Use an AI agent with browsing capabilities to automate the tedious process of finding valuable, underpriced collectible cards on eBay, turning hours of manual search into an automated background task.
Source episode · 19:10
How Alessio Fanelli uses Open AI Symphony for Autonomous Coding and Pokémon Card Trading Workflowswith Claire Vo
From 19:10 to 24:16, Alessio Fanelli shows Codex comparing graded Pokémon card listings with market data to find potentially underpriced cards. Clip range: 19:10 to 24:16.
A report of potentially underpriced graded Pokémon card listings with pricing comparisons and listing URLs.
OpenAI's cloud-based AI software engineering agent that can execute code, run tests, and handle complex multi-file tasks autonomously.
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Instruct the agent to browse the web and build a target list of high-value graded cards. Provide a starting point, like an initial certificate number, and a constraint, such as a minimum price. The agent will use vision to read certificate numbers from card images and compile them into your database.
fill out the certificate number for every card that costs more than a thousand dollars.
Develop a custom skill that contains the agent's search logic for eBay. This function should include rules for comparing different grading systems and a method for batching requests to avoid being blocked by the site.
Use a prompt to activate the agent's custom eBay skill. The prompt should reference your target list and instruct the agent to start searching for underpriced cards on eBay.
use the eBay PSA premium. Let's find some underpriced cards from our premium list.
The agent autonomously navigates eBay, scraping prices for cards on its target list. It compares these prices against your reference data and flags significantly underpriced listings in a report. You make the final purchasing decision based on the agent's findings.
For each underpriced card you identified, create a summary. The output should be a markdown table with columns for Card Name, Grade, eBay Listing URL, Current Price, and Estimated Market Value. Add a final column calculating the percentage difference between the current price and market value. Here is the data you collected: [paste collected data]
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
A guide for solo entrepreneurs to manage business operations using AI. Learn how to source manufacturers, build and maintain an e-commerce site, and replace dashboards with voice commands, all without a human team.
Turn a complex, artistic concept into a manufacturable 3D model. This workflow shows how to use AI to generate a design from a photo and then create CAD files for 3D printing, even for previously 'unmanufacturable' items.
Learn to translate fashion sketches into a full suite of marketing visuals. This workflow covers creating a detailed design spec, generating a core product photo with AI, and iterating for different contexts like runway and influencer shots.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.