List view
- Overdue by 2 month(s)•Due by April 8, 2025
- Overdue by 0 day(s)•Due by June 25, 2025•0/1 issues closed
- Overdue by 10 month(s)•Due by August 19, 2024
- Overdue by 1 year(s)•Due by October 6, 2023•1/1 issues closed
Launch traces and move out of experimental - [ ] website re-vamp - [ ] documentation - [ ] video tutorial - [ ] virtual workshop planning - [ ] press release
Overdue by 1 year(s)•Due by September 29, 2023•1/1 issues closed- Overdue by 1 year(s)•Due by September 6, 2023•1/1 issues closed
As an AI Engineer, I want to be able to understand how my generative application is running, specifically the parts (e.g. spans) that are running and the execution order. I want to be able to understand the parameters and the inputs / outputs of each span to uncover the black-box. As an AI Engineer, I want to know what my application bottlenecks are, particularly around timing and token usage, these values should be propagated and aggregated for me so that I can better understand the possible UX implications of my App is. Lastly, if certain components have exceptions, I want those surfaced early so I can correct them before I move my application to production. This is critical because it requires 0 infrastructure and because I don't have to worry about sending my data to a 3rd party.
Overdue by 1 year(s)•Due by September 15, 2023•4/4 issues closed