Data Report Generation: a Tokeny case study

Prepare the inputs

Create a separate workspace in Tokeny, download and unpack the sample inputs, then select a model that supports tools. The sample uses synthetic data or the public sources named in the article.

sales.csv

Download sample inputs

Send the task to Tokeny

The original task was executed in Chinese. Copying these instructions reproduces the same task; the results below include an English report.

把销售原始数据制成 Excel 报表，包含金额公式、渠道汇总、图表、冻结表头和条件格式，并提供独立核对值。

交付文件：report.xlsx、totals.json。
验收要点：
- 金额公式存在
- 合计 5064
- 有图表和条件格式
这是使用合成演示输入或指定公开资料的真实操作案例。请先读取工作空间输入，再实际生成文件并自检。所有写入、脚本与临时服务限于当前工作空间；临时服务只监听 127.0.0.1，执行后关闭；不触达外部收件人、不发布、不付款、不更改系统设置，不调用子智能体。需要公开资料时可读取给定 URL。只启用完成任务必需的工具。另写 report.md（中文）和 report.en.md（英文），简洁、完整，包含输入、处理步骤、真实结果、检查方式和局限；失败或未验证部分如实记录，不能宣称成功。最终回复用中文列出产物、关键结果与待核实项。
排版检查：Word 主标题仅出现一次，标题为黑色且与后续正文或表格保持同页；Excel 表头和长文字不能被窄列截断，合理设置列宽、换行、行高；HTML 在 390px 视口不能整页横向溢出。报告没有固定字数要求，不要为字数反复改写。

The recorded run used an isolated demonstration workspace. Review the commands and file paths before approving operations in your own workspace.

What actually ran

The task was submitted through the Tokeny input box. An online model read the inputs and executed tools. This run covers the local sample task and its actual files. Results and checks are recorded below.

The actual Tokeny 1.7.8 session and files for Data Report Generation. Open the image at full size.

A preview of the actual generated file included in the download.

Results and verification

Input

File: sales.csv
Content: 6 sales-detail rows with date, channel, product, quantity, and unit price.
Source: synthetic demonstration input supplied in the current workspace.

Processing

Read the CSV as UTF-8 and parsed quantity, unit price, and channel fields.
Wrote the source rows to the 销售明细 worksheet. The amount column uses =Drow*Erow; the grand total uses =SUM(F2:F7).
Added a 渠道汇总 worksheet with SUMIF formulas for orders, quantity, amount, and share by channel, plus a column chart.
Added an independent calculation in the 独立核对 worksheet and totals.json, so verification does not depend on an Excel formula cache.
Applied frozen header panes, practical column widths, wrapping, borders, number formats, and amount/quantity conditional formatting.

Actual Results

Detail rows: 6
Total quantity: 36
Total sales amount: 5064
官网: 3 orders, 22 units, 3378
社群: 3 orders, 14 units, 1686
Target total 5064: matches
Excel charts: 1 channel-amount column chart
Conditional-formatting ranges: 2
Frozen header panes: A2 on all three worksheets

Verification

Reopened report.xlsx and checked that detail amount, grand-total, and channel-summary formulas exist.
Inspected workbook structure for the chart, conditional formatting, and frozen panes.
Read totals.json and confirmed total_amount=5064.0 and matches_expected=true.
Checked column widths and wrapping so headers and long text are not clipped by narrow columns.

Limitations

openpyxl writes formulas but does not calculate their cached values. Independent values are therefore provided in totals.json and 独立核对; Excel will recalculate on open.
No Word or HTML file was requested or generated, so the Word same-page title check and 390px HTML overflow check are not applicable.

Download and inspect the outputs

The archive contains the files created during this run. Use these checks when adapting the example to your own data.

Reconcile the reported results against the downloadable sample inputs.
Open the generated files and check the contents relevant to your task.
Review the limitations and any unverified steps in the report.

report.xlsx · 10 KBtotals.json · 1 KBreport.md · 2 KBreport.en.md · 2 KB

Download actual outputs