Back to Prompt Library
implementation

Integrate Fixie for Voice Input/Output

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Ethics Compliance Agent for Financial Market Analysis

Format
Code-aware
Lines
14
Sections
1
Linked challenge
Ethics Compliance Agent for Financial Market Analysis

Prompt source

Original prompt text with formatting preserved for inspection.

14 lines
1 sections
No variables
1 code block
Enhance the 'Financial Analyst' agent to accept voice input via Fixie and provide voice output. Design a simple webhook or API endpoint that translates Fixie's speech-to-text output into the AutoGen agent's input, and converts the agent's textual response back to speech for Fixie's output. Ensure the voice interface clearly communicates compliance findings and asks clarifying questions when needed.
```python
# This example is conceptual; actual Fixie integration will depend on its SDK/API for webhooks or direct calls. # Pseudo-code for a Fixie agent backend service
# from fixie_sdk import Agent, Message
# from autogen import UserProxyAgent, AssistantAgent, GroupChat, GroupChatManager # Assuming autogen setup from previous step (manager, financial_analyst etc.) # class FixieAutoGenBridge(Agent):
# def handle_message(self, message: Message):
# user_input_text = message.text # # Initiate or continue chat with AutoGen
# # This would typically involve a persistent session management for AutoGen
# # For simplicity, we'll mock interaction:
# autogen_response = financial_analyst.initiate_chat(manager, message=user_input_text)
# # In a real scenario, you'd feed the output of the manager into the Fixie response # # Convert AutoGen's final response to speech (Fixie handles text-to-speech inherently)
# final_agent_message = autogen_response.messages[-1]['content'] # Get last message
# return Message(text=final_agent_message) # To run this, you would typically deploy the FixieAutoGenBridge as a Fixie Agent.
```

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.