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

Introducing Subworkflows (tools) for modular, reusable AI logic

Learn how to build modular, reusable, and version-controlled tools (subworkflows) to keep your workflows efficient.

5 min
Written by
Reviewed by
No items found.

AI workflows tend to grow messy as complexity increases.

That’s why we’ve built Subworkflow nodes in Vellum—a powerful new component to help you create reusable, version-controlled logic that will keep your AI workflows clean and easy to manage in production.

What are Subworkflow nodes?

Subworkflow nodes are like self-contained tools within your workflow.

Think of them as "black boxes" that perform specific tasks, from simple calculations to running advanced code or performing SERP lookups. They take inputs, process them with some predefined logic, and produce outputs—all without cluttering your main workflow.

Imagine you're building a real estate chatbot to help users find properties or connect with agents. Instead of cramming everything in one workflow, you can use Subworkflows: one that will filter listings by budget and location, and another to gather additional user information, keeping the process modular and reusable.

With the Vellum Workflow builder, your team can easily:

  • Create reusable Subworkflows that integrate into different workflows
  • Leverage version control to track updates or pin to static, stable versions
  • Safely reuse components without messing with the parent workflow’s logic
  • Simplify collaboration between developers, SMEs and PMs

Benefits for your organization

There are a few benefits from using modular components in your AI workflows.

For developers: Simplified debugging & versioning

With subworkflows, you’ll simplify your development process by breaking down complex AI systems into smaller, manageable components, making debugging and iteration much easier. Reusing tools like API handlers or parsers across workflows saves time and reduces duplication—you build them once and use them anywhere.

Inspired by software package management systems like PyPI and npm, Vellum lets you cut and tag releases for your SubWorkflows. Each version is tagged so you can pin to a version or automatically use the latest version of your subworkflow (tool).

Release details and other deployment info for a Q&A chatbot built in Vellum

For SMEs: More control

Subworkflows help you ensure that business logic and requirements are consistently applied across workflows. With pinned versions, you’ll have peace of mind knowing critical logic remains stable and won’t change unexpectedly.

For PMs: Clarity and speed

Subworkflows keep workflows organized and clear, letting you focus on delivering great user outcomes. Reusable tools and versioning enable faster, more reliable feature rollouts, with full participation from the product team throughout the process.

See It in Action

We used Vellum’s Workflow builder to build an SEO agent that has 4 tools (subworkflows) for things like keyword research, content analysis, content generation, and evaluation.

Read how we built it here and/or try the quick demo here.

Preview of an SEO agent built with 4 different tools (Subworkflows)

Try Vellum Workflows today

With Vellum’s Subworkflow nodes, you can simplify complex workflows—whether you’re keeping things organized, building reusable tools, or managing updates with version control.

If your team wants to try out Vellum’s tool (subworkflow) support and our Workflow builder, now’s the perfect time to explore how this flexibility can support your projects. Contact us on this link and we’ll have one of our AI experts help you setup your project.

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
Nov 27, 2024
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.
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

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

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

PDF Data Extraction to CSV
Extract unstructured data (PDF) into a structured format (CSV).
Legal contract review AI agent
Asses legal contracts and check for required classes, asses risk and generate report.

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

Synthetic Dataset Generator
Generate a synthetic dataset for testing your AI engineered logic.
SOAP Note Generation Agent
Extract subjective and objective info, assess and output a treatment plan.

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

Build AI agents in minutes

Agent that summarizes lengthy reports (PDF -> Summary)
Summarize all kinds of PDFs into easily digestible summaries.
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.
Trust Center RAG Chatbot
Read from a vector database, and instantly answer questions about your security policies.
Legal document processing agent
Process long and complex legal documents and generate legal research memorandum.
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.