Marketing Plan Creation: a Tokeny case study
Generate marketing plans with channel selection, budget allocation, and scheduling based on product and audience. 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.
- product-brief.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.
为产品制定 4 周试运营营销计划，预算 12000 元，包含渠道选择、周计划、负责人、衡量指标与停止条件，未知效果只能作为实验目标。 交付文件：marketing-plan.md、budget.csv。 验收要点： - 预算合计 12000 - 4 周各有动作与指标 - 不保证获客和转化效果 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.
Results and verification
Inputs
Read product-brief.md, ENVIRONMENT.md, and .tokeny/manifest.json from the current workspace.
The product brief identifies “Pinecone Task Board” as a fictional demo product for teams of 3–10 people. Its known features are task lists, assignees, due dates, and CSV export. The free tier supports up to 3 people and the team tier is 29 RMB per person per month. It has no mobile app, AI scheduling, or third-party authentication. The brief prohibits fabricated testimonials, sales figures, and third-party endorsements.
Processing Steps
- Designed a four-week trial operation as an experiment based on the known product features and limitations.
- Selected search ads, WeChat/ Zhihu content tests, small-team community cooperation, and online demos/interviews, with tracking and stop conditions.
- Split the fixed 12,000 RMB budget into auditable line items.
- Added weekly actions, owners, experimental metrics, and stop conditions.
- Generated the Chinese plan, CSV budget, and bilingual reports.
Actual Results
- Created
marketing-plan.mdwith the trial boundaries, five budget/channel categories, four weekly action plans, owners, metrics, stop conditions, and explicit non-guarantee language. - Created
budget.csvwith 10 budget detail rows and a target total of 12,000 RMB. - Created
report.mdas the Chinese report. - No ads were run, no communities were contacted, no demo was held, no payment was made, and no content was published. Therefore, there are no real acquisition, registration, activation, conversion, or return-on-investment results to report.
Checks
- Reviewed the plan for Week 1 through Week 4 actions and metrics, with stop conditions in every week.
- Read the CSV amount column and calculated the total, targeting 12,000 RMB; checked that the detail total matches the summary row.
- Checked that the plan states acquisition and conversion are not guaranteed and that unknown outcomes are framed as experimental goals or “cannot be determined.”
- Checked that the product limitations and the prohibition on fabricated endorsements are reflected in the plan.
Limitations and Open Items
- The only source was a synthetic demo brief. There is no real audience size, historical campaign data, landing-page data, or channel quotation; the budget is an experimental allocation, not a purchase quote.
- Channel performance, cost, registration, activation, export intent, and payment have not occurred and must be verified during execution using UTM data, sample sizes, and the stated stop conditions.
- This report records file generation and static checks only. It does not claim that the marketing experiment succeeded.
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.