Lesson Plan Generation: a Tokeny case study
Auto-generate lesson plans from syllabi with teaching objectives, activity designs, and assessment methods. Follow the recorded task, execution screenshots, actual files and verification notes.
By the Tokeny team · Windows · Tokeny 1.7.8 · gpt-6-sol
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.
- class.md
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.
为初中生设计 45 分钟的统计图入门课，包含可观察学习目标、课堂活动、差异化支持、形成性评价和课后题，输出 Word。 交付文件：lesson.docx、activities.md。 验收要点： - 活动总时长 45 分钟 - 评价与目标对应 - 适合给定设备 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。
Follow-up instructions after review (1)
独立 Microsoft Word 原生分页检查发现 lesson.docx：课堂流程表在第2页续表没有表头；评价记录表第3页只剩最后一行且无表头。请设置所有跨页表格重复表头、单行不拆分，并让仅数行的形成性评价记录表连同标题完整同页（必要时在标题前分页）。保留45分钟教学内容与数字，更新真实验证报告。
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.
Results and verification
Inputs
I read class.md and ENVIRONMENT.md and revised the existing lesson.docx in response to user-reported Microsoft Word pagination defects. The class has 32 middle-school students who have studied the mean but not statistical graphs. Only a projector and paper-and-pencil materials are available. The lesson covers bar versus line graphs, axes, and misleading truncated axes. In the earlier file, the classroom-flow table lacked a header on its continuation page, and the assessment table had only its last row on page 3 without a header.
Processing Steps
- Kept the six lesson segments totaling 45 minutes, their data, objectives, assessment, differentiation, and homework unchanged.
- Marked the first row of each of the three tables as a repeating header and prohibited every row from splitting across pages.
- Started the formative-assessment heading on a new page, kept it with the table, and linked the short table's earlier rows to their successors.
- Regenerated
lesson.docxand checked its properties and actual page locations in Microsoft Word.
Actual Results and Checks
- Deliverables:
lesson.docx,activities.md,report.md, andreport.en.md. Only the Word plan and the two reports changed in this revision; the activity handout did not. - Extracted lesson intervals of 0–5, 5–13, 13–25, 25–33, 33–40, and 40–45 minutes, totaling 45 minutes. The three tables have 7, 5, and 4 rows including headers. DOCX ZIP integrity passed.
- DOCX properties confirm repeating headers on all three tables, no row splitting on all 16 rows, and page-break-before/keep-with-next for the assessment heading. The first three assessment rows are kept with their successors.
- In a native Microsoft Word pagination check, the file has 3 pages. The classroom-flow table has its header and first four activity rows on page 1 and its final two activity rows on page 2. Word recognizes its first row as a repeating header. Every table row occupies a single page. The assessment heading, first row, and last row are all on page 3; that table remains together.
- The objective-to-assessment mapping and projector-and-paper equipment fit are preserved.
Limitations
The native Word check verified page locations and table properties, but not pixel-by-pixel appearance or live classroom projection and pacing. The separate DOCX schema validator previously could not run because a dependency was unavailable; DOCX parsing, ZIP integrity, and native Word pagination checks are reported instead, not as a successful run of that validator.
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.