Marketing AnalyticsAdvanced68 minSaves 2+ hours

Define Launch Week Analytics Dashboard for B2B SaaS

For growth and analytics leads at a B2B SaaS preparing for launch, define a comprehensive analytics dashboard specification to track critical metrics from day one.

This prompt assists growth and analytics leads at a B2B SaaS company in defining a precise launch-week analytics dashboard specification. It outlines core metrics, conversion events, attribution, and an event schema, ensuring critical data informs immediate post-launch decisions

ChatGPT Claude Gemini

READY-TO-USE PROMPT

Copy Prompt

prompt.txt

Role: Analytics Strategist

Context: Your B2B SaaS company, {{product_name}}, is preparing for its public launch in {{launch_date}}. We need a precise analytics framework to monitor performance immediately post-launch. The goal is to ensure we capture critical data points from day one to inform rapid iteration and decision-making. We require a clear specification for our launch-week analytics dashboard, focusing on actionable insights for growth and product teams.

Task: Develop a comprehensive analytics dashboard specification tailored for launch week. This specification must outline the core metrics, data collection requirements, and reporting structure needed to understand initial user engagement and conversion pathways.

Constraints:
* **Focus:** Strictly on launch-week performance monitoring.
* **Primary Conversion:** Define the key primary conversion event, e.g., `{{primary_conversion_event}}`.
* **Secondary Conversions:** Include secondary conversion events relevant to activation, such as waitlist sign-ups converting to active users.
* **Attribution:** Specify a basic attribution model to understand traffic sources.
* **Event Schema:** Outline a foundational event schema for tracking user interactions.
* **Review Cadence:** Propose a daily review process for the launch-week dashboard.
* **Audience:** The spec should be suitable for growth, product, and engineering teams.

Output: Provide the dashboard specification using the following structure:

1. **Dashboard Goals:**
* What are the overarching objectives for this launch-week dashboard?
* How will it inform immediate tactical decisions?

2. **Key Performance Indicators (KPIs):**
* **Primary Conversion:** Define the specific event, its definition, and how it will be tracked.
* **Secondary Conversions:** List 2-3 key secondary events, definitions, and tracking methods (e.g., waitlist activation, feature engagement).
* **Engagement Metrics:** Include 2-3 crucial engagement metrics (e.g., active users, session duration, key feature usage).
* **Attribution Metrics:** Specify how acquisition channels will be tracked and attributed (e.g., first-touch, last-touch, source breakdown).

3. **Event Schema:**
* Propose a concise list of 5-7 essential events to track during launch week. For each event, define:
* Event Name (e.g., `user_signed_up`)
* Description
* Key Properties (e.g., `user_id`, `plan_type`, `referral_source`)

4. **Dashboard Layout & Views:**
* Describe the logical sections or tabs within the dashboard.
* Suggest specific charts or visualizations for each KPI (e.g., daily conversion rate line chart, attribution source bar chart).

5. **Review Cadence & Responsibilities:**
* Outline a daily review process for the launch week.
* Specify who should be involved and what decisions should be made based on the dashboard data.
* Suggest a format for sharing daily insights.

Estimated results

DifficultyAdvanced

Setup time68 min

Time saved2+ hours

Best modelsChatGPT, Claude, Gemini

Best audienceSaaS

Editor's note

Why this prompt matters

For B2B SaaS companies, the period immediately following a product launch is critical. It's a compressed window where initial user behavior dictates early strategy adjustments. Without a clear, pre-defined analytics framework, teams risk collecting irrelevant data or, worse, missing crucial insights needed to pivot or double down on successful initiatives. This workflow addresses the challenge of establishing a focused data collection and reporting system for that intense first week.

This prompt is designed for growth and analytics leads responsible for ensuring their product launch is informed by actionable data. It provides a structured approach to defining the exact metrics, events, and reporting cadence required to understand initial user engagement and conversion funnels. By specifying the primary and secondary conversions, alongside a foundational event schema and attribution model, teams can move beyond anecdotal evidence to data-driven decisions quickly.

Reach for this workflow when your B2B SaaS product is nearing its public debut. It serves as a blueprint for aligning growth, product, and engineering teams on what truly matters to track from day one, preventing reactive data requests and fostering proactive strategic adjustments based on real user interactions. It helps ensure that the intense effort of a product launch is supported by clear, immediate performance feedback.

Anatomy

Prompt engineering breakdown

Role

This prompt directs the AI to act as an Analytics Strategist, developing a precise launch-week analytics dashboard specification for a B2B SaaS company to monitor initial performance and inform rapid iteration.

Context

The prompt establishes that a B2B SaaS company, "{{product_name}}", is launching on "{{launch_date}}". The need is for an analytics framework to monitor immediate post-launch performance, capture critical data, and inform rapid decision-making.

Goal

To develop a comprehensive analytics dashboard specification for launch week, detailing core metrics, data collection requirements, and a reporting structure to understand initial user engagement and conversion pathways.

Constraints

The specification must strictly focus on launch-week performance, define primary ("{{primary_conversion_event}}") and secondary conversion events (like waitlist to active users), specify a basic attribution model, outline a foundational event schema, propose a daily review process, and be suitable for growth, product, and engineering teams.

Output format

The required output is a structured dashboard specification with five main sections: Dashboard Goals, Key Performance Indicators (KPIs), Event Schema, Dashboard Layout & Views, and Review Cadence & Responsibilities. Each section has specific sub-requirements for detailed content.

Why this structure works

The prompt effectively uses role priming by assigning 'Analytics Strategist', which sets expectations for a data-driven, strategic response. Explicit constraints ensure the output remains focused on launch-week metrics and specific conversion types. Finally, the structured output format, clearly outlining sections like 'KPIs' and 'Event Schema', guides the model to produce a comprehensive and immediately actionable document.

Pick your version

Prompt variations

BeginnerWorks with any model

For quickly generating a basic outline of a launch-week dashboard, suitable for initial planning or smaller teams with fewer complex data needs.

prompt.txt

You are an Analytics Helper. Your company, {{product_name}}, is launching. We need a simple plan for an analytics dashboard to see how things are going in the first week. Focus on the main things we need to track.Please create a dashboard plan that includes:1.  **What we want to achieve:** What are the top 1-2 goals for seeing this data?2.  **Key Numbers:**    *   Our main goal (like `{{primary_conversion_event}}`).    *   1-2 other important actions users take (e.g., signing up from a waitlist).    *   How we know where users came from.3.  **Events to Track:** List 3-5 key actions users do, with simple names and details.4.  **How the Dashboard Looks:** What main sections should it have?5.  **Daily Check-in:** How should we review this data every day during launch week?

ProfessionalBest with chatgpt

When a detailed, actionable analytics plan is needed for a B2B SaaS launch, requiring specific metrics, attribution models, and review processes for growth and product teams.

prompt.txt

Role: Analytics StrategistContext: Your B2B SaaS company, {{product_name}}, is launching on {{launch_date}}. We need a precise analytics framework to monitor performance immediately post-launch to inform rapid iteration. The goal is actionable insights for growth and product teams.Task: Develop a comprehensive launch-week analytics dashboard specification. Outline core metrics, data collection, and reporting structure for initial user engagement and conversion pathways.Constraints:*   **Focus:** Strictly launch-week performance monitoring.*   **Primary Conversion:** Define `{{primary_conversion_event}}`.*   **Secondary Conversions:** Include activation events (e.g., waitlist to active users).*   **Attribution:** Specify a basic attribution model.*   **Event Schema:** Outline a foundational event schema.*   **Review Cadence:** Propose a daily review process.*   **Audience:** Growth, product, and engineering teams.Output: Provide the dashboard specification using this structure:1.  **Dashboard Goals:** Overarching objectives and how they inform tactical decisions.2.  **Key Performance Indicators (KPIs):**    *   **Primary Conversion:** Event, definition, tracking.    *   **Secondary Conversions:** 2-3 events, definitions, tracking (e.g., waitlist activation).    *   **Engagement Metrics:** 2-3 crucial metrics (e.g., active users, session duration).    *   **Attribution Metrics:** Acquisition channels tracked (e.g., first-touch, source breakdown).3.  **Event Schema:**    *   5-7 essential events: Name (e.g., `user_signed_up`), Description, Key Properties (e.g., `user_id`, `referral_source`).4.  **Dashboard Layout & Views:** Logical sections/tabs, suggested charts/visualizations for each KPI.5.  **Review Cadence & Responsibilities:** Daily review process, involved parties, decision-making, daily insight sharing format.

Short VersionWorks with any model

For a concise, high-level overview or initial brainstorming session when time is limited and only the core requirements are needed.

prompt.txt

As an Analytics Strategist, outline a launch-week analytics dashboard specification for {{product_name}}'s launch on {{launch_date}}. Focus on immediate performance monitoring. Define the primary conversion (`{{primary_conversion_event}}`), secondary activations, and a basic attribution model. Propose a foundational event schema (5-7 events with names and key properties) and a daily review process. Structure the output with sections for Dashboard Goals, KPIs (primary, secondary, engagement, attribution), Event Schema, Dashboard Layout, and Review Cadence. This spec should inform rapid iteration for growth and product teams post-launch.

EnterpriseBest with claude

For larger organizations that require a comprehensive analytics specification addressing data governance, compliance, cross-functional stakeholder reporting, and risk mitigation in addition to core performance metrics.

prompt.txt

Role: Lead Analytics ArchitectContext: Our enterprise B2B SaaS product, {{product_name}}, is launching publicly on {{launch_date}}. We require a robust, compliant, and scalable analytics dashboard specification for the critical launch week. This framework must facilitate rapid, informed decision-making across all relevant departments while adhering to corporate data governance and privacy policies. The goal is to establish a single source of truth for initial performance.Task: Develop a comprehensive, enterprise-grade analytics dashboard specification for launch week. This spec must detail core metrics, data collection protocols, attribution methodologies, stakeholder reporting structures, and data integrity checks.Constraints:*   **Focus:** Launch-week performance, data integrity, and compliance (e.g., GDPR, CCPA).*   **Primary Conversion:** Clearly define `{{primary_conversion_event}}` with specific data points and legal considerations.*   **Secondary Conversions:** Include 3-4 activation-focused secondary conversions, detailing data provenance.*   **Attribution Model:** Specify a multi-touch attribution model (e.g., U-shaped, W-shaped) with data reconciliation strategies.*   **Event Schema:** Propose a detailed event schema (7-10 events) including event name, description, critical properties, data type, and privacy implications.*   **Review & Governance:** Outline a daily review process, escalation paths for anomalies, and data governance ownership.*   **Audience:** Suitable for Executive Leadership, Legal, Growth, Product, and Engineering.Output: Provide a detailed specification covering: Dashboard Objectives, Comprehensive KPIs (including financial impact), Granular Event Schema (with data definitions and privacy tags), Multi-Channel Attribution Reporting, Dashboard Architecture & Data Sources, and a Structured Review & Governance Cadence with defined responsibilities and reporting mechanisms.

What you'll get

Expected output

1. Dashboard Goals:

Overarching Objectives: Provide a real-time, comprehensive view of InnovateFlow's initial market reception, user acquisition, and primary conversion pathways during launch week. Identify immediate opportunities for optimization in marketing, product messaging, and user onboarding.
Inform Immediate Tactical Decisions: Inform daily stand-ups to identify underperforming channels, unexpected user drop-off, or high-performing features. Decisions will include adjusting ad spend, refining call-to-action language, or prioritizing critical bug fixes.

2. Key Performance Indicators (KPIs):

Primary Conversion: `demo_booked`

* Definition: User successfully completes a demo booking form and confirms a scheduled slot. * Tracking: Event demo_booked fired upon successful submission. Properties: user_id, company_size, source_channel.

Secondary Conversions:

* Waitlist Activation: * Definition: Waitlist user completes product registration and first login. * Tracking: Event waitlist_activated upon first login, linked to waitlist_signup. Properties: user_id. * Trial Started: * Definition: New user completes initial setup and initiates free trial. * Tracking: Event trial_started upon onboarding completion. Properties: user_id, trial_plan.

Engagement Metrics:

* Daily Active Users (DAU): Unique users performing any key action within the product daily. * Key Feature Usage: Number of times critical features (e.g., "Project Creation") are used. * Session Duration: Average active time per user session.

Attribution Metrics:

* Acquisition Channel Breakdown: Track traffic sources (e.g., Google Ads, Organic Search). * Attribution Model: First-touch attribution for initial page_view. * Tracking: source_channel, utm_source persisted with user_id.

3. Event Schema:

`page_view`: User views a page. Properties: user_id, page_url, source_channel, device_type.
`user_signed_up`: User completes registration. Properties: user_id, email, signup_method, source_channel.
`demo_booked`: User schedules a demo. Properties: user_id, company_size, source_channel.
`trial_started`: User initiates free trial. Properties: user_id, trial_plan_type, onboarding_status.
`feature_used`: User interacts with a core feature. Properties: user_id, feature_name, action_type.
`session_start`: Marks session beginning. Properties: user_id, session_id, timestamp.

4. Dashboard Layout & Views:

Tab 1: Overview & Topline Metrics: Daily demo_booked (line chart), Cumulative demo_booked (area chart), Daily DAU (line chart).
Tab 2: Acquisition & Attribution: demo_booked by source_channel (bar chart), user_signed_up by utm_source (pie chart).
Tab 3: Conversion Funnel: Funnel visualization: Landing -> Sign Up -> Trial Start -> Demo Booked.
Tab 4: User Engagement: feature_used counts (bar chart), Average Session Duration (line chart).

5. Review Cadence & Responsibilities:

Daily Review Process: 30-minute stand-up at 9:30 AM daily during launch week.
Involved Teams: Growth Lead, Product Lead, Analytics Lead.
Decisions Made: Identify blockers, reallocate marketing budget, refine messaging, prioritize product tweaks.
Sharing Insights: Executive summary email post-meeting; Slack channel for real-time alerts.

Under the hood

Why this prompt works

This prompt structure yields effective results by employing several targeted prompt engineering techniques. Firstly, role priming establishes the model as an "Analytics Strategist," ensuring the output adopts the correct tone, perspective, and depth of technical understanding required for a dashboard specification. This prevents generic advice and focuses on actionable, data-driven recommendations.

The inclusion of detailed context setting and explicit constraints is critical. By defining the product, launch date, primary conversion event, and specific requirements like attribution models and event schemas, the prompt narrows the solution space considerably. This specificity prevents the model from generating irrelevant KPIs or a generalized analytics plan, instead forcing it to produce a highly tailored and relevant specification for a B2B SaaS launch. For instance, requiring "launch-week performance monitoring" ensures the metrics are immediate and tactical, not long-term strategic.

Finally, the prompt's explicit demand for structured output is essential for usability. By outlining the exact headings and sub-sections (e.g., "Dashboard Goals," "Key Performance Indicators," "Event Schema"), it guides the model to produce a logically organized and immediately parseable document. This structured approach means the output can be directly used as a draft for a real-world analytics spec, reducing the need for extensive post-generation editing and ensuring all required components are present. This comprehensive structure produces a far more actionable result than a single, open-ended request.

Model fit

Best AI models for this prompt

ChatGPT

ChatGPT is effective for generating structured outlines and defining metrics. Its ability to process and synthesize information quickly makes it suitable for drafting the initial dashboard goals, KPIs, and event schema. However, ensure explicit context is provided to keep the output focused on B2B SaaS nuances and avoid generic definitions. See the full ChatGPT hub for deeper guidance.

Claude

Claude excels at following multi-part instructions and maintaining a coherent, detailed narrative. This makes it well-suited for developing the comprehensive dashboard specification, including the rationale behind each section and the proposed review cadence. It handles the integration of different data points into a logical structure with minimal re-prompting. See the full Claude hub for deeper guidance.

Gemini

Gemini is strong in producing well-organized lists and clear definitions, which is beneficial for the KPI and event schema sections of this prompt. Its capability to break down complex requests into actionable components helps in generating precise event properties and dashboard layout suggestions. Focus on providing clear delimiters for structured output. See the full Gemini hub for deeper guidance.

When to use

When launching a B2B SaaS product and needing immediate, focused data insights.
For aligning growth, product, and engineering teams on critical launch metrics and priorities.
To establish a clear, data-driven daily review process for the initial post-launch period.
When defining primary and secondary conversion events for early product adoption and activation.
To specify a foundational event schema before data collection begins, ensuring critical data is captured.

When not to use

For long-term strategic analytics planning beyond the initial launch week.
If the product is already mature and not undergoing a public launch.
When a comprehensive, deeply granular attribution model is required from day one.
For defining product-specific feature usage analytics that aren't critical to early conversion.
If engineering resources are insufficient to implement the defined event tracking and dashboard setup.

Get more from it

Pro tips

1
Prioritize event tracking implementation with engineering pre-launch to prevent critical data gaps during the initial rollout.
2
Clearly define conversion event criteria with all stakeholders to prevent misinterpretation of early performance results.
3
Set realistic expectations for initial data volume and statistical significance to prevent premature conclusions or overreactions.
4
Regularly cross-reference dashboard data with qualitative feedback to understand the 'why' behind user behavior patterns.
5
Keep the launch-week dashboard focused on core metrics only, preventing analysis paralysis from excessive data points.
6
Thoroughly test all tracking events in a staging environment before launch to ensure data accuracy and reliable reporting.
7
Prepare a concise communication plan for daily insights to keep all relevant teams informed and aligned on progress.

Don't ship this

Common mistakes

✗ Overloading the dashboard with too many metrics, leading to confusion and delayed decision-making.
Fix — Restrict the dashboard to 5-7 core KPIs directly tied to launch success for actionable daily reviews.
✗ Vague event definitions causing inconsistent tracking and unreliable data collection post-launch.
Fix — Work with engineering to precisely define each event name, description, and property before implementation.
✗ Not assigning clear ownership for daily data review and action items during launch week.
Fix — Designate a lead for each daily standup to drive discussion, summarize insights, and assign responsibilities.
✗ Neglecting pre-launch tracking validation, resulting in broken events or inaccurate dashboard visualizations.
Fix — Thoroughly test all event tracking and dashboard components in a staging environment before the public launch.
✗ Ignoring qualitative feedback from users in favor of purely quantitative data during the initial week.
Fix — Integrate user interviews or support tickets into daily reviews for behavioral context and deeper insights.
✗ Failing to define the primary conversion event clearly, leading to misalignment across teams.
Fix — Ensure a single, unambiguous primary conversion metric is agreed upon and documented by all stakeholders.

Frequently asked questions

Q.Can this be adapted for a B2C product launch?

Yes, but you'll need to adjust the primary/secondary conversion events and engagement metrics to align with typical B2C user flows and acquisition funnels. The core structure remains relevant.

Q.How prescriptive is the event schema provided by the prompt?

It's a foundational proposal. You should refine it collaboratively with your engineering team, aligning with your specific product, data infrastructure, and analytics tool capabilities.

Q.What if we don't have all the attribution data fully integrated initially?

Start with basic source tracking (e.g., UTMs). You can iterate on more complex attribution models after launch week, once initial data stabilizes and more granular data becomes available.

Q.Is this approach suitable for a product that has been live for months?

No, this specification is specifically designed for the rapid, focused insights required during the immediate launch week. A mature product requires a broader, ongoing analytics strategy.

Q.Should I include error monitoring or system health metrics in this dashboard spec?

While important for launch, this spec focuses on user behavior and conversion. Error monitoring is typically handled by separate engineering or operations dashboards for clarity.

Q.How long should the input values for variables like `{{product_name}}` or `{{primary_conversion_event}}` be?

Keep these inputs concise, ideally 1-3 words. This maintains clarity within the generated specification and ensures readability of the dashboard goals and KPIs.

Version 1.0Last reviewed July 12, 2026

Reviewed by PromptInFlow Editorial Team