Kade Heyborne
48c6ddc066
- Complete planning documentation for 5-phase development - UI design specifications and integration - Domain architecture and directory templates - Technical specifications and requirements - Knowledge incorporation strategies - Dana language reference and integration notes
1.6 KiB
1.6 KiB
These following rules are various points that I want to ensure make it into the end project
- Privacy
- Local directories for user's knowledge ensuring they keep all data for themselves
- Usage of private locally ran models, capable and viable due to proper context engineering
- Useful for anyone
- System designed for accelerating user's goals based on their current understanding
- System should have a proper ingestion/setup process & also should debrief the user daily
- No goal should be too big nor too small.
- All domains should be able to gather and utilize the highest level of information about the subject as possible
- Automated research engine
- Automated ingestion engine
- Automated expert agent improvements from data
- Each different domain of knowledge is fully contained within a directory for that domain
- These directories are further enhanced with: A). Sub-agents B). Skills/Rules/System Prompt C). Workflows / Tools / Functions D). An expert chat UI per domain E). Raw data (docs/transcripts/pdf/etc) F). Processed data (fabric extractions, personal notes, etc.)
- Each expert domain is 'agent as a tool'
- All information should be properly rated and fact checked for optimal truth
- Information between the user's personal knowledge and the wider knowledge of the world should be intertwined*
- This process should constantly be guiding the user towards a new subject they should study or pursue applying
- System should be neuro-symbolic Need to refine exactly how to use weighted data and context engineering properly