to help the organizations using Vellum to become truly AI-native.
Developers can rapidly test logic changes, fine-tune prompts, and debug without juggling API calls or external apps
Product, Ops & Business teams can validate automations against real data, ensuring processes run smoothly before they go live.
Leaders & Stakeholders can interact with Workflows firsthand, gaining clarity and confidence in how AI is shaping business operations.
Internal teams can use AI Apps as powerful AI tools for day-to-day work, without needing a custom UI or API integration.
AI Apps are just the beginning of making Workflows accessible across every corner of your organization. We’re excited to keep building on this foundation, and can’t wait to see how your teams put AI Apps to work.
AI Apps are interactive, no-code interfaces automatically generated for any deployed Workflow in Vellum. They let you run, test, and share Workflows directly in the platform without needing custom code or external tools.
2. How do AI Apps differ from using the API directly?
While the API gives developers full control for integrations, AI Apps provide a ready-made interface for testing, demos, and everyday internal use. Both hit the same production-grade APIs under the hood, so results are identical.
3. Who can use AI Apps inside my organization?
You can enable anyone in your org with access to your Workflow’s App with a sharable link. This makes Workflow testing and usage collaborative instead of developer-only.
4. Can AI Apps be shared outside of my organization?
Yes, you can share any AI App through the AI App link. Fetch the link by pressing the “Share” button in Workflows or the AI App link present in the deployments window.
5. What types of inputs are supported in AI Apps?
AI Apps support any input available in your workflow. It auto-generates input fields based on your Workflow to make it easy to populate input fields and replicate production conditions when testing.
6. How do AI Apps support internal tooling?
Teams can internally use AI Apps as powerful AI agents or automations for all sorts of tasks like document analysis, reporting, content generation, etc. This avoids the need to build a custom UI or integrate with another system just to use the Workflow.
7. Do AI Apps cost extra to use?
No. Running a Workflow through an AI App consumes the same credits/resources as running it through the API. There are no additional fees for using the AI App interface itself.
8. How do I get started with AI Apps today?
Simply deploy a Workflow in Vellum. From the Deployments page or the Share button in Workflows, use the link to open the AI App. You’ll instantly see a ready-to-use interface.
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.
ABOUT THE reviewer
Anita Kirkovska
Founding Growth Lead
An AI expert with a strong ML background, specializing in GenAI and LLM education. A former Fulbright scholar, she leads Growth and Education at Vellum, helping companies build and scale AI products. She conducts LLM evaluations and writes extensively on AI best practices, empowering business leaders to drive effective AI adoption.
Top Low-code AI Agent Platforms for Product Managers
LLM basics
September 25, 2025
•
8 min
The Best AI Agent Frameworks For Developers
LLM basics
September 18, 2025
•
7 min
Top 11 low‑code AI workflow automation tools
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
The Best AI Tips — Direct To Your Inbox
Latest AI news, tips, and techniques
Specific tips for Your AI use cases
No spam
Thank you! Your submission has been received!
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.
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.
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.
This workflow automates the review of healthcare claims to detect anomalies and benchmark pricing against established guidelines. It processes claim documents, extracts relevant data, and generates both structured JSON outputs and natural language summaries for human reviewers.
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.
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.
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.
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.
.avif)
