Step01
Ingest Unstructured Data
Aggregate all your unstructured business data from various sources, such as support tickets, GitHub PRs, user conversations from your app, and Linear tickets.
AdvancedProduct
How to Build a Multi-Model AI Product Insights Engine
Create a powerful product insights engine by combining Jev with other LLMs. Use Jev for large-scale classification of customer feedback and development data, then apply reasoning models to analyze the structured output for deep insights.
Before you start
Tools used
- JevVisitJev
TypeSafe AI’s model for fast structured decisions, including choices, scores, and boolean probabilities.
- CodexVisitCodex
OpenAI's cloud-based AI software engineering agent that can execute code, run tests, and handle complex multi-file tasks autonomously.
Step by step
The workflow
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Step02
Classify and Cluster with Jev
Use Jev to perform large-scale classification and pairwise groupings on the raw data. This organizes the messy, unstructured signals into structured groups.
Jev's low cost and high speed make it ideal for this heavy-lifting classification stage, which would be too expensive with larger models.
Step03
Analyze Clusters with a Reasoning Model
Pass the structured groups created by Jev to a powerful reasoning model like Astra. Ask high-level questions to understand patterns, trends, and connections across the data.
Example prompt
What the heck's going on across all of this?
Step04
Generate Summaries with a Creative Model
Use a creative model, like Sol or Luna, to generate user-friendly summaries, reports, or text based on the analysis from the reasoning model. This is the final step for creating human-readable output.
Build your next product with ChatPRD
Turn an idea into a PRD, user stories, and a plan.
Keep building
Related workflows
intermediateContentJev
How to Analyze YouTube Comments for Audience Insights with AI
Quickly analyze thousands of YouTube comments for sentiment and new content ideas using the Jev AI model. This workflow helps creators turn audience feedback into actionable insights for their content strategy.
Open
intermediateEngineeringJevCodex+1
How to Analyze GitHub PRs to Understand Engineering Effort with AI
Use the Jev AI model to cheaply and quickly cluster thousands of GitHub pull requests into thematic areas. This helps engineering and product leaders understand the breakdown of work between new features, tech debt, and maintenance.
Open
beginnerDesignCodex
How to Generate Unique and Usable SVG Icons with AI
Go beyond generic icon libraries by prompting an AI model to create custom, characterful SVG icons. This workflow shows how to get unique, well-designed icons for your projects by providing simple, clear descriptions.
Open
Start shipping
better products.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.
Free to start
No credit card
SOC 2 certified
Enterprise ready