Weekly-report exercise: was the completed change later reverted?

Build a claim-to-event ledger from fictional development records, checking reversals, drafts and work still in progress.

Execution environment and usage

AI / software

Gemini

Where to operate

Ordinary text chat in the Gemini consumer web app at gemini.google.com. This card uses manually supplied text only.

Getting started

  1. Prefer an adult personal Google account and check regional/account eligibility first. Do not buy a plan for this exercise.
  2. Paste the fictional fixture into ordinary chat, or substitute authorized de-identified short text. Connect no external services.
  3. Compare output with the human acceptance checks. Preserve errors, gaps and unknowns for review.

Setup and plan requirements

Official web documentation checked 2026-11-10 lists Hong Kong, Macau and Taiwan, plus Simplified, Traditional and Hong Kong Chinese and English. An adult personal account is our recommended exercise scope, not a claim that all child, school or work accounts qualify. Personal/school accounts generally require 13 or the local applicable age; work accounts have separate 18+, administrator and plan conditions. Child/Family Link documentation contains inconsistent wording and needs separate verification.

Prompt portability limits

Start with standard free access; no subscription is required for this card. Taiwan advertises NT$0/month for free access. Local Hong Kong/Macau paid prices are unverified, so no local paid price is promised. Compute limits vary with model, complexity and conversation length, including five-hour and weekly caps; no fixed number of prompts is guaranteed. Wait if limited rather than assuming an upgrade is needed. Mobile, API, CLI and the original automation have separate eligibility, account and cost requirements.

Usage limitations

Documentation review is not a test from the three regions. Prompts, account access, model output and the original full workflow were not tested. Use fictional or de-identified data, never confidential inputs; some data can receive human review. Disabling activity is not zero retention: relevant chats can remain for 72 hours and undergo safety review. A person must verify outputs; text advice is not execution.

Environment sources

適用情境 / When to use

Build a claim-to-event ledger from fictional development records, checking reversals, drafts and work still in progress. Adds a known-answer reversal fixture and a cutoff-state ledger, rather than merely rewriting activity as a post. Fictional fixture, not a real usage record: E1: Monday, PR41 merged an export feature. E2: Tuesday, issue52 marked in progress. E3: Wednesday, commitC9 fully reverted PR41. E4: Thursday, PR77 is an unmerged documentation draft. Cutoff is Friday; no deployment or user-impact evidence is supplied.

步驟 / Steps

  1. Preserve the input IDs and use the fictional fixture with the parameterized prompt in text chat.
  2. Human acceptance check: cite E1 and E3 together and mark the export change reverted; issue52 remains in progress and PR77 remains a draft. No deployment or productivity gain is established.
  3. If output fails a check, record the discrepancy and revise the request for human review. Never present an expected answer as observed model output.

提示詞 / Prompt

Using [event list, reporting window and timezone, audience, word limit], draft a report in [language/format]. First map each claim to event IDs, cutoff status, contrary evidence and unknowns. Apply reversals and reopenings chronologically. Do not equate merging with deployment, describe drafts as finished, or invent impact. Mark gaps for review; do not connect accounts or publish.

Fictional fixture, not a real usage record: E1: Monday, PR41 merged an export feature. E2: Tuesday, issue52 marked in progress. E3: Wednesday, commitC9 fully reverted PR41. E4: Thursday, PR77 is an unmerged documentation draft. Cutoff is Friday; no deployment or user-impact evidence is supplied.

留意事項 / Cautions

  • Platform and region: ordinary Gemini web text chat. Official lists include Hong Kong, Macau, Taiwan, Chinese variants and English. Documentation checked 2026-11-10; local connections were not tested.
  • Plan and account: prefer an adult personal account. Standard free access is a starting point, with variable usage caps and no required subscription. Taiwan advertises NT$0/month free access; Hong Kong/Macau paid prices are unverified. No particular model or prompt count is guaranteed. Work, school and child accounts need separate checks.
  • No original toolchain is connected. Web availability does not establish mobile, API, CLI or original-automation access. Never supply confidential data. Activity-off chats can still remain for 72 hours and receive safety review.
  • Do not supply private repositories, unreleased plans, keys or colleagues’ personal data.

來源限制 / Evidence limits

The author describes GitHub collection, Gemini narration, Notion and a DEV.to draft. A draft is not a public article; no efficiency or reliability has been independently established. Source publication: exact date unverified; checked: 2026-11-10. The original source provides inspiration, not validation of this exercise. Its toolchain, regional services and plans have not been reproduced. This card uses only the documented Gemini web text environment.

流程說明 / Workflow note

Original editorial adaptation, not a newly discovered use case or the source author’s verbatim workflow. Source-reported outcomes do not guarantee this exercise. Prompts were not tested. Adapted from this existing case: https://hkfrees.com/ai/case/reported-github-narrative-attribution/?lang=en Adds a known-answer reversal fixture and a cutoff-state ledger, rather than merely rewriting activity as a post. Open this card’s title for the official environment-source links and human acceptance steps on its full case page.

原始工具組合 / Original tool stack

Gemini; Mastra; GitHub; Notion; DEV.to

Source checked: 2026-11-10

Turning Weekly GitHub Activity Into Blog Posts on Notion + DEV.to