AI-Engineer-Foundation / agent-protocol

Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.

Home Page:https://agentprotocol.ai

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Example scenarios in documentation

nalbion opened this issue · comments

It would be useful to have examples of various scenarios included in the documentation:

  • Write Washington to a text file (end of task in one line)
  • Create a chat app (user begins conversation)
  • Agent starts with "Hi, would you like to book a flight or accommodation?" (#63)
  • GitHub action triggers a new task, sends Issue title (and body & comments? ) as input, agent does some tasks synchronously, also waits for user response through Slack
  • Optional additional_input/config used to provide auth token, model name, task/step type...

...I'm really curious to see how the "Write Washington to a text file (end of task in one line)" scenario would be implemented.

  • Is "Write Washington to a text file (end of task in one line)" the input for Task or Step?
  • If for Task, how can the agent provide a response message "Ok, the file has been created"?

It would be create to have a "hello world"-like example too. An Echo-example for example.

It would be create to have a "hello world"-like example too. An Echo-example for example.

The example for the Python SDK (here https://github.com/AI-Engineers-Foundation/agent-protocol-sdk-python/blob/main/examples/minimal.py) is essentially an echo example.

I think some more examples would be good to have. And if anybody creates working examples, it would be great to add them to the docs as a reference!

Lemme take a stab at creating some examples. Will update here.