General analytics
AuraScore 89/100

Product Onboarding Funnel Diagnostic Report

Analyze SaaS user onboarding drop-offs, cohort decay, and activation bottlenecks into an executive diagnostic report.

Use this template when onboarding metrics lag behind industry baselines or when releasing major product experience updates. It guides an analyst to identify friction points and prioritize engineering or product interventions.

Template

Role: Principal Product Analytics Consultant with over a decade of SaaS user lifecycle and behavioral telemetry experience.

Context

  • Product Analyzed: {{product_name}}
  • Cohort Definition: {{target_cohort}}
  • Funnel Telemetry: {{onboarding_steps_data}}
  • Target Retention Benchmark: {{retention_benchmark}}
  • Analysis Window: {{timeframe}}
  • Telemetry Architecture: {{telemetry_source}}

Task

Produce an exhaustive onboarding funnel diagnostic report that pinpoints precise behavioral bottlenecks across the activation journey, quantifies revenue and retention drag against established benchmarks, and delivers prioritized product interventions.

Method

  1. Map every step of {{onboarding_steps_data}} against expected completion paths to establish an absolute conversion baseline for {{target_cohort}}.
  2. Calculate step-over-step drop-off percentages and median completion duration between successive milestone events within {{timeframe}}.
  3. Segment conversion velocities by user attributes and identify statistical variance between high-activating users and churned cohorts.
  4. Correlate milestone drop-off points against {{retention_benchmark}} to evaluate Day-7, Day-14, and Day-30 retention decay.
  5. Audit telemetry event fidelity from {{telemetry_source}} to separate actual user friction from potential instrumentation gaps or event latency.
  6. Formulate three root-cause hypotheses for top friction steps using behavioral cohorting and session characteristics.
  7. Develop an impact-effort matrix containing targeted product, UX, and lifecycle messaging interventions.
  8. Establish measurable leading indicators to track post-intervention recovery during subsequent evaluation cycles.

Constraints

  • MUST evaluate metrics exclusively within the context of {{product_name}} and {{target_cohort}}.
  • MUST NOT make assumptions about missing tracking events without explicitly flagging them as instrumentation gaps.
  • Quantitative claims MUST cite specific drop-off rates and completion timelines derived from {{onboarding_steps_data}}.
  • Keep recommendations tightly scoped to product-led onboarding without proposing broad marketing redesigns.

Output format

Generate a structured diagnostic report with the following mandatory sections:

  1. Executive Summary (max 200 words)
  2. Funnel Conversion Telemetry Breakdown (table format: Step Name, Conversion %, Median Time, Drop-off %)
  3. Cohort Retention & Benchmark Variance Analysis (max 350 words)
  4. Root Cause Friction Diagnoses (3 numbered findings)
  5. Prioritized Remediation Roadmap (table format: Initiative, Impact, Effort, Target Metric)

Self-review

  • Are all 6 contextual variables explicitly synthesized in the findings?
  • Is the transition between step-level friction and benchmark variance mathematically logical?
  • Are recommendations actionable for product management and data engineering teams?
AuraScore breakdown
89/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering10/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification14/14 · Strong

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness5/5 · Strong

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-general
technology-software
product analytics
saas onboarding
funnel analysis