Turn your own tasting notes into a reusable preference profile, then use that profile to narrow a restaurant wine list by fit, value, and confidence instead of asking for generic recommendations.
Source episode · 51:00
How I AI: Chintan Turakhia’s Playbook for AI Adoption at Coinbasewith Claire Vo
Chintan photographs handwritten Champagne notes, asks ChatGPT to infer his taste profile, then gives it a restaurant wine list for value picks, splurges, and bottles to avoid.
A source-grounded taste profile plus a short list of menu recommendations with prices, fit, value, and uncertainty.
OpenAI conversational AI
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Photograph tasting notes with ratings, memorable phrases, producer names, and clear contrasts between what you liked and disliked. Include enough examples to reveal patterns rather than one favorite bottle.
You can upload multiple images at once to provide the AI with a comprehensive view of your tasting history.
Have ChatGPT transcribe the notes first, mark uncertain readings, then infer a profile with supporting examples and confidence. Correct the transcription before reusing the profile.
Transcribe these Champagne tasting notes and flag any producer, cuvée, vintage, rating, or word you cannot read confidently. Then infer my preferences across sweetness, acidity, age, producer style, grape, texture, and value. Cite the notes supporting each pattern, include dislikes and exceptions, and label confidence as high, medium, or low.
Photograph the complete restaurant wine list or upload its PDF. Include prices, vintage, producer, cuvée, region, bottle size, and any page needed to avoid evaluating an incomplete menu.
This also works with screenshots of online wine lists or PDF menus.
In the same conversation, ask for a short list grounded in the saved profile, meal, budget, and menu. Require exact menu names and prices plus a reason, confidence, and alternatives.
Using my taste profile and only the bottles visible on this wine list, what would I like? We are eating [meal], serving [party size], and want to spend about [budget]. Give me: best personal match, best value, crowd pleaser, adventurous pick, splurge, and bottles that are poor fits for my preferences. Quote the exact menu name and price for every recommendation and flag uncertain label readings.
Keeping this in the same chat is crucial, as the AI will use the context of your previously analyzed taste profile to make its recommendations.
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
Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.
Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.
Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.