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

How Coursemojo Sped Up AI Delivery by 6+ Months

Learn how Coursemojo uses Vellum to unlock engineering productivity and deploy AI-powered edTech solutions faster.

5 min
Written by
Reviewed by
No items found.

Coursemojo is an education technology company using AI to empower both teachers and students in the classroom. For students, an AI teaching assistant Mojo delivers “conversational worksheets” that provide hints, scaffolding, and context to guide them toward answers without giving solutions away or going off-topic. For teachers, Mojo transforms existing assignments into interactive, curriculum-aligned activities that enable real-time insights that better support student learning.

With the help of Vellum, Coursemojo was able to save over 6+ months of engineering time while rapidly scaling from serving ~7,000 students last year to 60,000+ students and growing today.

We sat down with Jamie, CTO at Coursemojo, to hear how their team uses Vellum to build, evaluate, and deploy Mojo with particular assurance that material is accurate, information dense, and secure from being derailed.

The Challenge: Build or Buy?

Coursemojo’s engineering team began building an internal solution to power and iterate on Mojo, but as complexity grew, the bottlenecks became clear:

  • Engineering drain: Most of developers' time would be spent iterating and maintaining infrastructure instead of improving the student and teacher experience.
  • No evaluations & insights: Their solution lacked an evaluation system to test and validate prompt/workflow updates before production.
  • Non-technical lockout: Educators and content teams had no way to create or refine workflows without heavy engineering support.

When evaluating whether to continue building in house or build with Vellum, the answer was clear.

When we saw Vellum, we realized we could turn this on today and essentially leapfrog six months of software development or more — Jamie Forrest, CTO, Coursemojo

TLDR;

Result Detail
Activities scaled 2,000+ new Mojo curriculum activities (vs. 200 last year before Vellum)
Student reach 7,000 → 60,000+ students in under a year
Engineering time saved 6+ months
Non-technical enablement Teams outside engineering now own AI workflow creation
Learning outcomes 8% higher end-of-year exam scores for Mojo users vs. students who don’t use Mojo (WSMV4)

Goal: Building GenAI solutions fast and reliably

Coursemojo needed a platform that enabled building and collaborative iteration on Mojo, without creating overhead for engineers. This is what they set out to do on Vellum:

  • Build & orchestrate AI workflows that could generate curriculum-aligned activities and teacher insights, with guardrails to prevent students from taking the AI off-topic or into inappropriate territory.
  • Evaluate prompts, workflows, and content changes before production to catch regressions and handle edge cases.
  • Reliably deploy updates and new workflows at scale without introducing regressions or compromising quality.
  • Deploy updates instantly without requiring engineering redeploys or downtime.
  • Enable cross-team collaboration so technical and non-technical contributors could work within the same AI workflow environment.

The Solution

Several teams at Coursemojo work within Vellum to build, test, and refine AI workflows, with each contributing in different ways to keep iteration fast and effective.

  • Transformation team: Specialists who bridge educators and engineers by handling prompt engineering, workflow creation, and bulk updates.
  • QA team: A team that uses Vellum’s evaluation tools to test prompt changes, catch regressions, and address edge cases before deployment.
  • Engineering team: Provides orchestration support and debugging when needed, while staying out of daily workflow iteration.

Here are the solutions that enabled the transformation team to use Vellum for rapid iteration in turning curriculum materials into AI workflows.

1/ Orchestrate AI workflows visually

Vellum’s visual environment lets the team build complex AI workflows, run them in parallel, and merge outputs all without backend coding. This made it possible to easily build and orchestrate multi-step AI solutions for both students and teachers, complete with guardrails to keep interactions on-topic and age-appropriate.

When I first saw Vellum, it was clear that it was exactly what we were building, only much further ahead and ready to use today.
-
Jamie

2/ Evaluation tooling to catch regressions and edge cases

Before Vellum, any time the team wanted to adjust a prompt, they had no reliable way of knowing how the change would affect the student experience. Even small tweaks introduced risk in breaking the flow of activities.

Vellum’s evaluation and observability tools gave Coursemojo a structured way to test prompt changes, compare outputs, and identify regressions or problematic edge cases before deployment.

If we ever wanted to change anything , we had zero insight into how that would affect the experience…so, that was one of the things Vellum solved for us. We got evals out of the box.

3/ Instant, code-free prompt deployment

By managing prompts directly in Vellum, updates can be pushed live without a full engineering redeploy. This eliminates a major iteration bottleneck and frees developers to focus on core product improvements.

All the extra engineering overhead, coming from time spent tweaking workflows, is gone from using Vellum.
-
Jamie

4/ Eliminate engineering bottlenecks

With Vellum’s drag-and-drop interface, non-technical staff now own workflow creation and iteration. Engineers step in only for complex debugging, significantly accelerating iteration speed.

Vellum is now empowering our non-technical users to build these workflows themselves, it’s no longer an engineering task to build and manage our workflows. As a result we saved 6+ months of engineering time so far. - Jamie

The Results

With Vellum, Coursemojo was able to push beyond AI pilots and has a reliable AI solution in production. With Vellum’s help they have achieved amazing progress: 

  • 6+ months of engineering time saved by relying on Vellum’s infra instead of building in-house
  • 10x growth in students served (7,000 → 60,000) without expanding engineering team
  • 2,000+ new activities launched for the new school year
  • 8% higher end-of-year exam scores for students using Coursemojo vs. non-users (WSMV4)

These results show how Vellum gave Coursemojo the speed, scale, and flexibility to deliver thousands of safe, curriculum-aligned AI activities without expanding headcount or development overhead.

Last year, we served around 7,000 students, and this year we're at 60,000 students and growing. Vellum is supporting the 10x growth in curricula.
-
Jamie

Eliminate engineering bottlenecks with Vellum

Vellum is proud to support Coursemojo in transforming classrooms nationwide by providing an all in one platform that eliminates engineering overhead and empowers teams to build, test, and deploy AI powered activities at scale.

If you want to give your teams the ability to iterate faster, maintain quality, and collaborate seamlessly on AI features, we can help.

Book a demo with us and discover how Vellum’s suite of products can help you develop, evaluate, and continuously improve the AI capabilities that power your product.

ABOUT THE AUTHOR
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.

ABOUT THE reviewer

No items found.
lAST UPDATED
Sep 9, 2025
EdTech
share post
Expert verified
EdTech
Related Posts
Product Updates
October 1, 2025
7
Vellum Product Update | September
Guides
September 30, 2025
15
A practical guide to AI automation
LLM basics
September 25, 2025
8 min
Top Low-code AI Agent Platforms for Product Managers
LLM basics
September 25, 2025
8 min
The Best AI Agent Frameworks For Developers
Product Updates
September 24, 2025
7 min
Introducing AI Apps: A new interface to interact with AI workflows
LLM basics
September 18, 2025
7 min
Top 11 low‑code AI workflow automation tools
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
Personalized healthcare explanations of a patient-doctor match

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

Start with some of these insurance examples

AI agent for claims review and error detection
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

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.

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).

Dynamic template box for Supply Chain/Logistics, Use {{supply}}

Start with some of these supply chain examples

Risk assessment agent for supply chain operations

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.

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

Start with some of these agents

Automated Code Review Comment Generator for GitHub PRs
Personalized healthcare explanations of a patient-doctor match

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

Build AI agents in minutes

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.
PDF Data Extraction to CSV
Extract unstructured data (PDF) into a structured format (CSV).
Competitor research agent
Scrape relevant case studies from competitors and extract ICP details.
E-commerce shopping agent
SOAP Note Generation Agent

Build AI agents in minutes for

{{industry_name}}

Competitor research agent
Scrape relevant case studies from competitors and extract ICP details.
AI agent for claims review and error detection
E-commerce shopping agent
Retail pricing optimizer agent
Analyze product data and market conditions and recommend pricing strategies.
Risk assessment agent for supply chain operations
Insurance claims automation agent
Collect and analyze claim information, assess risk and verify policy details.

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.