This guide helps you maximize your AI assistant by structuring requests for maximum effectiveness. The Naro agent functions as a skilled analyst capable of searching organizational knowledge, identifying patterns, and creating compelling content.
Vague requests like "analyze our calls" won't unlock the agent's full potential. Structured requests generate actionable insights and high-quality outputs.
What the Agent Can Access
The agent draws from six primary data sources:
- Sales calls: Recorded conversations with transcripts and participant details
- Customer insights (artifacts): Pain points, objections, questions, use cases, success stories, feature requests, competitor mentions
- Content library: Educational materials, sales assets, multimedia, research
- Sales insights: Reusable facts extracted from conversations
- Content briefs: Planning documents for upcoming content
- Content scoring: Artifacts scored 0–4 based on existing content coverage
Core Capabilities
The agent can find and search across sources, organize and group findings, conduct web research, analyze trends and gaps, summarize data, draft content, and identify strategic insights.
Effective Prompting Patterns
The optimal structure: Gather → Organize → Analyze → Create
Pattern 1: Find, Cluster, and Analyze "Find all customer pain points from the last month, cluster them into themes, and provide a summary of each theme with recommendations for our product team."
Pattern 2: Research and Create Content "Search for security-related objections from the last quarter, cluster them by specific concern, extract key quotes from each cluster, then help me draft a security FAQ that addresses the top concerns."
Pattern 3: Assess and Improve "Find all use cases mentioned by enterprise customers in the last 3 months and assess how well our current content supports them. Focus on identifying the biggest gaps we need to fill."
Pattern 4: Competitive Intelligence "Find all competitor mentions from the last two months, cluster them by competitor and topic discussed, then create a competitive battle card highlighting our advantages for each main competitor."
Pattern 5: Time-Based Analysis "Compare customer objections from Q1 versus Q2. Show me what new objections emerged, which ones disappeared, and how the frequency changed. Create a trend report with recommendations."
Tips for Better Results
Be specific about outputs
- No: "Analyze our content"
- Yes: "Find all product demo videos, assess how well they address common technical questions, and create a plan for new demo content that fills the gaps"
Use time frames
- No: "Find customer feedback"
- Yes: "Find all customer pain points from the last 30 days"
Chain actions together
- No: "What do customers think?"
- Yes: "Find customer objections from last quarter, cluster them by theme, summarize the top 3 clusters, and draft email responses for each"
Power Words That Help
- Cluster — groups similar items into themes
- Assess — evaluates content coverage and identifies gaps
- Extract quotes — pulls actual customer language
- Draft — creates new content based on findings
- Compare — analyzes differences between groups or time periods
- For each — applies the requested task to each source individually
Getting Started
Three foundational patterns:
- Basic: "Find [what] from [when], cluster by [method], and summarize each cluster"
- Analysis: "Find [what] from [when], cluster by [method], analyze [specific aspect], and create [output]"
- Content Creation: "Find [what] from [when], cluster by [method], extract [evidence], and draft [content type]"
The agent performs best with specific requests about what to find, how to organize it, what analysis is needed, and what output is expected.