How it works
From raw CSV to board-ready PowerPoint in four steps — with a data-integrity pipeline that makes hallucinated numbers structurally impossible, not just unlikely.
The walkthrough
Drop in a CSV or Excel file containing your business metrics. Our system automatically detects the schema and structure.
The intelligence layer analyzes column meanings, identifies business domain, and surfaces initial insights with confidence scores.
You validate or correct the AI's interpretation. Low confidence items require your input before proceeding.
Once understanding is validated, the system generates a PowerPoint deck with charts, insights, and narrative that match your data precisely.
The trust problem, solved in code
Generative AI produces plausible output — including plausible, wrong numbers. In front of a board or an investor, that's disqualifying. InsightNarrative's pipeline makes a hallucinated figure structurally impossible, not just unlikely.
Your file is parsed deterministically and every numeric value is captured in an immutable snapshot — before any AI is involved.
The AI interprets your metrics using that snapshot as its only source of truth, labeling each interpretation with a confidence score.
Before a single slide is generated, you review and correct how the AI understood your data. Low-confidence readings require your sign-off.
Every number the AI returns is diffed against your file's actual values in application code. Anything that doesn't match is rejected.
Validation is code, not a prompt — AI output is checked against your file's actual values before anything ships. Your numeric data is never modified.
The output
The result is a standard PPTX file with charts, KPIs, and an executive narrative — editable in PowerPoint like any deck your team makes, with every figure traceable to your file.
Slide 2 of 8
MRR · Jun 2024
$85,000
Verified · row 6Churn · Jun 2024
1.9%
Verified · row 6Every figure on this slide traces to a cell in the uploaded file — validated in code before export.
Flexible Input
Our AI understands different data formats automatically — no restructuring needed.
Multiple metrics tracked over time periods
| Period | Revenue | Customers | Churn |
|---|---|---|---|
| Jan 2024 | $45K | 120 | 2.3% |
| Feb 2024 | $52K | 145 | 1.8% |
| Mar 2024 | $61K | 168 | 2.1% |
Best for: Monthly SaaS metrics, quarterly reports, weekly KPIs
Point-in-time metrics as key-value pairs
| Metric | Value |
|---|---|
| Total Revenue | $2.75M |
| ARR | $25.2M |
| Team Size | 28 |
| Runway | 10 mo |
Best for: Fundraising decks, board reports, status overviews
Related metrics with different units side by side
| Week | New Users | Active | NPS |
|---|---|---|---|
| Week 1 | 1,250 | 8,500 | 42 |
| Week 2 | 1,420 | 9,200 | 45 |
| Week 3 | 1,680 | 10,500 | 48 |
Best for: Product analytics, growth tracking, cohort analysis
Automatic detection
AI identifies your data structure and column meanings without manual configuration.
Mixed units supported
Combine percentages, currency, counts, and ratios in the same dataset.
CSV & Excel ready
Upload .csv, .xlsx, or .xls files directly from your spreadsheet tools.
FAQ
The file is parsed deterministically — CSV, XLSX, and XLS are supported up to 10MB — and its structure, time columns, and granularity are detected before any AI is involved. Every numeric value is captured in an immutable snapshot that becomes the single source of truth for the rest of the pipeline.
Two ways. First, the AI only ever sees your data through the snapshot, and its role is limited to interpretation and narrative. Second, after generation, every numeric value the AI returns is compared against the snapshot in application code. Values that don't match your file are rejected — validation is code, not another AI call.
Before slides are generated, InsightNarrative shows you how it interpreted your data — column meanings, business domain, and initial insights — each labeled with a confidence score. Low-confidence interpretations require your explicit confirmation or correction before generation proceeds.
Yes. You can give feedback and regenerate single slides in the editor. Feedback is screened deterministically so that requests to alter numeric values are blocked — narrative changes are welcome, data changes are not possible.
Upload your data and check the output against your own spreadsheet. Every number in the deck is validated in code — that's the point.