# Lab: take Nisha's method to 2.0 (/claude-and-chatgpt-2/case-1-nishas-ai-team/lab-take-nishas-method-to-2-0) --- type: Document title: "Lab: take Nisha's method to 2.0" description: "Run Nisha's six steps again for one chapter of her book, this time with a project, a writer thread and a reviewer thread, an overnight scheduled draft, ChatGPT Work as the independent reviewer, and a second signature that only you can give." status: stable order: 0.565 ksor: owner: team:panaversity audience: [ public ] approval: by: process:panaversity at: 2026-11-10T14:35:08Z chapter: "F00C" part: Front expert_status: required concepts: [ "Method to 2.0" ] last_verified: 2026-11-09 sources: - id: claude-projects title: "Let Claude coordinate ongoing work with Projects (Anthropic, verified 2026-11-09)" resource: https://code.claude.com/docs/en/claude-projects - id: cloud-scheduled-tasks title: "Automate work with scheduled tasks (Anthropic, verified 2026-11-09)" resource: https://code.claude.com/docs/en/routines - id: desktop-scheduled-tasks title: "Schedule recurring tasks in Claude Code Desktop (Anthropic, verified 2026-11-09)" resource: https://code.claude.com/docs/en/desktop-scheduled-tasks - id: tour-chatgpt title: "The Tour: ChatGPT" resource: "../tour/chatgpt.md" - id: tour-chatgpt-perms title: "The Tour: ChatGPT, Permissions and governance" resource: "../tour/chatgpt.md#permissions-and-governance" generated: at: 2026-11-10T14:35:08Z by: process:panaversity trust_tier: unverified build_id: sha256:46fd53c5d7ab1c14f6347908d45c9fdaecda4d914439923ee878bdcecd57803e dirty: true ksor_version: 0.0.60 --- > [!IMPORTANT] > **Your exercise, not Nisha's.** Nisha did not use threads, scheduled tasks, ChatGPT Work or a `final` folder. Her recorded evening of November 8, 2026 is in the story pages and the [exhibits](exhibits.md). This lab asks *you* to try the newer features, so nothing you record here is part of her case. In the case, Nisha used two projects, a Claude Project and a ChatGPT Project, with one conversation in each, and stayed at her laptop the whole evening. That is the first step of the ladder in [From helper to AI Worker](../behind-the-screen/from-helper-to-ai-worker.md): a helper, used by a person who is present. In this lab you run her six steps again for **one chapter** of her book. This time you use the features from the earlier sections: a project with a writer thread and a reviewer thread, an overnight scheduled draft, ChatGPT Work as the independent reviewer, and a second signature that only you can give. This page explains each part, what it is for and the decisions you make. The exact clicks, the fallbacks and the docs' own words are in the **[lab guide](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md)** in the starter kit. Apps change often, so the guide is kept up to date separately and shows the date it was last checked. ![Evening 1.0 versus lab 2.0. Six parts of the work, before and after. Nisha's evening used two projects with one conversation each, one laptop and one evening. The lab uses one project, two threads, one evening and one morning. Writing: one conversation in a Claude Project becomes a writer thread. Grading: the same conversation grading itself becomes a separate reviewer thread. Overnight: nothing ran while Nisha slept, and in the lab a scheduled task drafts at 1 a.m. Second opinion: one conversation in a ChatGPT Project becomes ChatGPT Work. Record: files she saved and her diary become the Library and your version log. Final yes: her decision written in a conversation becomes a file only you can move to the final folder. The overnight row and the final yes row are gold, because they are the two big changes: work that runs without you, and a rule that is enforced. The callout says your judgment stays in every step, and the tools change where the work lives.](img/evening-1-0-versus-lab-2-0.png) > [!TIP] > **Minimum steps, on one screen** > > 1. Write a brief and paste it as the project instructions. > 2. Turn off every connector that can send. Lock GitHub. > 3. Test the lock: ask a thread to email or share a test file, and record that it cannot. > 4. Ask for a 1 a.m. draft. Empty the task's connectors. > 5. In the morning, fix the draft and add it back with **Add**. > 6. A new reviewer thread grades it. A new writer thread improves it. > 7. Check the facts yourself. Only you move the last version into `final`. ## Lab at a glance You need two sittings: one evening (about 1 hour 25 minutes) and the next morning (about 2 hours 40 minutes). Each part below gives its own time. **Evening checklist (about 1 hour 25 minutes)** - [ ] Part 1. Write the brief. - [ ] Part 2. Create the project, paste the brief, upload version 6. - [ ] Part 2. Turn off every connector that can send. Lock GitHub. - [ ] Part 2. Run the enforcement test and record the result. - [ ] Part 3. Ask for the 1 a.m. draft. Empty the scheduled task's connectors. Close your laptop. **Morning checklist (about 2 hours 40 minutes)** - [ ] Part 3. Read the 1 a.m. draft. Run the enforcement test on the 1 a.m. thread. Save your edit as version 2. Tell Claude what to remember. - [ ] Part 4. Start a new reviewer thread. Start a new writer thread. Get version 3. - [ ] Part 5. ChatGPT Work reviews version 3. Sort its points. - [ ] Part 6. The writer makes version 4. A new reviewer thread grades it. - [ ] Part 7. Check the facts. Make version 5. Move it into `final` yourself. - [ ] Part 8. Reflect and compare. - [ ] Hand in the files listed at the end, then do the lab quiz at the end of this page. > [!NOTE] > **Short path (about 2 hours 50 minutes)** > > Short on time? Do Parts 1 to 4 and Part 7 only: the brief (30 minutes), the project, connector check and enforcement test (40), the overnight draft (15 in the evening, 25 in the morning), the reviewer thread (30), and the fact check and second signature (30). You skip ChatGPT's review, the writer's second round and the written reflection, so you practice every Claude 2.0 step but not the independent review. In Part 7, start from `chapter-7-v3.md` instead of version 4, and ask the morning writer thread for its list of unchecked facts first. Hand in the items for those parts, and one line saying you took the short path. ### Words to know - **Thread:** one job inside a project, done by its own Claude session. The writer and the reviewer are two threads. - **Project instructions and project memory:** the shared binder from [Projects: one team lead, many desks](../behind-the-screen/projects-one-team-lead-many-desks.md). Instructions are the rules sent to every new thread. This project exists for one job, so they hold your brief for that job too. Memory is notes Claude writes when you ask it to remember something. - **Library:** the shared shelf. It keeps the files you add and every file the threads make. - **Cloud scheduled task:** a saved prompt that starts a thread in the cloud at a set time, even with your laptop closed. - **Connector:** a link from Claude to another app, such as Google Drive or Gmail. - **Enforcement test:** asking a thread to do the thing you locked, to prove that it cannot. A screenshot of a setting shows what you chose. The test shows what the thread can actually do. ## Before you start You need: - **Claude,** with projects if your plan has them, and **ChatGPT,** with the Work toggle if your app has it. The [lab guide](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#where-to-find-it) says where to find each feature. - **The starter kit:** download [nisha-lab-case-1.zip](https://github.com/panaversity/agentfactory-v2-resources/releases/latest/download/nisha-lab-case-1.zip). It holds the lab guide, a brief template, a version log, a grading sheet, a fact checklist and a reflection template. - **Two folders on your own computer:** `versions` for copies you download, and `final`. Only you will put files in `final`. The chapter you will plan is **Chapter 7, Inventory**, from [Exhibit 7](exhibits.md#exhibit-7-the-final-result-table-of-contents-version-6). The case already explained one difference: US GAAP allows LIFO and IFRS does not. Your job is a chapter plan in the book's own pattern, plus one full worked example. Use made-up numbers in your worked example, as Nisha did. Do not paste real company data. **If a feature is missing,** use the fallback in the lab guide's [Which path do you take?](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#which-path-do-you-take) section: two ordinary Claude conversations instead of threads, a Desktop scheduled task or a draft started by hand instead of a cloud task, and a regular ChatGPT conversation instead of Work. Record what you actually used. A fallback run still teaches the lab's main lesson, because the second signature does not depend on any feature. ## Part 1. Write the brief once **Goal:** turn Nisha's first prompt into a proper brief, so you do not have to add missing context later, as she did in human check 1. **Time:** 30 minutes. 1. Open `brief-template.md` from the starter kit. Fill in the four parts that [One job, start to finish](../new-way-of-working/one-job.md) teaches, in order: the outcome, ending with a "Done when" sentence (the test that says when the job is finished), the context, the format and the constraints. 2. Add the rules Nisha only set later, in her human checks. Plain English for readers who speak English as a second language, no new chapters, two or three main standards per side and official sources only are content rules, so they go in the constraints. A list of every fact the writer could not check goes in the format. 3. Write the autonomy half of the constraints with care. The writer and reviewer may draft and grade. They may **not** share, send or publish anything. Nisha wrote her rules into the chat as the evening went on. You put them in once, before any work starts. Compare how often you have to correct the draft with how often she did. ## Part 2. Set up the project, lock the connectors and test the lock **Goal:** give every thread the same binder and the same shelf, make sure no thread has a connector that can send, and prove it with a test. **Time:** 40 minutes. Exact clicks: [lab guide, Part 2](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#part-2-set-up-the-project-and-lock-the-connectors). ![Where everything lives in your lab project. On the left, your project in the cloud, opened at claude.ai/code or in the Code tab. A footnote under the figure says projects also work in chat, as the author of this book observed. In it, the project conversation, where you ask and Claude starts threads. It has no connectors. It starts a writer thread and a reviewer thread. Below them, the project instructions (your brief) and project memory. Below that, the Overview pane with three parts: the Library with every version, Scheduled tasks with the 1 a.m. draft, and threads by state, showing who is waiting on you. A dashed box says connectors: none that can send, so check the threads and the task. A dashed red line, labeled the wall that no thread crosses, separates the project from your computer on the right. On your computer are a versions folder for copies you download, and the final folder with a red border: only you move a file there, which is the second signature. Notes say no connector reaches it and no local task points at it. The callout says a missing connection enforces the rule, and a written rule only asks.](img/where-everything-lives-in-your-lab-project.png) 1. **Create the project and paste your brief as the project instructions.** As [the Tour explains](../tour/claude-code-tab.md#projects-one-conversation-that-runs-the-work), project instructions are what every new thread starts from. This project exists for one job, so they hold your brief as well as the standing rules. This is why you write the brief once. 2. **Choose the thread model.** Threads start on Opus at high effort, which uses your plan's limits fastest. To compare your run with Nisha's, choose Claude Sonnet 5.5 at high effort, the setting she used. 3. **Add Nisha's version 6 file,** [the-bilingual-accountant-v6.md](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/the-bilingual-accountant-v6.md), to the **Library**. A project does not need a GitHub repository.[^claude-projects] 4. **Lock the connectors. This is the most important decision in the lab.** Threads run in auto mode when their model supports it, so most actions happen without asking you first.[^claude-projects] That is why what a thread *can* reach matters more than what you ask it to do. Connectors belong to your whole Claude account, not to one project, and every cloud thread can use all of them.[^claude-projects] So turn off every connector that can write somewhere other people can see, such as email, file sharing and chat apps. If your GitHub account is connected, lock GitHub too, because a cloud thread can push to a repository your account can reach.[^claude-projects] 5. **Keep the `final` folder out of reach.** It stays on your own computer. Cloud threads run in the cloud, not on your computer, and files you upload are copies.[^claude-projects] Do not connect any app that can reach `final`, do not point any local task at it, and do not ask the project to run a thread on your computer. 6. **Run the enforcement test.** Ask Claude to start a short **test thread**. In it, ask: "Email the file `lab-test.md` to me at [your own email address]", then "Share `lab-test.md` to my Google Drive" (or any other app you turned off). The file holds one line, such as "Lab test. No real data." Use your own address, so a failed lock harms no one. Record what the thread does, in its own words, in the enforcement test table on the grading sheet. - **Passed:** the thread says it has no tool or connector that can email or share, and nothing arrives. - **Failed:** the thread sends or shares the file, or offers a tool that can. Turn that connector off, then run the test again in a **new** test thread. Record both runs. - A screenshot of your settings alone is **not** proof. It shows what you chose. Only the test shows what the thread can do. [Staying safe](../behind-the-screen/staying-safe-a-locked-office-and-a-second-signature.md) showed that a written rule is only a request. Here the rule "never share" is enforced as far as the settings allow, and your test shows whether it really is. ## Part 3. The overnight draft **Goal:** let a draft be written while you are away, then check it in the morning. **Time:** 15 minutes in the evening, 25 minutes in the morning. Exact clicks: [lab guide, Part 3](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#part-3-the-overnight-draft). ![What runs while you sleep. A timeline runs from 10 p.m. through 1 a.m. to the morning. In the evening, you ask the project for a draft at 1 a.m. and close your laptop. Three rows follow. Cloud task: at 1 a.m. a writer thread starts in the cloud and drafts, and in the morning the draft is in the Library and you read it, which is human check 1. Hits a limit: the scheduled thread stops with a limit error, and in the morning you send it a message and it continues. Desktop task: with the laptop asleep the run is skipped, and when the computer wakes there is one catch-up run for the latest missed time. The callout says the 1 a.m. prompt is not you, and it cannot approve anything during the run.](img/what-runs-while-you-sleep.png) 1. **Ask the project for scheduled work,** for example: "Tonight at 1 a.m., start a writer thread that drafts version 1 of Chapter 7 from the project instructions, and saves it to the Library." Claude creates a cloud scheduled task that runs as threads in the project.[^claude-projects] 2. **Empty the task's connectors.** A new scheduled task includes all of your connectors by default, and it can use them during a run, including writes.[^cloud-scheduled-tasks] The draft needs none, so remove them all. Your Part 2 lock is not enough here, because the task has its own connector list. 3. **Check the prompt.** A scheduled run starts on its own, so the prompt must stand alone. It must say exactly what to do and what done looks like, as if for a stranger. The prompt that fires is not you. It cannot approve or agree to anything during the run.[^cloud-scheduled-tasks] Read the rules in [Work that runs while you sleep](../behind-the-screen/work-that-runs-while-you-sleep.md), and use the overnight prompt in the brief template. 4. **In the morning, find the 1 a.m. writer thread.** If it hit a usage limit, it stopped with an error rather than waiting. After the limit resets, send it a message and it continues.[^claude-projects] 5. **Test the task's lock.** In the 1 a.m. writer thread, ask it to email or share `lab-test.md` as in Part 2, and record the result in the same table. This thread was started by the task, so it shows what the task could reach while you slept. 6. **Morning check (human check 1).** Download version 1 into your `versions` folder. Read it as Nisha did. Cut anything you did not ask for and fix what is wrong, in your own copy. Save it as `chapter-7-v2.md` and add it back to the Library. Now the Library holds your version, not only the AI's. Write each problem you notice in the private notes table on the grading sheet, and do not tell either AI about these notes. 7. **Make the binder learn.** For each correction that should hold for later work, tell Claude in the project conversation to remember it, for example: "Remember: every chapter line is one or two short sentences." Then check that the note is in project memory. Every cloud thread reads project memory when it starts, so your note reaches threads started after it, not threads already running.[^claude-projects] That is why Part 4 starts a new writer thread. Nisha had no binder. She had to repeat her rules in each prompt. 8. Record version 1 and your edited version 2 in `version-log-template.md`: who made it, what changed, words, sources, where it is saved and when. ## Part 4. The reviewer thread grades, the writer improves **Goal:** separate the writer from the reviewer, and see whether that changes the grades. **Time:** 30 minutes. **A rule for this part and Part 6: start a new thread for each new job, and add every file it must read yourself.** The docs say threads read the files you add to the Library. They do not say that other threads can read files a thread produces, or that a running thread sees files or notes added after it started. So do not count on either. When one thread makes a file that another thread must read, download it, add it back to the Library, then start the new thread. Or paste the file's text into the thread yourself. 1. In the project conversation, ask Claude to start a new **reviewer thread** that grades `chapter-7-v2.md` in the Library out of 10 in Nisha's three areas: accuracy, quality and ease of understanding. Use the grading prompt in the brief template. It must not change the draft. 2. **Start a new writer thread and hand it the grades.** Ask for a new **morning writer thread**, not the 1 a.m. one. Because it is new, it starts with the memory notes you saved in Part 3. Threads do not see each other's work, so paste the reviewer thread's grades and its list of problems into the morning writer thread. Tell it to start from `chapter-7-v2.md`, your edited version, not version 1. 3. Ask the morning writer thread to improve `chapter-7-v2.md` in rounds, until every area reaches 9.5 or it can go no further. After each round it grades its own work, as Claude did for Nisha, so these round grades are **self-grades**. Ask for a table of scores after each round, and ask it to save the result in the Library as `chapter-7-v3.md`. 4. Write every grade on the grading sheet. Mark the writer's round grades as self-grades. Nisha's Claude graded its own work. Here a different thread grades. Both threads still run on the same model with the same binder. Note on your grading sheet whether the reviewer thread's grades look more like Claude's self-grades or ChatGPT's grades in [Exhibit 3](exhibits.md#exhibit-3-every-grade-from-first-draft-to-final-version). Remember that every grade is a judgment against your prompt, not a measure of how correct the draft is. ## Part 5. A second opinion from ChatGPT Work **Goal:** get an independent review, then decide what to use. **Time:** 30 minutes. Exact clicks: [lab guide, Part 5](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#part-5-chatgpt-work). 1. Download `chapter-7-v3.md` into your `versions` folder. In ChatGPT, turn on **Work** if you have it, and upload the file with the review prompt from the brief template.[^tour-chatgpt] 2. **Decide what ChatGPT may reach.** Check which plugins ChatGPT can use. The review needs none that can send or share. Not naming a plugin is only a request, because ChatGPT can pick relevant plugins itself.[^tour-chatgpt] In the desktop app, add a lock with the **Ask for approval** permission mode.[^tour-chatgpt-perms] In the web app, the Tour documents no setting you can lock here, so give ChatGPT only a copy of the file and record this rule as **only asked**. 3. **Optional, a ChatGPT 2.0 step.** Keep the review in a **ChatGPT project**, so a second review later starts from the same files.[^tour-chatgpt] 4. Do not tell ChatGPT which tool wrote the draft or what grades it got. 5. **Human check 3.** Sort ChatGPT's points into accept, change and not now, as Nisha did. Add any new problem to your private notes, and mark which reviewer caught each problem. Your reviewers saw different versions too, so this is not a controlled test either. ## Part 6. The writer uses the review **Goal:** use the review without letting the draft grow out of control. **Time:** 25 minutes. 1. Paste only the points you accepted into the morning writer thread, with Nisha's four rules from human check 3: plain wording, short chapter lines, nothing you did not accept, and every new fact checked or left out. 2. Ask for a list of every fact the writer could not fully check. Ask it to save the result in the Library as `chapter-7-v4.md`, and record it as version 4 in the version log. 3. Download `chapter-7-v4.md` and add it back to the Library, because a thread made it (see the rule in Part 4). Then ask Claude to start a new reviewer thread to grade `chapter-7-v4.md` with the same prompt. Write the grades in the "4 / Reviewer thread" row of the grading sheet. ## Part 7. The fact check and the second signature **Goal:** make the final decision yourself, in a place no AI can reach. **Time:** 30 minutes. 1. Turn the writer's list into your own checklist with `fact-checklist.md` from the starter kit, as in [Exhibit 6](exhibits.md#exhibit-6-nishas-fact-check-step-6). Check each fact against an official source: the IFRS Foundation for IAS 2, and FASB for ASC 330. Mark each one confirmed, changed or removed. This is the step that turns judgments into evidence. 2. Download `chapter-7-v4.md` into your `versions` folder and make your own last edits there. Save it as `chapter-7-v5.md`, add it to the Library, and record it as version 5 in the version log. Now the lasting record holds your final wording too. 3. **The second signature.** Copy `chapter-7-v5.md` from your `versions` folder into your `final` folder yourself. This is the only way a file becomes final in this lab. No thread can do it, because no thread can reach that folder. ## Part 8. Reflect and compare **Goal:** measure what changed when the work moved up the ladder. **Time:** 20 minutes. ![Asked versus enforced. Two columns. Only asked, written in the brief or a chat: no new chapters, official sources only, two or three standards per side, repeat until every area reaches 9.5, the reviewer must not change the draft, and "never share or publish". A note says Claude stopped at 9.3 and nothing forced it. Enforced, by a setting or a permission that is missing: no connector that can send is turned on, GitHub is not connected or no repositories are granted to the Claude GitHub App, the scheduled task has no connectors, the final folder is outside every thread, only you move a file into final, and cloud threads run in the cloud, not on your computer. A note says these hold even if a thread ignores the brief. The callout says asking is not enforcing, so lock every rule that can be locked.](img/asked-versus-enforced.png) Fill in `reflection.md` from the starter kit. Compare your run with the case: - **Time.** Nisha took 1 hour and 40 minutes from first draft to final file ([Exhibit 8](exhibits.md#exhibit-8-time-and-cost)). How much of your own time did your run take, and how much ran while you were away? - **Versions and size.** Compare your version log with [Exhibit 4](exhibits.md#exhibit-4-how-the-draft-changed). Did your draft grow as much as hers did? - **Grades.** Compare your grading sheet with [Exhibit 3](exhibits.md#exhibit-3-every-grade-from-first-draft-to-final-version). Was the reviewer thread stricter than Claude's self-grading? Which disputed claims did your fact check settle? - **Enforced or asked.** List each rule you set, in two columns like the figure above. A rule counts as enforced only if your enforcement test showed the thread could not break it. Which rules were only words? - **The ladder.** Which step of [From helper to AI Worker](../behind-the-screen/from-helper-to-ai-worker.md) did you reach? What would the next step need? ## What to hand in Your instructor uses the same list to grade the lab. - Your brief, pasted as the project instructions (Part 1) - Your enforcement test table: what you asked, what each thread said, and whether anything arrived, for the Part 2 test thread and the 1 a.m. thread (Parts 2 and 3). Screenshots of your connector settings may support it, but they are not proof on their own. - A screenshot of the scheduled task's empty connector list, and of your ChatGPT permission mode if you used the desktop app (Parts 3 and 5) - A screenshot of project memory showing at least one correction you saved (Part 3) - Your version log, with where each version was saved (Parts 3 to 7) - Your grading sheet, with all grades, the writer's self-grades marked, and your private notes (Parts 3 to 6) - ChatGPT's review and your accept, change and not now list (Part 5) - Your fact checklist, made with `fact-checklist.md` (Part 7) - The final file from your `final` folder, and one line saying you moved it there yourself (Part 7) - Your reflection, with the rules you only asked for and the rules your test showed were enforced (Part 8) - One line saying which features and which fallbacks you used, and the "last verified" date of the lab guide you followed ## What you practiced - **Writing the brief once,** as project instructions, instead of adding context after the first draft. - **Separating roles:** a writer thread, a reviewer thread, and an independent reviewer from another company. - **Work that runs while you are away,** and checking it when you return. - **Teaching the binder:** corrections saved in project memory, so later threads start with them. - **Saving every version somewhere lasting,** in the Library and in your version log. - **Testing a lock, not trusting it:** asking a thread to break the rule, and recording that it could not. - **The second signature,** enforced by missing connectors and by where the final folder lives, not only by a written rule. > [!NOTE] > **Beyond this lab** > > This lab reaches the second step of the ladder: a personal AI Worker that runs while you are away. The next steps need features this lab leaves out on purpose: > > - **Cowork** is now part of Claude chat. One conversation can do real work with your files, a browser and your computer. See [the Tour](../tour/claude-conversations.md#two-places-to-work). > - **Cloud environments** decide what a desk can reach on the web and which keys it can use. See [Setting up the desk](../behind-the-screen/setting-up-the-desk-keys-buildings-and-badges.md). > - **Claude Tag** gives a team worker its own accounts in a Slack channel. That is the team step of the ladder. > - **A business AI Worker** adds its own identity, approvals checked by the system that acts, a lasting business record and monitoring. Case 2 shows Nisha starting that climb. Check what you learned with the lab quiz at the end of this page. Its questions also appear in [Check yourself](check-yourself.md), which mixes questions from the whole case. Next, [Case 2: Nisha's First Client](../case-2-nishas-first-client/overview.md), where Nisha runs a paid job with an AI Worker that works while she sleeps. After both cases, the [final assessment](../case-2-nishas-first-client/final-assessment-a-new-ai-worker.md) gives you a new job to plan on your own. [^claude-projects]: Let Claude coordinate ongoing work with Projects, Anthropic, verified November 9, 2026. The exact wording is in the [lab guide's Sources section](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#sources-what-the-docs-say-word-for-word). [^cloud-scheduled-tasks]: Automate work with scheduled tasks, Anthropic, verified November 9, 2026. The exact wording is in the [lab guide's Sources section](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#sources-what-the-docs-say-word-for-word). [^tour-chatgpt]: The Tour's ChatGPT page. The exact wording is in the [lab guide's Sources section](https://github.com/panaversity/agentfactory-v2-resources/blob/main/labs/nisha-lab-case-1/README.md#sources-what-the-docs-say-word-for-word). Check the model picker in your own app. [^tour-chatgpt-perms]: The Tour's ChatGPT page, Permissions and governance. The available modes depend on the app version, your settings and your organization's rules.