Page Inspect

Vellum AI | Build agents in plain English

- Products

Orchestration

SDK

Evaluations

Retrieval

Deployment

Observability
- Solutions

Healthcare

Retail

Supply chain

Insurance

Government
- Resources

Resources

News

Blog

Leaderboards

Webinars

GPT-5 Playbook

Customer Spotlights

Case Studies

Use Cases

latest case study
- Platform

Products

Orchestration

SDK

Evaluations

Retrieval

Deployment

Observability

Solutions

Enterprise

Healthcare

Retail

Supply chain

Insurance

Government
- Pricing
- Docs
- Careers

Request Demo

Get Started

Upload JSON File

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

# The fastest way to build AI agents

Create agents by chatting with AI, low-code, or code

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Customer support

Marketing

Sales

Healthcare

Legal tech

Financial services

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Customer support

Create a customer support chatbot that classifies each user message into one of four categories: Billing & Payments, Product Help, Account Management, or Escalation. For the first three, reply using information from my support knowledge database. For Escalation use an Agent Node to send a Slack message in #triage-user-messages saying “user has requested \[summary of issue\]” and tell the user that a human will follow up soon.

Customer support chatbot

Create a customer support chatbot that classifies each user message into one of four categories: Billing & Payments, Product Help, Account Management, or Escalation. For the first three, reply using information from my support knowledge database. For Escalation use an Agent Node to send a Slack message in #triage-user-messages saying “user has requested \[summary of issue\]” and tell the user that a human will follow up soon.

Preview prompt

Sales

Create an agent that reviews all deals marked as “Closed Lost” in HubSpot for the week.
• Extract key details: deal size, loss reason, competitor, and stage lost.
• Identify recurring themes or reasons (e.g., pricing, missing feature).
• Summarize findings in a Slack or Notion update for the Sales and Product teams every Friday.

Closed lost review

Create an agent that reviews all deals marked as “Closed Lost” in HubSpot for the week.
• Extract key details: deal size, loss reason, competitor, and stage lost.
• Identify recurring themes or reasons (e.g., pricing, missing feature).
• Summarize findings in a Slack or Notion update for the Sales and Product teams every Friday.

Preview prompt

Sales

Create an agent that gives a weekly update on active deals in Hubspot, summary consisting: of size of deal, last communication, % likelihood, next activity date etc.Ranks Green, Yellow, Red dealsWraps up any past close date deals (Red). Prompts user to either move close date or change to close lost with reason.

Pipeline review

Create an agent that gives a weekly update on active deals in Hubspot, summary consisting: of size of deal, last communication, % likelihood, next activity date etc.Ranks Green, Yellow, Red dealsWraps up any past close date deals (Red). Prompts user to either move close date or change to close lost with reason.

Preview prompt

Sales

Create an agent that takes in call transcript and customer email address as text, extracts objections, and updates the associated HubSpot contact record.If a field for objections doesn't exist then create one.

Call insights

Create an agent that takes in call transcript and customer email address as text, extracts objections, and updates the associated HubSpot contact record.If a field for objections doesn't exist then create one.

Preview prompt

Marketing

Create an agent that takes a webinar transcript as text input. It should extract the main themes, do light web research for supporting stats, and generate 3 LinkedIn posts, 1 blog outline, and a Slack summary draft.

Content generation

Create an agent that takes a webinar transcript as text input. It should extract the main themes, do light web research for supporting stats, and generate 3 LinkedIn posts, 1 blog outline, and a Slack summary draft.

Preview prompt

Marketing

Create an agent to analyze the earnings calls of software companies and quickly turn those into content that I can share with my network that adds valuable insights.The input would be the transcript of the earnings call.
The agent should find the most interesting highlights from the earnings call, whether quantitative or qualitative, summarize, and output a 4 or 5 slide brief to automatically create a presentation.

Market research

Create an agent to analyze the earnings calls of software companies and quickly turn those into content that I can share with my network that adds valuable insights.The input would be the transcript of the earnings call.
The agent should find the most interesting highlights from the earnings call, whether quantitative or qualitative, summarize, and output a 4 or 5 slide brief to automatically create a presentation.

Preview prompt

Marketing

Create an agent that helps with creative writing. I will provide a web url & the desired output. Output could be a blog, poem, Slack message. Once the agent has the web url it should extract the main themes from the url. Then use the main themes to do web research with LLM's native capabilities. Use web research and the document to come up with the output

Creative writing

Create an agent that helps with creative writing. I will provide a web url & the desired output. Output could be a blog, poem, Slack message. Once the agent has the web url it should extract the main themes from the url. Then use the main themes to do web research with LLM's native capabilities. Use web research and the document to come up with the output

Preview prompt

Legal tech

Create an agent that checks data processing agreements (DPAs) or privacy policies for compliance with GDPR, CCPA, and other frameworks.
• Parse documents and extract references to key obligations (data retention, subprocessor lists, breach notification).
• Compare coverage against a compliance checklist.
• Output a compliance score, missing elements, and action recommendations.

Privacy compliance reviewer

Create an agent that checks data processing agreements (DPAs) or privacy policies for compliance with GDPR, CCPA, and other frameworks.
• Parse documents and extract references to key obligations (data retention, subprocessor lists, breach notification).
• Compare coverage against a compliance checklist.
• Output a compliance score, missing elements, and action recommendations.

Preview prompt

Legal tech

Create an agent that reviews NDAs (Mutual or One-Way) and highlights deviations from standard terms.
• Extract clauses around confidentiality period, exclusions, governing law, and IP ownership.
• Compare each clause to a company-approved template.
• Generate a summary of differences and a risk assessment (Low / Medium / High).
• Output a short summary in Slack and a detailed Markdown review.

NDA reviewer

Create an agent that reviews NDAs (Mutual or One-Way) and highlights deviations from standard terms.
• Extract clauses around confidentiality period, exclusions, governing law, and IP ownership.
• Compare each clause to a company-approved template.
• Generate a summary of differences and a risk assessment (Low / Medium / High).
• Output a short summary in Slack and a detailed Markdown review.

Preview prompt

Legal tech

Create an agent that reviews legal contracts against a checklist and generates risk assessments with lawyer-friendly summaries.
‍
• **Inputs:**
\- Contract PDFs
\- Review checklist document
\- Risk profile (Low / Medium / High)

• **Workflow:**

1\. **ParseDocs:** Extract sections from contracts and checklist items into structured JSON.
2\. **ClauseCheck (GPT-4.1):** Compare contract clauses to checklist items, flag missing or concerning language, and summarize findings.
3\. **RiskAssessment (GPT-4.1):** Score each flagged issue based on the provided risk profile, categorize risks (legal, financial, compliance), and propose mitigations.
4\. **Summary (GPT-4.1):** Generate a professional legal memorandum including:
\- Executive summary and risk overview
- Clause-level redline recommendations (CHANGE FROM / TO format)
\- Negotiation strategy and approval guidance

• **Outputs:**

\- flagged\_issues: structured JSON risk assessment
\- review\_summary: Markdown-formatted legal summary

Contract assessment

Create an agent that reviews legal contracts against a checklist and generates risk assessments with lawyer-friendly summaries.
‍
• **Inputs:**
\- Contract PDFs
\- Review checklist document
\- Risk profile (Low / Medium / High)

• **Workflow:**

1\. **ParseDocs:** Extract sections from contracts and checklist items into structured JSON.
2\. **ClauseCheck (GPT-4.1):** Compare contract clauses to checklist items, flag missing or concerning language, and summarize findings.
3\. **RiskAssessment (GPT-4.1):** Score each flagged issue based on the provided risk profile, categorize risks (legal, financial, compliance), and propose mitigations.
4\. **Summary (GPT-4.1):** Generate a professional legal memorandum including:
\- Executive summary and risk overview
- Clause-level redline recommendations (CHANGE FROM / TO format)
\- Negotiation strategy and approval guidance

• **Outputs:**

\- flagged\_issues: structured JSON risk assessment
\- review\_summary: Markdown-formatted legal summary

Preview prompt

Healthcare

Create an agent that generates personalized care plans from EHR data and clinical guidelines.
• Parse diagnosis codes, medications, and lab results.
• Recommend care steps, goals, and follow-up intervals.
• Format in clinician-friendly Markdown for EHR entry.

Care plan generator

Create an agent that generates personalized care plans from EHR data and clinical guidelines.
• Parse diagnosis codes, medications, and lab results.
• Recommend care steps, goals, and follow-up intervals.
• Format in clinician-friendly Markdown for EHR entry.

Preview prompt

Healthcare

Create an agent that reviews claim submissions for policy compliance and error detection.
• Cross-check diagnosis, procedure, and modifier codes against payer rules.
• Identify duplicates, invalid codes, or unbundling issues.
• Recommend adjustments or rejections with explanations.

Claims adjudication

Create an agent that reviews claim submissions for policy compliance and error detection.
• Cross-check diagnosis, procedure, and modifier codes against payer rules.
• Identify duplicates, invalid codes, or unbundling issues.
• Recommend adjustments or rejections with explanations.

Preview prompt

Healthcare

**Create a prior authorization review agent that:
‍**• Accepts 3 documents (clinical notes, codes, medical necessity forms) and plan criteria
• Extracts text from documents (GPT-5 requires text, not files)
• Uses agent tools to parse notes, extract codes, check coverage, and identify missing docs
• Outputs structured JSON summary with coverage determination, missing items, and recommendations

Prior authorization

**Create a prior authorization review agent that:
‍**• Accepts 3 documents (clinical notes, codes, medical necessity forms) and plan criteria
• Extracts text from documents (GPT-5 requires text, not files)
• Uses agent tools to parse notes, extract codes, check coverage, and identify missing docs
• Outputs structured JSON summary with coverage determination, missing items, and recommendations

Preview prompt

Financial services

Create an agent that compiles a weekly summary of each client’s investment portfolio.
• Pull holdings, performance, and benchmark data from a PDF file upload that I will provide as input
• Highlight top-performing assets, risk exposure, and allocation drift.
• Generate personalized Markdown summaries for advisors to share with clients.

Wealth management summary

Create an agent that compiles a weekly summary of each client’s investment portfolio.
• Pull holdings, performance, and benchmark data from a PDF file upload that I will provide as input
• Highlight top-performing assets, risk exposure, and allocation drift.
• Generate personalized Markdown summaries for advisors to share with clients.

Preview prompt

Financial services

Create an agent that automates “Know Your Customer” (KYC) checks.
• Take customer-uploaded documents as inputs (ID, proof of address, corporate certificates).
• Verify document validity, completeness, and expiry.
• Flag missing or inconsistent information and recommend follow-up actions.
• Output a compliance summary

KYC reviewer

Create an agent that automates “Know Your Customer” (KYC) checks.
• Take customer-uploaded documents as inputs (ID, proof of address, corporate certificates).
• Verify document validity, completeness, and expiry.
• Flag missing or inconsistent information and recommend follow-up actions.
• Output a compliance summary

Preview prompt

Financial services

Create an agent that analyzes transaction patterns to identify potential fraud.
• Pull recent transactions from a PDF file upload that I’m going to provide as input
• Build Agent node with tools that will detect anomalies using rule-based and LLM pattern recognition (e.g., velocity, unusual merchant, location mismatch).
• Summarize flagged cases in Slack #triage-user-messages with supporting evidence.
• Generate JSON output for fraud operations dashboards.

Fraud detection assistant

Create an agent that analyzes transaction patterns to identify potential fraud.
• Pull recent transactions from a PDF file upload that I’m going to provide as input
• Build Agent node with tools that will detect anomalies using rule-based and LLM pattern recognition (e.g., velocity, unusual merchant, location mismatch).
• Summarize flagged cases in Slack #triage-user-messages with supporting evidence.
• Generate JSON output for fraud operations dashboards.

Preview prompt

Customer support

Create an agent that detects when a support ticket is escalated (e.g., repeated follow-ups or high urgency).
‍
\- Summarizes the full context and previous correspondence.
\- Assigns it to the correct engineer in Linear and posts a summary to the #internal-support-triage channel.

Escalation assistant

Create an agent that detects when a support ticket is escalated (e.g., repeated follow-ups or high urgency).
‍
\- Summarizes the full context and previous correspondence.
\- Assigns it to the correct engineer in Linear and posts a summary to the #internal-support-triage channel.

Preview prompt

Customer support

Create an agent that scans HubSpot for deals with upcoming renewal dates in the next 60 days. Rank customers by renewal risk (High, Medium, Low) based on communication recency, usage metrics, and deal notes. Send a weekly renewal risk summary to the account owner with action recommendations (e.g., “Schedule QBR,” “Share new feature update”). Send this summary to a slack channel ID that the user provides as input

Renewal tracker

Create an agent that scans HubSpot for deals with upcoming renewal dates in the next 60 days. Rank customers by renewal risk (High, Medium, Low) based on communication recency, usage metrics, and deal notes. Send a weekly renewal risk summary to the account owner with action recommendations (e.g., “Schedule QBR,” “Share new feature update”). Send this summary to a slack channel ID that the user provides as input

Preview prompt

No Prompts Found

Trusted by

Trusted by product-led companies, global enterprises & major service providers

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

Case Study

## Build agents in plain English

Talk to Vellum like you're briefing a teammate. Describe even your most complex agent requirements, and it automatically builds the workflow logic, tools, and integrations ready for you to review and refine.

## Full agent visibility

Use the sandbox console to test as you build and catch issues before users see them. After launch, review real conversations to see where your agent succeeds and where it needs work.

## Ship it your way

Embed in your app: Get the SDK code or connect via API to integrate it directly into your product.

Share with your team: Publish internally so anyone can access and run it instantly.

Share with users: Publish your app with 1 click for users to interact with

ENTERPRISE

## **Deploy AI agents at scale, securely**

Built-in evals and monitoring to ensure quality

Share and manage agents across teams

SOC 2 Type 2, HIPAA, with VPC and on-prem options

See Enterprise Features

## Your first agent is seconds away.

Start prompting

RESOURCES

- Case Studies
- Reasoning models
- Guides
- Product Updates
- Model Comparison
- Documentation
- LLM Leaderboard
- Free Tools
- Newsletter
- Use Cases

PRODUCTS

- Prompt Engineering
- Document Retrieval
- Orchestration
- evaluations
- Deployments
- Monitoring
- SDK

COMPANY

- Blog
- Careers
- Contact Us

Affiliate program rules

Terms of Use

Privacy Policy

SOCIALS

- LinkedIn
- Twitter
- Youtube