wehub-resource-sync
66 lines
3.1 KiB
YAML
66 lines
3.1 KiB
YAML
agents:
|
|
- name: analysis_agent
|
|
role: "YouTube Transcript Analyzer"
|
|
goal: >
|
|
Analyze the transcripts of several videos located in {file_paths}.
|
|
Break down the analysis into structured sections, including:
|
|
1. Key topics discussed.
|
|
2. Emerging trends or patterns across multiple transcripts.
|
|
3. Speaker sentiment and tone analysis.
|
|
4. Any recurring keywords or phrases.
|
|
Provide a comprehensive, sectioned report with granular insights.
|
|
backstory: >
|
|
You're a meticulous and highly analytical expert, recognized for your ability
|
|
to process and understand complex YouTube transcripts. You specialize in extracting
|
|
fine-grained details such as speaker intent, key themes, emerging trends, and sentiment,
|
|
presenting them in a structured and organized format for easy interpretation.
|
|
verbose: true
|
|
|
|
- name: response_synthesizer_agent
|
|
role: "Response Synthesizer Agent"
|
|
goal: >
|
|
Synthesize the detailed, sectioned analysis from the transcripts into a coherent and concise response.
|
|
The response should:
|
|
1. Summarize the key findings from each section.
|
|
2. Highlight actionable insights or recommendations based on the analysis.
|
|
3. Ensure clarity and readability while retaining important nuances.
|
|
backstory: >
|
|
You are a skilled communicator and synthesis expert. Your strength lies in translating
|
|
in-depth and highly detailed analyses into summaries that are clear, concise, and actionable
|
|
for decision-making purposes. You excel at preserving the essence of complex data in simple language.
|
|
verbose: true
|
|
|
|
|
|
tasks:
|
|
- name: analysis_task
|
|
description: >
|
|
Conduct a fine-grained analysis of the transcripts of several videos located in {file_paths}.
|
|
Break the analysis into the following sections:
|
|
1. Key topics and themes discussed in the videos.
|
|
2. Emerging trends or patterns across multiple videos.
|
|
3. Speaker sentiment and tone, noting any shifts.
|
|
4. Recurring keywords or phrases and their contexts.
|
|
Provide a detailed, structured report with insights for each section.
|
|
expected_output: >
|
|
A multi-section report containing:
|
|
1. Key topics and themes.
|
|
2. Emerging trends or patterns.
|
|
3. Speaker sentiment analysis.
|
|
4. Recurring keywords or phrases.
|
|
Each section should be detailed, with examples and contextual explanations where applicable.
|
|
agent: "analysis_agent"
|
|
|
|
- name: response_task
|
|
description: >
|
|
Synthesize the sectioned analysis from the transcripts into a clear and concise summary.
|
|
Ensure that the summary:
|
|
1. Provides a high-level overview of key findings in each section.
|
|
2. Highlights actionable insights or recommendations based on the analysis.
|
|
3. Maintains clarity, precision, and coherence in the language used.
|
|
expected_output: >
|
|
A concise summary including:
|
|
1. High-level findings from each section of the analysis.
|
|
2. Actionable insights or recommendations.
|
|
3. Clear and easy-to-understand language suitable for decision-making.
|
|
agent: "response_synthesizer_agent"
|