Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Design] Add intro to the Prototype #69

Open
01painadam opened this issue Jan 3, 2025 · 3 comments
Open

[Design] Add intro to the Prototype #69

01painadam opened this issue Jan 3, 2025 · 3 comments
Assignees

Comments

@01painadam
Copy link
Collaborator

01painadam commented Jan 3, 2025

Goal(s)

  • Add a clear description of the prototype's capabilities to ground user expectations.
  • Add a few pre-canned prompt suggestions to guide the users on how to get started
  • Show available datasets, with links

e.g. "Hi! I’m Land & Carbon Lab’s alert explorer. I can help you find and investigate disturbances in your area of interest using the Land Disturbance Alert Classification System and other contextual data."

<surface dataset descriptions w/ links>

"To start, ask me about an area and types of alerts you are interested in."

Expected user prompts:

  • Show me alerts in natural grassland in the Cerrado.
  • How many disturbances to natural forests have there been in Colombia in the past month?
  • Show me recent alerts in Virunga National Park

User Stories & Acceptance Criteria

  • When I enter the prototype, I want to know its capabilities and available data, so that I understand what it can and cant do, and therefore what kinds of prompts are appropriate for me to input
    • Given [context], when [specific action], then [response or consequence to action]

Risks & Questions

  • How do we handle the user asking questions related to the intro? We need to ensure Zeno stays on track.

Solution Hints

  • This could be pre-canned as an initial LLM message?
  • Should it give an example prompt? could this be a CTA button "Show me an example prompt"
  • should the model have RAG access to metadata about its own tools and capabilities?

Future work

Relates to #82

@yellowcap
Copy link
Collaborator

Normally each agent has its own prompt text describing its prupose, and the LLM should be able to generate a description of its capabilities I think. Need to confirm this.

@01painadam 01painadam changed the title Add intro to the Prototype [FE] Add intro to the Prototype Jan 7, 2025
@01painadam
Copy link
Collaborator Author

Ok, once you confirm, we can provide some copy for a boilerplate landing module which gives a broad overview of the capabilities and suggests some prompts to get started with. Those can include asking the LLM about its agents.

@LanesGood could you put together a small design for this landing modal? I believe your initial wireframe moved in this direction already (it had an option to choose between the different prototypes). This would the next modal that explains this specific prototype

@01painadam 01painadam changed the title [FE] Add intro to the Prototype [FE][Design] Add intro to the Prototype Jan 9, 2025
@01painadam 01painadam changed the title [FE][Design] Add intro to the Prototype [Design] Add intro to the Prototype Jan 9, 2025
@LanesGood
Copy link
Collaborator

LanesGood commented Jan 9, 2025

@01painadam I've started working on the text for this here:
https://docs.google.com/document/d/1ddzvlwfW5fs_mBYAglxhjTiV5pdYMdBwwND111o_K5A/edit?usp=sharing

And a basic modal as per our initial wireframe designs:

Image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants