Reconcile two exports and explain every mismatch

Compare datasets by agreed keys and tolerances, preserving duplicates and separating missing rows from value differences.

PLPromptByte Library@promptbytePublished Sep 8

TextData & Analysis #csv #data quality #reconciliation

Version 1 of 1 · published Sep 8, 2026Version 1 · only version

Example output

No public result for version 1 yet

Nobody has shared what a model actually produced from this exact version, and PromptByte never generates examples itself. Run the prompt and add yours to fill this in.

Add your result

Prompt

Version 1 · 3 variables · 3 required

Fill in the values below — the customized prompt updates as you type. marks a required value.

Export a{{export_a}}

First dataset and its source/time-window description. Default: Illustrative CSV: order_id,total A1,25.00 A2,10.00 A3,18.50

Export b{{export_b}}

Second dataset and its source/time-window description. Default: Illustrative CSV: order_id,total A1,25.00 A2,10.50 A4,18.50

Reconciliation rules{{reconciliation_rules}}

Keys, units, exclusions and allowed tolerances. Default: One row per order. Match exact order_id. Totals are USD; allow an absolute difference no greater than 0.01. Treat files as samples.

Customized prompt

live preview

Resolved user prompt19 lines

Reconcile these two datasets.

Export A: Illustrative CSV:
order_id,total
A1,25.00
A2,10.00
A3,18.50
Export B: Illustrative CSV:
order_id,total
A1,25.00
A2,10.50
A4,18.50
Matching and comparison rules: One row per order. Match exact order_id. Totals are USD; allow an absolute difference no greater than 0.01. Treat files as samples.

Confirm the row grain, keys, time window and units before comparing. Test whether the proposed keys are unique in each supplied dataset; do not silently collapse duplicates.

Report matched rows, rows present only in A, rows present only in B, conflicting values and ambiguous matches. For each mismatch, show the key, both original values, the applicable comparison rule and a likely investigation step. Apply tolerances only where specified.

Provide counts that reconcile to the input row totals and explain how duplicate or excluded records affect those counts. Preserve original data and do not merge uncertain identities by guesswork. If the inputs are only samples, label all findings as sample-scoped.

Resultsfor version 1

All models

Version 1 · only version

No public examples yet for version 1

Results show what a model actually produced from this exact version. Share yours to help others decide.

code · sql
```
**Assumptions**

- `order_items.order_id` joins to `orders.id`, and `products.category_id` joins to `categories.id`. These are inferred from the naming convention, since no foreign keys were listed.
- "Last 90 days" is measured against `orders.order_date` relative to today, inclusive of today.
- Revenue is `quantity * unit_price` summed over line items; there is no discount or tax column in the schema, so none is applied.
- Cancelled orders are excluded. If `status` uses different values than `'
```
Code preview: **Assumptions** - `order_items.order_id` joins to `orders.id`, and `products.category_id` joins to `categories.id`. These are inferred from the naming convention, since no foreign keys were listed. - "Last 90 days" is measured against `orders.order_date` relative to today, inclusive of today. - Revenue is `quantity * unit_price` summed over line items; there is no discount or tax column in the schema, so none is applied. - Cancelled orders are excluded. If `status` uses different values than `'
SQL query generator from a plain-English request
Converts a natural-language data requirement plus a table schema into a syntactically correct SQL query for a named database, with its assumptions stated up front.
CodeData & Analysis OpenAI · GPT-5.5
PL@promptbyteAug 27
Score 1
0 comments1 results
No public results yet
Audit SQL joins for duplicate rows and inflated totals
Check join cardinality and aggregation grain to explain duplicate rows or double-counted measures before changing a reporting query.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Design a forecast backtest that respects time and information
Specify temporal evaluation, leakage checks, baselines and business-relevant metrics before judging a forecasting model.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Critique an existing chart for misleading interpretation
Review a chart's scales, labels, aggregation and claims, separating visual issues from data questions that need verification.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Classify comment sentiment with traceable evidence
Label supplied comments consistently while preserving mixed opinions, unclear cases and the exact words supporting each label.
TextData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results
No public results yet
Reshape a wide CSV into tidy records without losing meaning
Produce a deterministic transformation from repeated measure columns to tidy rows with explicit keys, types and missing-value rules.
CodeData & Analysis
PL@promptbyteSep 8
Score 0
0 comments0 results

Browse Data & Analysis

Example output

Prompt

Customized prompt

Resultsfor version 1

Related prompts

SQL query generator from a plain-English request

Audit SQL joins for duplicate rows and inflated totals

Design a forecast backtest that respects time and information

Critique an existing chart for misleading interpretation

Classify comment sentiment with traceable evidence

Reshape a wide CSV into tidy records without losing meaning

Discussion 0