Goal
How does the chunking workflow differ from Model Customization to RAG? What would an MVP experience look like for both?

Problem statement
We want to make this process feel intuitive and supportive by:

• Breaking the task down into clear, manageable steps
• Providing helpful examples and tips along the way
• Reminding them of the real-world use case their work is supporting
• Making it easy to edit, retry
• Helping them feel confident that what they’re doing is correct and impactful

Acceptance Criteria

• We should look at the experience beyond just day 0 (re-try, update, etc.)
• Based on Maria’s current mocks for model customization, how difficult would it be to implement? Let’s work with Shabana on understanding that.
• Work with Anastas to review current chunking experience (chunk a bunch of docs and see what we get)
• Identify what do good chunks and bad chunks look like? Ex of a “Bad chunk”- sentence getting cut off.

Resources

Deliverables