Product Analytics and Reporting Analyst Agent Template

• What it does: Answers product and website questions with reproducible GA4 and Microsoft Clarity analysis, charts, caveats, and next experiments.
• Best for: SaaS teams, startups, mobile product teams, ecommerce teams, and product leaders.
• Apps used: Google Analytics, Microsoft Clarity.
• Setup time: 10 to 15 minutes after connecting GA4 and optionally Microsoft Clarity.

Last verified from workflow config on 2026-08-20. Includes exact connector scopes, common failure modes, and fixes.

The Product Analytics & Reporting Analyst answers business questions with reproducible GA4 and Clarity analysis, charts, and caveats. This template acts as a starting point: open any agent and use Use AI to help draft or update its instructions—adding new agents or connecting new tools is done manually in the canvas.

The problem this template solves

• Business questions reach analysts: without clear metrics, dimensions, date windows, or falsifiable hypotheses.
• GA4 and Clarity data: get joined as if their identities and definitions were automatically compatible.
• Reports present observational patterns: as causes without testing alternative explanations.

How do you build a product analytics agent yourself?

A reliable product analytics agent needs analytics metadata checks, compatible report queries, behavior exports, deterministic calculations, chart generation, caveat tracking, and reproducible report files. The method must keep source evidence, calculations, recommendations, and external actions distinct so a user can review what happened.

You can build this with Claude Code, Codex, or a custom stack. You would own authentication, schemas, retries, storage, approval state, testing, and ongoing connector maintenance. This template starts with those workflow decisions already represented in an editable Agent Build.

If the adjacent job is a better fit, the AI Database Q&A Analyst template provides a related starting point without forcing this agent beyond its actual scope.

Setup guide

Step 1: Clone the template into the right Project

Open the template gallery from Agent Space, choose Product Analytics and Reporting Analyst, and clone it into the Project that holds the relevant customer context. The workflow opens as an editable draft with its agents, notes, tools, and installed skills.

Step 2: Review Project context and complete first-run setup

Open Run and start a new conversation with Product Analytics Analyst. The agent checks read-only Project files and its reusable setup record before asking only for unresolved choices from the installed Investigate Product Analytics and Build Reports method.

Step 3: Connect only the apps this workflow needs

Open Agent Build, inspect each tool node, and connect the required accounts for Google Analytics, Microsoft Clarity. Review the allowlisted actions shown in the Apps used table below, and avoid granting broader write access than the template needs.

Step 4: Confirm goals, limits, and approval policy

Review the saved setup fields, reporting window, output preferences, cost limits, and any external-write policy. Keep analysis and draft work available by default, and require explicit approval for any live side effect described in the workflow guardrails.

Step 5: Test a normal prompt and an edge case

Run Why did signup conversion fall this month compared with last month? Then open a clean conversation and test Investigate the drop without exposing user-level personal information or claiming causality. Inspect tool calls, files, human-input pauses, and the final answer in the trace before changing instructions.

Step 6: Publish the tested draft

Return to Build, save the final configuration, then publish it from Deploy after the draft test behaves as expected. Use Playground for ongoing work and Agent Space to watch live status or requests that need human input.

Common issues and fixes

• A required connector is disconnected: Open Tools and Skills, connect the account in the same Project, and confirm the intended actions remain allowlisted.
• Project context is incomplete: Add or update the relevant brand, goal, policy, glossary, or source file at Project scope, then ask the agent to refresh setup instead of guessing.
• The requested action is unsupported: Keep the local analysis or draft, state the connector gap, and do not claim a live write without a returned identifier.
• The result uses the wrong window or target: Confirm the saved setup, source period, locale, identity, and output goal before rerunning a cost-bearing or external step.

Customization knobs

• GA4 account/property and Clarity project: Review and update this value through the first-run setup flow when the Project changes.
• north-star and guardrail metrics: Review and update this value through the first-run setup flow when the Project changes.
• conversion/key-event definitions: Review and update this value through the first-run setup flow when the Project changes.
• funnel steps and important segments: Review and update this value through the first-run setup flow when the Project changes.
• timezone, currency, and reporting calendar: Review and update this value through the first-run setup flow when the Project changes.
• known tracking gaps and release dates: Review and update this value through the first-run setup flow when the Project changes.

Who this template is for

• SaaS product teams: Ranked from product analytics for saas (0 US searches/month in the evaluated dataset). The workflow fits because it can answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports.
• Startups: Ranked from product analytics for startups (0 US searches/month in the evaluated dataset). The workflow fits because it can answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports.
• Mobile app teams: Ranked from product analytics for mobile apps (0 US searches/month in the evaluated dataset). The workflow fits because it can answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports.
• Ecommerce product teams: Ranked from product analytics for ecommerce (0 US searches/month in the evaluated dataset). The workflow fits because it can answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports.

What the agent does

This template can:

• Translate the business question: into metrics, dimensions, filters, segments, date windows, and a falsifiable hypothesis.
• Check GA4 property metadata: and compatibility before running reports.
• Retrieve only required GA4: standard, realtime, funnel, or pivot reports.
• Export the relevant Clarity: project data and document its available dimensions and limits.
• Use code interpreter to: clean, join only compatible aggregates, calculate deltas, and create charts/tables.
• Investigate alternative explanations such: as seasonality, tracking changes, mix shifts, and releases.
• Separate descriptive findings from: causal claims and recommend the next validating analysis or experiment.
• Save query definitions, source: windows, datasets, charts, and an executive report.

How the workflow works

1. Translate the business question into metrics, dimensions, filters, segments, date windows, and a falsifiable hypothesis.
2. Check GA4 property metadata and compatibility before running reports.
3. Retrieve only required GA4 standard, realtime, funnel, or pivot reports.
4. Export the relevant Clarity project data and document its available dimensions and limits.
5. Use code interpreter to clean, join only compatible aggregates, calculate deltas, and create charts/tables.
6. Investigate alternative explanations such as seasonality, tracking changes, mix shifts, and releases.
7. Save the evidence, approvals, files, and final result for review.

This is a single-agent workflow. The main agent owns research, planning, tool use, approvals, files, and the final response without passing routine stages between specialists.

Requirements and setup inputs

Use the template in a Project that contains the relevant business context. Connect only the accounts required for Google Analytics, Microsoft Clarity. The agent reads Project files before asking questions and stores confirmed reusable setup at agent scope.

• GA4 account/property and Clarity project: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• north-star and guardrail metrics: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• conversion/key-event definitions: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• funnel steps and important segments: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• timezone, currency, and reporting calendar: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• known tracking gaps and release dates: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.
• privacy thresholds and recurring report preferences: Confirm this only when it is not already available from Project context, public evidence, or a saved setup record.

No template-wide sample-data artifact is installed. The template installs its reusable methods and setup.md through skills, then creates customer-specific profiles, reports, charts, exports, and receipts from authorized evidence. Generated files can be inspected in Playground.

Apps and tools used

Connector actions are scoped to this Agent Build. A Project connection does not automatically grant every agent or every action access.

Practical use cases

First setup and baseline

SaaS product teams can use the template to answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: saas product teams.

Focused analysis or production run

Startups can use the template to answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: startups.

Ongoing review and iteration

Mobile app teams can use the template to answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: mobile app teams.

Safe edge-case handling

Ecommerce product teams can use the template to answer product and website questions with reproducible analytics, explain uncertainty, and produce useful charts and reports. The saved setup and evidence files reduce repeated onboarding while keeping unknowns visible.

Best for: ecommerce product teams.

Example prompts and outputs

Example prompt: core workflow

Why did signup conversion fall this month compared with last month?

Example output: A reproducible report with query definitions, source windows, KPI deltas, charts, caveats, and next experiments. The actual numbers, sources, files, and connector receipts depend on the user's authorized data.

Example prompt: safety or limitation check

Investigate the drop without exposing user-level personal information or claiming causality.

Expected behavior: the agent follows this boundary, preserves useful local work, and does not claim an unsupported or unapproved external action.

Why use this template

• Research happens before questions: the agent inspects Project context, saved setup, and available evidence before requesting unresolved choices.
• The method stays maintainable: detailed repeatable steps live in human-readable skills instead of one oversized agent prompt.
• External actions stay reviewable: connector scopes, approval boundaries, and returned identifiers are explicit.
• Files carry the detail: reports, evidence, drafts, charts, and receipts remain inspectable instead of being lost in a long chat response.
• The workflow remains editable: teams can refine one agent, skill, tool scope, or handoff at a time and retest it.

Related templates

• AI Database Q&A Analyst: Translates business questions into bounded read-only SQL and returns validated answers, tables, and charts.
• Google Ads Performance Manager: Audits live Google Ads performance, checks search demand, and turns evidence into approval-controlled optimization actions.
• Meta Ads Performance Manager: Diagnoses campaign, audience, placement, and creative performance and proposes measurable Meta Ads improvements.
• Cross-Channel Social Media Strategist: Combines channel evidence into one coordinated strategy, calendar, KPI plan, and optional content package.