Periodic Sales Performance Review

Periodic Sales Performance Review

Pulls rep-level and team-level sales data from whatever system the user tracks performance in, analyzes it over a chosen period, and produces a report that answers the questions a sales leader actually cares about: Are we going to hit the number? Who's carrying the team? Who needs help? Where are the coaching opportunities? Are our forecasts reliable?

Two output modes:

• Executive summary: 1-page snapshot. Quota attainment, top/bottom performers, red flags, green lights. What a VP Sales reads before the Monday standup.
• Detailed diagnostic: Full rep-by-rep breakdown, activity analysis, deal progression, win/loss patterns, forecast accuracy, and coaching recommendations.

Both are always produced. The executive summary sits at the top of the report.

When to Auto-Load

Load this composite when:

• User says "sales performance review", "team performance report", "how's the team doing", "rep scorecard"
• User says "weekly sales review", "monthly performance review", "quarterly sales analysis"
• User says "who's hitting quota", "quota attainment report", "rep performance"
• An upstream workflow (Pipeline Ops, management cadence) triggers an end-of-period review
• User asks about forecast accuracy, rep productivity, or team-level trends

Step 0: Configuration (One-Time Setup)

On first run, collect and store these preferences. Skip on subsequent runs.

Data Source Config

Team Structure

Example team structure:

team_structure: {
  "SDR": ["Alex", "Jordan"],
  "AE - SMB": ["Sam", "Casey"],
  "AE - Enterprise": ["Morgan", "Riley"]
}
managers: {
  "SDR": "Taylor",
  "AE - SMB": "Jamie",
  "AE - Enterprise": "Jamie"
}

Quota & Targets

Example quota config:

rep_quotas: {
  "Sam": 50000,
  "Casey": 50000,
  "Morgan": 150000,
  "Riley": 150000
}
quota_period: "monthly"
team_target: 400000
activity_targets: {
  "SDR": { "calls_per_day": 50, "emails_per_day": 80, "meetings_per_week": 10 },
  "AE": { "calls_per_day": 15, "emails_per_day": 20, "meetings_per_week": 8 }
}

Pipeline Stage Definitions

Forecast Config (Optional)

Store config in: clients/<client-name>/config/periodic-sales-performance-review.json or equivalent.

Step 1: Pull Performance Data

Purpose: Extract deal data, activity data, and (optionally) forecast data for the specified period.

Input Contract

period: {
  type: "weekly" | "monthly" | "quarterly" | "custom"
  start_date: string              # ISO date (auto-calculated from type, or user-specified)
  end_date: string                # ISO date (default: today)
  comparison_period: boolean      # Include prior period for trend comparison (default: true)
}
crm_tool: string                  # From config
access_method: string             # From config
activity_source: string           # From config
rep_names: string[]               # From config

Process

Pull three categories of data:

A) Deal Data (per rep)

For each rep, pull:

• All deals closed (won + lost) in the period
• All deals created in the period
• All deals currently open (active pipeline)
• Deal amounts, stages, close dates, sources, loss reasons

B) Activity Data (per rep)

For each rep, pull:

• Calls made (count, duration if available)
• Emails sent (count, reply rate if available)
• Meetings held (count, no-shows if available)
• Proposals/demos delivered
• LinkedIn touches (if tracked)

C) Forecast Data (if tracked)

Pull the forecast submitted at the start of the period for comparison to actuals:

• Commit forecast per rep
• Best case forecast per rep
• Pipeline forecast per rep

Data Standardization

Normalize all data into a standard structure:

performance_data: {
  current_period: {
    start_date: string
    end_date: string
    reps: [
      {
        name: string
        team: string | null
        manager: string | null
        quota: number

        revenue: {
          closed_won: number
          closed_lost_value: number
          deals_won: integer
          deals_lost: integer
          avg_deal_size: number | null
          largest_deal: { name: string, amount: number } | null
        }

        pipeline: {
          deals_created: integer
          pipeline_value_created: number | null
          open_deals: integer
          open_pipeline_value: number | null
          weighted_pipeline: number | null
        }

        activity: {
          calls: integer | null
          emails_sent: integer | null
          meetings_held: integer | null
          meetings_booked: integer | null
          proposals_sent: integer | null
          no_shows: integer | null
        } | null

        velocity: {
          avg_days_to_close: float | null
          avg_days_in_stage: { stage: string, days: float }[] | null
        } | null

        qualification: {
          meetings_to_qualified_rate: percentage | null
          qualified_deals: integer | null
        } | null

        deals_closed: [
          {
            name: string
            company: string
            amount: number
            stage: string            # won or lost
            close_date: string
            days_to_close: integer | null
            source: string | null
            loss_reason: string | null
          }
        ]

        forecast: {
          commit: number
          best_case: number
          pipeline: number
        } | null
      }
    ]
  }
  comparison_period: { ... } | null    # Same structure for prior period
}

Human Checkpoint

## Performance Data Pulled

Source: [CRM name]
Activity source: [Activity tool name]
Current period: [start] to [end]
Comparison period: [start] to [end]

Reps found: [list of rep names]
Deals closed in period: X won, Y lost
Activity data available: [yes/partial/no]
Forecast data available: [yes/no]

Data looks correct? (Y/n)

Step 2: Analyze Performance

Purpose: Run the full analysis across six dimensions. Pure computation + LLM reasoning.

Input Contract

performance_data: { ... }           # From Step 1
rep_quotas: { ... }                 # From config
team_target: number                 # From config
activity_targets: { ... } | null    # From config
pipeline_stages: string[]           # From config
expected_cycle_days: integer        # From config

Analysis Dimensions

Run all six analyses on the current period data. Where comparison period exists, calculate period-over-period trends.

Analysis 1: Quota Attainment

Questions answered: Are we going to hit the number? Who's on track and who isn't?

Output:

quota_attainment: {
  team: {
    target: number
    closed: number
    attainment_pct: percentage
    run_rate_projection: number
    projected_attainment_pct: percentage
    gap_to_target: number
    vs_prior_period: percentage_change | null
  }
  by_rep: [
    {
      name: string
      team: string | null
      quota: number
      closed: number
      attainment_pct: percentage
      run_rate_projection: number
      gap_to_quota: number
      rank: integer
      vs_prior_period: percentage_change | null
      status: "crushing" | "on_track" | "behind" | "at_risk"
    }
  ]
  distribution: {
    above_100: integer
    pct_80_to_100: integer
    pct_50_to_80: integer
    below_50: integer
  }
}

Status thresholds (adjusted for time elapsed in period):

• Crushing: >110% attainment (pace-adjusted)
• On track: 90-110% attainment (pace-adjusted)
• Behind: 60-90% attainment (pace-adjusted)
• At risk: <60% attainment (pace-adjusted)

Analysis 2: Activity Metrics

Questions answered: Are reps putting in the work? Who's active and who's coasting?

Output:

activity_analysis: {
  by_rep: [
    {
      name: string
      team: string | null
      calls_per_day: float | null
      emails_per_day: float | null
      meetings_per_week: float | null
      proposals_sent: integer | null
      activity_to_meeting_rate: percentage | null
      meeting_to_opp_rate: percentage | null
      no_show_rate: percentage | null
      revenue_per_meeting: number | null
      vs_targets: {
        calls: "above" | "at" | "below" | null
        emails: "above" | "at" | "below" | null
        meetings: "above" | "at" | "below" | null
      } | null
      vs_prior_period: {
        calls_change: percentage | null
        emails_change: percentage | null
        meetings_change: percentage | null
      } | null
      activity_grade: "high" | "adequate" | "low" | "critical"
    }
  ]
  team_averages: {
    avg_calls_per_day: float | null
    avg_emails_per_day: float | null
    avg_meetings_per_week: float | null
    avg_revenue_per_meeting: number | null
  }
  efficiency_leaders: {
    most_efficient_rep: string         # Highest revenue per activity
    most_active_rep: string            # Highest total activity volume
    best_conversion_rep: string        # Highest meeting-to-opp rate
  }
}

Activity grade thresholds (relative to targets or team average):

• High: >120% of target/average
• Adequate: 80-120%
• Low: 50-80%
• Critical: <50%

Analysis 3: Deal Progression & Velocity

Questions answered: How fast are deals moving? Are deals progressing or stalling?

Output:

deal_progression: {
  by_rep: [
    {
      name: string
      avg_days_to_close: float | null
      deals_progressed: integer
      deals_stalled: integer
      pipeline_created: number | null
      pipeline_coverage: float | null
      coverage_assessment: "healthy" | "adequate" | "at_risk" | "critical"
      fastest_deal: { name: string, days: integer } | null
      slowest_stage: { stage: string, avg_days: float } | null
    }
  ]
  team: {
    avg_days_to_close: float | null
    vs_expected_cycle: string
    total_pipeline_created: number | null
    total_pipeline_coverage: float | null
    deals_progressed: integer
    deals_stalled: integer
    stall_rate: percentage
    vs_prior_period: {
      velocity_change: string | null
      stall_rate_change: percentage_change | null
    } | null
  }
}

Pipeline coverage thresholds:

• Healthy: 3x+ remaining quota
• Adequate: 2-3x
• At risk: 1-2x
• Critical: <1x

Analysis 4: Win/Loss Patterns

Questions answered: Why are we winning? Why are we losing? Are there patterns by rep?

Output:

win_loss: {
  team: {
    win_rate: percentage
    deals_won: integer
    deals_lost: integer
    avg_deal_size_won: number | null
    total_revenue_lost: number | null
    vs_prior_period: percentage_change | null
    top_loss_reasons: [
      { reason: string, count: integer, percentage: percentage }
    ]
    loss_by_stage: [
      { stage: string, count: integer, percentage: percentage }
    ]
    competitive_losses: [
      { competitor: string, count: integer, deals: string[] }
    ] | null
  }
  by_rep: [
    {
      name: string
      win_rate: percentage
      deals_won: integer
      deals_lost: integer
      avg_deal_size_won: number | null
      vs_prior_period: percentage_change | null
      top_loss_reason: string | null
      loss_stage: string | null          # Stage where most losses occur
      notable_wins: [ { deal: string, amount: number } ] | null
    }
  ]
}

Analysis 5: Rep Benchmarking & Coaching Priorities

Questions answered: How do reps compare to each other? Where does each rep need help?

Skill gap inference logic:

Output:

rep_benchmarking: {
  rankings: [
    {
      name: string
      composite_score: float               # 0-100
      rank: integer
      attainment_pct: percentage
      activity_grade: string
      win_rate: percentage
      pipeline_coverage: float
      trend: "improving" | "stable" | "declining" | null
    }
  ]
  coaching_priorities: [
    {
      rep_name: string
      priority: "urgent" | "high" | "medium" | "low"
      primary_gap: string                  # e.g., "discovery skills"
      evidence: string                     # The data pattern that reveals this gap
      recommended_coaching: string         # Specific action for their manager
      secondary_gaps: string[] | null
    }
  ]
  team_strengths: string[]                 # What the team does well
  team_weaknesses: string[]                # Systemic issues across multiple reps
}

Coaching priority logic:

• Urgent: Rep is <50% attainment AND activity is low — needs immediate intervention
• High: Rep is <80% attainment with identifiable skill gap — coaching can move the needle
• Medium: Rep is on track but has a specific area significantly below team average
• Low: Rep is performing well — coach to maintain and stretch

Analysis 6: Forecast Accuracy (if forecast data available)

Questions answered: How reliable are our forecasts? Who sandags? Who over-commits?

Output:

forecast_accuracy: {
  team: {
    commit_forecast: number
    best_case_forecast: number
    actual_closed: number
    commit_accuracy: percentage           # Actual / commit
    best_case_realization: percentage
    accuracy_grade: "reliable" | "optimistic" | "conservative" | "unreliable"
  }
  by_rep: [
    {
      name: string
      commit_forecast: number
      actual_closed: number
      accuracy: percentage
      pattern: "accurate" | "over_commits" | "sandbags" | "volatile"
      deviation: number                   # Actual - commit
    }
  ]
  insights: string[]                      # Patterns observed
} | null

Accuracy grades:

• Reliable: Team closes within 90-110% of commit
• Optimistic: Team consistently closes <90% of commit
• Conservative: Team consistently closes >110% of commit (sandbagging)
• Unreliable: Wide variance, no consistent pattern

Output Contract (Full Analysis)

analysis: {
  period: { type, start_date, end_date }
  quota_attainment: { ... }
  activity_analysis: { ... }
  deal_progression: { ... }
  win_loss: { ... }
  rep_benchmarking: { ... }
  forecast_accuracy: { ... } | null
}

No human checkpoint after this step — the analysis feeds directly into report generation.

Step 3: Generate Report

Purpose: Transform the raw analysis into two report formats: an executive summary and a detailed diagnostic with rep-level coaching notes. Pure LLM reasoning.

Input Contract

analysis: { ... }                     # From Step 2
rep_quotas: { ... }                   # From config
team_target: number                   # From config
activity_targets: { ... } | null      # From config

Executive Summary Format

One page. Numbers and rankings. What a VP Sales needs to see in 60 seconds.

# Sales Performance Review — [Period Type]: [Start Date] to [End Date]

## Team Snapshot
| Metric | This Period | Prior Period | Change |
|--------|------------|-------------|--------|
| Revenue closed | $X | $Y | +/-Z% |
| Team attainment | X% | Y% | +/-Z pts |
| Deals won | X | Y | +/-Z |
| Avg deal size | $X | $Y | +/-Z% |
| Win rate | X% | Y% | +/-Z pts |
| Avg days to close | X | Y | +/-Z |
| Pipeline coverage | Xx | Yx | +/-Z |

## Rep Attainment Leaderboard
| Rank | Rep | Closed | Quota | Attainment | Status |
|------|-----|--------|-------|------------|--------|
| 1 | [Name] | $X | $Y | Z% | Crushing |
| 2 | [Name] | $X | $Y | Z% | On track |
| ... | ... | ... | ... | ... | ... |

## Red Flags
- [Any rep below 50% attainment — names and specifics]
- [Activity metrics below target]
- [Pipeline coverage below 2x for any rep]
- [Win rate declining]
- [Forecast accuracy deteriorating]

## Green Lights
- [Reps exceeding quota]
- [Metrics trending up]
- [Pipeline coverage healthy]
- [Wins against key competitors]

## Top 3 Actions
1. [Most impactful thing to do this week — e.g., "Coach [rep] on discovery — 8 meetings but 0 qualified deals"]
2. [Second most impactful]
3. [Third most impactful]

Detailed Diagnostic Format

Full rep-by-rep breakdown with coaching recommendations.

# Sales Performance Diagnostic — [Period]

## 1. Quota Attainment
[Team attainment summary]
[Rep-by-rep attainment table]
[Run rate projections]
[Gap analysis — what's needed to hit the number]
[Commentary: are we going to make it? What needs to happen?]

## 2. Activity Analysis
[Team activity averages vs. targets]
[Rep-by-rep activity table]
[Efficiency metrics — revenue per meeting, conversion rates]
[Commentary: who's doing the work? Who's efficient vs. just busy?]

## 3. Deal Progression & Velocity
[Pipeline creation and coverage by rep]
[Velocity metrics — avg days to close, stage duration]
[Stalled deals by rep]
[Commentary: is the pipeline healthy? Where are bottlenecks?]

## 4. Win/Loss Analysis
[Team win rate and trends]
[Rep-by-rep win rates]
[Loss reasons — team-level and rep-level patterns]
[Competitive loss analysis]
[Commentary: why are we losing? Any rep-specific patterns?]

## 5. Rep Scorecards
[For each rep, a mini-scorecard]:

### [Rep Name] — [Status: Crushing / On Track / Behind / At Risk]
| Metric | Value | vs. Target | vs. Team Avg | Trend |
|--------|-------|-----------|-------------|-------|
| Attainment | X% | [+/-] | [+/-] | [up/down/flat] |
| Activity | [grade] | [+/-] | [+/-] | [up/down/flat] |
| Win rate | X% | — | [+/-] | [up/down/flat] |
| Avg deal size | $X | — | [+/-] | [up/down/flat] |
| Pipeline coverage | Xx | [+/-] | [+/-] | [up/down/flat] |

**Strengths:** [What this rep does well, with data]
**Gaps:** [Where they need improvement, with data]
**Coaching recommendation:** [Specific action for their manager]

## 6. Forecast Accuracy (if available)
[Team forecast accuracy]
[Rep-by-rep accuracy table]
[Patterns: who sandbags, who over-commits]
[Commentary: can we trust the forecast?]

## 7. Recommendations
[Numbered list of specific, actionable recommendations.
 Each recommendation cites the data point that drives it.]

### Urgent (This Week)
1. [Action — data point — expected impact]

### High Priority (This Month)
2. [Action — data point — expected impact]
3. [Action — data point — expected impact]

### Systemic (Ongoing)
4. [Process or tooling change — data point — expected impact]

Recommendations Logic

Generate recommendations based on patterns found in the analysis:

Output Contract

report: {
  executive_summary: string           # Markdown formatted
  detailed_diagnostic: string         # Markdown formatted
  rep_scorecards: [
    {
      rep_name: string
      status: "crushing" | "on_track" | "behind" | "at_risk"
      strengths: string[]
      gaps: string[]
      coaching_action: string
    }
  ]
  recommendations: [
    {
      priority: "urgent" | "high" | "medium" | "systemic"
      area: string
      recommendation: string
      data_point: string
      expected_impact: string
    }
  ]
}

Human Checkpoint

Present the executive summary first, then offer the detailed diagnostic:

[Executive Summary rendered]

---

Full detailed diagnostic is also available with:
- Rep-by-rep scorecards with strengths, gaps, and coaching recommendations
- Deal-level analysis (progression, stalled deals, velocity)
- Win/loss deep dive with competitive analysis
- Forecast accuracy breakdown

Coaching priorities this period:
| Rep | Priority | Gap | Recommended Action |
|-----|----------|-----|--------------------|
| ... | ... | ... | ... |

Want to see the full diagnostic? Or drill into a specific rep's scorecard?

Step 4: Export & Share (Optional)

Purpose: Save the report and optionally push it to the user's preferred location.

Process

Based on user preference:

Execution Summary

Total human review time: ~15-20 minutes for a full sales performance review that would normally take 1-2 hours of CRM digging and spreadsheet building.

Adapting to Data Availability

Not every team tracks every metric. The analysis degrades gracefully:

Minimum viable data for a useful report: Rep names + deals closed (with amounts) + quota targets. Everything else enriches but isn't required.

Cadence Guide

The report depth automatically scales with the period length. A weekly review emphasizes activity and deal movement. A quarterly review emphasizes attainment trends, coaching ROI, and forecast reliability.

Tips

• Run this on a consistent cadence. The value compounds. A monthly review reveals trends. A quarterly review reveals who's improving and who's plateauing. Without consistency, you're always flying blind.
• Don't just look at quota attainment. A rep hitting quota through one large deal is different from a rep hitting quota through consistent execution. The underlying metrics tell you who is sustainably performing.
• Activity metrics without conversion context are useless. "Jordan made 500 calls" sounds impressive until you see 0 meetings booked. Always pair activity with outcomes.
• The coaching section is the ROI. The numbers tell you WHAT is happening. The coaching priorities tell you WHAT TO DO about it. A performance review without coaching actions is just a report card.
• Watch for the "middle" reps. Top performers and bottom performers get attention. The reps at 70-90% attainment often have the highest coaching ROI — they're close enough that fixing one skill gap puts them over the line.
• Forecast accuracy is a team discipline, not individual talent. If everyone's forecasts are off, it's a process problem. Implement deal inspection criteria: "What has to be true for this deal to close this period?"
• Compare rep performance within segments, not across them. An SMB AE closing $40K/month and an Enterprise AE closing $40K/month are having very different quarters. Always normalize for role and territory.
• Use the trend data. A rep at 60% attainment who was at 40% last month is improving. A rep at 90% who was at 120% last month is declining. Trajectory matters more than a single snapshot.