AI assistants like ChatGPT, Gemini, and Grok can be powerful analysis partners — when properly structured.

Because Godcaster exports include structural nuances (attribution fields, device indicators, session reconstruction limits, timestamp precision, etc.), how you prompt the AI directly affects accuracy.

To produce consistent, board-ready reports, Godcaster recommends a Two-Step Reporting Method.

Before asking for narrative interpretation, first instruct your AI assistant to:

• Confirm CSV column headers
• Normalize header spacing if necessary
• List all distinct values in the Actioncolumn
• Confirm whether Episode and Program identifiers exist on Support and Share events
• Explicitly state structural limitations
• Compute all KPIs before summarizing
• Show calculation logic
• Reconstruct sessions if necessary

This prevents:

• Fabricated attribution
• Missed structural limitations
• Incorrect session reconstruction
• Overstated conclusions

After KPIs and limitations are verified, then ask the AI to:

• Produce a 1–2 page board-level executive summary
• Use only the verified metrics
• Avoid introducing new calculations
• Clearly explain any data constraints
• Identify 2–3 strategic opportunities

Separating computation from narrative improves reliability across AI tools.

1. Export your monthly performance CSV from the Godcaster dashboard
2. Open your AI assistant (ChatGPT, Gemini, etc.)
3. Upload the CSV
4. Copy Step 1 prompt below and run it
5. After results are generated, copy Step 2 prompt below and run it

Do not shorten the prompts. Structure ensures accuracy.

You are analyzing a monthly performance export (CSV) from our Godcaster digital station.

Before summarizing, first perform a Data Audit:

• List all column headers exactly as shown
  • Trim/normalize header spacing if needed
  • List all distinct values in the Action column
  • Confirm whether Episode and Program identifiers exist on Support and Share events
  • Identify any structural limitations

Rules:

• Analyze only the data provided
  • Do not fabricate missing attribution
  • Clearly state limitations
  • If session IDs are absent, reconstruct sessions by grouping events by IP + UserAgent chronologically and break sessions after 30 minutes of inactivity
  • If timestamps lack minute/second precision, state session reconstruction limitations

Now compute:

1. Total plays + resumes
2. Total shares
3. Total support clicks
4. Program-level rankings (top 10 by plays + resumes)
5. Episode-level rankings (if identifiers exist)
6. Device breakdown (Mobile / Desktop / Tablet)
7. Live → On-Demand transitions (if reconstructable)
8. Estimated unique listeners range using:
   • Unique IP count (low estimate)
   • Unique IP + UserAgent combinations (high estimate)

Show calculation logic for each KPI.
Do not write executive narrative yet.

END STEP 1 COPY

Using ONLY the verified metrics generated above:

Create a concise, board-level executive summary for [Station Name] for [Month, Year].

Include:

• Audience reach trends
  • Engagement strength (plays + shares)
  • Support/giving activity
  • Top-performing programs
  • Device usage patterns
  • Live → On-Demand behavior (if available)
  • 2–3 strategic opportunities
  • Plain-language explanation of data limitations

Do not introduce new calculations.
Do not overstate conclusions beyond what the data supports.

END STEP 2 COPY

Without structure, AI models may:

• Prioritize narrative over computation
• Infer missing attribution
• Skip session reconstruction
• Blend assumptions with verified metrics

With structure, AI becomes:

• A disciplined reporting assistant
• A KPI verification tool
• A board-ready narrative generator

AI assistants analyze only the CSV file you upload.

They do not:

• Access your dashboard
• Identify individual listeners
• Track personal identities

All insights are based solely on aggregated export data.

You already own the data.

Used correctly, AI helps you clearly see:

• What’s growing
• Where engagement is strongest
• Where giving intent exists
• How Live and On-Demand behavior interact
• Where leadership attention should focus next

Structured properly, AI becomes a strategic reporting partner — not just a summary tool.