1# Review budget vs. actuals | Codex use cases1---
2 2name: Review budget vs. actuals
3Codex use cases3tagline: Turn plan, actuals, and close notes into a variance workbook.
4 4summary: Give ChatGPT a budget, actuals export, and close notes, then ask it to
55 map actuals to plan, calculate variances, flag reconciliation issues, and
6 6 separate supported explanations from open finance questions.
77skills:
8 8 - token: $spreadsheets
9Codex use case9 description: Inspect spreadsheet inputs, clean and map rows, create variance
10 10 tables, and produce reviewable workbook outputs.
11# Review budget vs. actuals11bestFor:
12 12 - Month-end reviews that compare budget plans with actual spend exports.
13Turn plan, actuals, and close notes into a variance workbook.13 - Finance teams preparing leadership commentary from GL, spend, or department
14 14 actuals.
15Difficulty **Easy**15 - Workbooks where category mapping, tie-outs, and unsupported explanations
16 16 need review.
17Time horizon **30m**17starterPrompt:
18 18 title: Review budget vs. actuals
19Give Codex a budget, actuals export, and close notes, then ask it to map actuals to plan, calculate variances, flag reconciliation issues, and separate supported explanations from open finance questions.19 body: >-
20 20 Use $spreadsheets to update the budget vs. actuals review from the attached
21## Best for21 files.
22 22
23- Month-end reviews that compare budget plans with actual spend exports.23
24- Finance teams preparing leadership commentary from GL, spend, or department actuals.24 Compare actuals to plan, map actuals to the right budget categories,
25- Workbooks where category mapping, tie-outs, and unsupported explanations need review.25 summarize the major variances, and prepare a clean review view as an
26 26 editable .xlsx workbook.
27# Contents27
28 28
29[← All use cases](https://developers.openai.com/codex/use-cases)29 Preserve the raw inputs, use formulas for dollar and percentage variance
30 30 calculations, and flag categories that do not map cleanly instead of forcing
31Copy page [Export as PDF](https://developers.openai.com/codex/use-cases/budget-vs-actuals-review/?export=pdf)31 a match. Use account type to determine favorable or unfavorable variance:
32 32 revenue above plan is favorable, while expense above plan is unfavorable.
33Give Codex a budget, actuals export, and close notes, then ask it to map actuals to plan, calculate variances, flag reconciliation issues, and separate supported explanations from open finance questions.33 suggestedEffort: medium
34 34relatedLinks:
35Easy35 - label: Agent skills
36 36 url: /codex/build-skills
3730m37---
38
39Related links
40
41[Agent skills](https://developers.openai.com/codex/skills)
42
43## Best for
44
45- Month-end reviews that compare budget plans with actual spend exports.
46- Finance teams preparing leadership commentary from GL, spend, or department actuals.
47- Workbooks where category mapping, tie-outs, and unsupported explanations need review.
48
49## Skills & Plugins
50
51- Spreadsheets
52
53 Inspect spreadsheet inputs, clean and map rows, create variance tables, and produce reviewable workbook outputs.
54
55| Skill | Why use it |
56| --- | --- |
57| Spreadsheets | Inspect spreadsheet inputs, clean and map rows, create variance tables, and produce reviewable workbook outputs. |
58
59## Starter prompt
60
61Use $spreadsheets to update the budget vs. actuals review from the attached files.
62Compare actuals to plan, map actuals to the right budget categories, summarize the major variances, and prepare a clean review view as an editable .xlsx workbook.
63Preserve the raw inputs, use formulas for dollar and percentage variance calculations, and flag categories that do not map cleanly instead of forcing a match. Use account type to determine favorable or unfavorable variance: revenue above plan is favorable, while expense above plan is unfavorable.
64
65Open in the Codex app
66
67Use $spreadsheets to update the budget vs. actuals review from the attached files.
68Compare actuals to plan, map actuals to the right budget categories, summarize the major variances, and prepare a clean review view as an editable .xlsx workbook.
69Preserve the raw inputs, use formulas for dollar and percentage variance calculations, and flag categories that do not map cleanly instead of forcing a match. Use account type to determine favorable or unfavorable variance: revenue above plan is favorable, while expense above plan is unfavorable.
70 38
71## Introduction39## Introduction
72 40
73If you’re working on a budget and want to review the variances or inspect any issues, Codex can help you create a fully functional review workbook you can work with.41If you're working on a budget and want to review the variances or inspect any issues, ChatGPT can help you create a fully functional review workbook you can work with.
74 42
75Attach the budget plan, actuals export, and close notes, then ask Codex for an editable review workbook. Codex can preserve the raw inputs, map actuals to plan, calculate variances, and create a summary view you can inspect in the thread.43Attach the budget plan, actuals export, and close notes, then ask ChatGPT for an editable review workbook. ChatGPT can preserve the raw inputs, map actuals to plan, calculate variances, and create a summary view you can inspect in the task.
76
77[
78Your browser does not support the video tag.
79](https://openaiassets.blob.core.windows.net/$web/codex/docs/developers-website/use-cases/budgets-vs-actuals.mp4)
80 44
81## Create the review workbook45## Create the review workbook
82 46
831. Attach the budget plan, actuals export, and close notes, or provide exact file references along with the source.
842. Run the starter prompt and ask for an editable `.xlsx` workbook.
853. Open the workbook in Codex. Expand it into the full-screen view to inspect the raw inputs, mappings, variance formulas, and summary tab.
864. Continue in the same thread to fix category mappings, add department cuts, or draft the finance summary.
87
88If the source files are in a connected app, mention the exact files or folder. Avoid asking Codex to search a broad Drive or workspace when the review should use specific finance sources. When the workbook appears in the thread, open it in Codex and expand it full-screen to review the raw inputs, mappings, variance formulas, and summary tab before asking for revisions.
89
90## Check the variances
91
92Before sharing the workbook, ask Codex to audit the categories, formulas, and variance explanations.
93
94Check the budget vs. actuals review before I share it.
95List:
96- the most material unfavorable variances by dollar impact
97- the most material favorable variances by dollar impact
98- categories that may be mapped incorrectly
99- accounts where the favorable or unfavorable sign convention is unclear
100- explanations supported by the close notes
101- explanations that need human review
102- formula or tie-out issues in the workbook
103Fix safe formatting or formula issues, then list anything finance should resolve before leadership review.
104
105## Related use cases
106
107[
108
109### Forecast cash flow
110 47
111Give Codex cash-flow inputs and model constraints, then ask it to create an editable...
112 48
113Data Knowledge Work](https://developers.openai.com/codex/use-cases/cash-flow-forecast)[491. Attach the budget plan, actuals export, and close notes, or provide exact file references along with the source.
114 502. Run the starter prompt and ask for an editable `.xlsx` workbook.
115### Model a DCF valuation513. Open the workbook in ChatGPT. Expand it into the full-screen view to inspect the raw inputs, mappings, variance formulas, and summary tab.
116 524. Continue in the same task to fix category mappings, add department cuts, or draft the finance summary.
117Attach historical financials, valuation assumptions, and modeling notes, then ask Codex for...
118 53
119Data Knowledge Work](https://developers.openai.com/codex/use-cases/dcf-model)[
120 54
121### Clean and prepare messy data
122 55
123Drag in or mention a messy CSV or spreadsheet, describe the problems you see, and ask Codex...56If the source files are in a connected app, mention the exact files or folder. Avoid asking ChatGPT to search a broad Drive or workspace when the review should use specific finance sources. When the workbook appears in the task, open it and expand it full-screen to review the raw inputs, mappings, variance formulas, and summary tab before asking for revisions.
124 57
125Data Knowledge Work](https://developers.openai.com/codex/use-cases/clean-messy-data)58## Check the variances
126 59
60Before sharing the workbook, ask ChatGPT to audit the categories, formulas, and variance explanations.