A space for anyone using Vellum to ask questions, share ideas, and learn how others are building and running AI in real work.
Create an agent that pulls product usage data from {{PostHog}} and account data from {{Salesforce}}, detects declining usage trends, flags at risk accounts ahead of renewal dates, and outputs a prioritized list with risk level and recommended next actions in {{Notion}}.
Create an agent that pulls {{Linear}} updates, PR statuses, and release notes, then generates a weekly team update with per person task summaries, posting it to {{Slack}} and saving a full report as a {{Notion}} page.
Create an agent that takes a keyword from a {{Google Sheets}} spreadsheet, searches the web for top-ranking articles using {{SerpAPI}}, scrapes key insights using {{Firecrawl}}, and generates a comprehensive, SEO-optimized article draft in {{Google Docs}}.
Create an agent that analyzes transaction patterns to identify potential fraud. Pull recent transactions from {{Stripe}}. Then build agent 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}}.
Create an agent that automates "Know Your Customer" (KYC) checks. Look at customer-uploaded documents in {{Hubspot}}. Verify document validity, completeness, and expiry. Flag missing or inconsistent information and recommend follow-up actions. Output a compliance summary and send a report via {{Gmail}}. Send a report to internal {{Slack}} channel (i will provide it).
Create an agent that compiles a weekly summary of each client’s investment portfolio. Pull holdings, performance, and benchmark data from a PDF. Then generate a summary for top performing assets, risk exposure and allocation drift. Using this summary generate a 5 page slide {{Gamma}} presentation. Send the slides to my clients (I'll provide their emails).
