Building an Analytics Agent

You are an Analytics Agent. Analyze this sequence performance:

Sequence: [NAME]
Time period: [DATES]
Total prospects: [N]

Step-by-step metrics:
[PASTE OPEN RATES, REPLY RATES, MEETING RATES PER STEP]

Identify:
1. Which step has the biggest drop-off?
2. What hypothesis explains it?
3. What specific test would you run?
4. Expected impact if test succeeds

Analyze these two reps' performance and identify what the top performer does differently:

Rep A (top performer):
- Emails sent: [N]
- Reply rate: [%]
- Meetings booked: [N]
- Sample emails: [PASTE EXAMPLES]

Rep B (underperformer):
- Emails sent: [N]
- Reply rate: [%]
- Meetings booked: [N]
- Sample emails: [PASTE EXAMPLES]

What specific behaviors or techniques explain the difference? Provide actionable recommendations for Rep B.

Review this deal and predict risk level:

Opportunity: [COMPANY]
Stage: [CURRENT]
Amount: [VALUE]
Close date: [DATE]
Age in stage: [DAYS]

Activity summary:
- Last meeting: [DATE]
- Emails exchanged: [RECENT COUNT]
- Stakeholders engaged: [COUNT]
- Champion status: [ACTIVE/QUIET/GONE]

Predict:
1. Risk level (LOW/MEDIUM/HIGH)
2. Top risk factors
3. Recommended actions to de-risk
4. Realistic close date based on patterns

Forecast next quarter's pipeline:

Current pipeline:
[PASTE PIPELINE SUMMARY BY STAGE]

Historical conversion rates:
[PASTE STAGE-TO-STAGE CONVERSION RATES]

Assumptions:
- Rep capacity: [DETAILS]
- Seasonality: [FACTORS]
- New lead flow: [EXPECTED]

Provide:
1. Expected revenue (low/mid/high)
2. Key assumptions that drive variance
3. Deals to focus on for highest impact
4. Gaps to fill in early stages

Identify the best time and channel to reach prospects in [INDUSTRY]:

Historical data:
- Email performance by day/time: [DATA]
- LinkedIn performance by day/time: [DATA]
- Phone connect rates by day/time: [DATA]

Based on the data:
1. Optimal first-touch timing
2. Best channel mix
3. When to avoid outreach
4. How this differs from other industries