ChatGPT Work Practical Guide:
6 Role Workflow Prompt Templates + Scheduled Tasks

If you already know what ChatGPT Work is, the real question is: what can you actually use it for tomorrow? On July 9, 2026, OpenAI launched ChatGPT Work and merged Codex into the new ChatGPT desktop app. OpenAI's recommended starting point is straightforward — hand it a task you already know well, such as month-end variance analysis, a marketing campaign brief, or sales meeting prep. This guide breaks down real workflows across Sales, Marketing, Finance, Operations, Product, and Engineering with copy-paste Prompt templates, Plan Mode review checklists, Scheduled Tasks automation recipes, and practical tips to avoid runaway usage.

• Wrong mode: Running cross-app long tasks in Chat, or using Work for simple Q&A, wastes usage credits.
• Wrong Prompt style: Step-by-step instructions like "open Salesforce, export…" fight Work's design — describe outcomes and let it plan.
• Plugins not authorized: Gmail, Slack, Drive, and other data sources must be connected before the task starts, or even a perfect Plan cannot pull data.
• Scheduled Task misconfiguration: Desktop Scheduled Tasks require the device to stay online — a closed laptop lid stops triggers.
• High-stakes tasks without review: External emails, financial reports, and client deliverables need line-by-line Plan review before execution.

SECTION 01 How to Use ChatGPT Work: 3 Core Principles and Chat / Work / Codex Mode Routing

Before copying Prompts, understand how ChatGPT Work differs from regular Chat:

The new ChatGPT desktop app runs three modes side by side. Using the wrong mode wastes usage:

SECTION 02 Universal Workflow Framework: 5-Step Runbook + Prompt Formula + Plan Mode Checklist

Regardless of role, follow this flow:

1. Connect plugins → 2. Define goal and output format → 3. Review Plan Mode → 4. Intervene mid-run to correct course → 5. Accept deliverable and iterate

Work mode Prompt writing formula:

[Role] + [Data source @plugin] + [Specific task] + [Output format] + [Constraints] + [Acceptance criteria]

Example skeleton:
You are a [role]. Pull [data type] from @Salesforce and @Gmail for [time range].
Complete [specific action], output as [Google Docs / Excel / PPT / Sites].
Constraints: [do not modify source data / amounts to two decimals / do not send external emails].
When done, [notify me on Slack / save to specified folder].

Plan Mode review checklist (confirm each item before execution):

• Are data sources correct (wrong customer or wrong month)?
• Are there high-risk actions like "send externally," "delete," or "overwrite files"?
• Does the output format match team templates?
• Can intermediate steps be trimmed to save usage?
• Do you need a human confirmation checkpoint?

SECTION 03 6 Role Playbooks: Copy-Paste Prompt Templates

These templates are drawn from OpenAI official examples, early tester feedback (Zapier, Nvidia, Virgin Atlantic, and others), and the Workspace Agent Cookbook. Replace @PluginName with your actual tool stack.

3.1 Sales

Scenario A: Auto meeting brief (daily scheduled) — Pain point: reps spend 1–2 hours daily assembling client background manually. Work solution: scan calendar on schedule → pull CRM notes → search recent news → generate brief and archive.

Create a scheduled task: run every weekday at 4:00 PM.

1. Check my @Google Calendar client meetings for tomorrow (exclude internal meetings)
2. For each client meeting:
   - Pull account notes and interaction history from the past 30 days via @SharePoint / @Salesforce
   - Search public news and executive activity for that company from the past 30 days
   - Write a 2–3 sentence background summary for each external attendee
3. Generate a 2–3 page brief per meeting, saved as @Google Drive documents
4. Send me a @Gmail summary email with links to each brief

Output format: email subject "Tomorrow's Client Meeting Briefs — [date]", body as a table (Client | Meeting time | Key topics | Brief link)

OpenAI internal case: a sales team turned one Discovery conversation into a customized PoC proposal within 24 hours (traditionally weeks).

Scenario B: Account command center (Sites + daily refresh) — Pain point: key account info scattered across CRM, email, and Slack; account plans require manual upkeep.

Based on all opportunities, contacts, and recent activity for [Account Name] in @Salesforce:

1. Create an interactive account command center (Sites) containing:
   - Pipeline overview (stage, amount, expected close date)
   - Key signals from the past 7 days (email, meetings, support tickets)
   - Recommended next actions (priority sorted)
2. Set a Scheduled Task: auto-update the Site every weekday at 8:00 AM
3. DM me on @Slack when there are major changes

Constraints: do not auto-send any external emails; amounts must match CRM source data.

Scenario C: Lead review and pipeline repair (adapted from Zapier case) — Pain point: thousands of leads per month; follow-up gaps are hard to spot.

Analyze new leads from the past 30 days in @Salesforce and their follow-up records, cross-referenced with sales correspondence in @Gmail.

Find:
1. Leads with no follow-up for 48+ hours (grouped by source)
2. Follow-up chain break points (where response rate drops sharply)
3. Estimated pipeline loss amount

Output:
- Excel detail table (Lead ID | Source | Last follow-up | Break type | Recommended action)
- 1-page executive summary PPT highlighting seven-figure potential loss opportunities
- A weekly repeatable review workflow (for Scheduled Task use)

3.2 Marketing

Scenario A: Research → Brief → multi-market assets (end-to-end pipeline)

I uploaded the following customer research materials: [attachment / @Google Drive link]

Complete the end-to-end marketing workflow:

Phase 1 — Brief:
- Extract target audience, core pain points, competitive positioning
- Output Campaign Brief (Google Docs) with message pillars and channel recommendations

Phase 2 — Asset generation:
- From the Brief, generate: 1 acquisition email, 3 LinkedIn posts, 1 landing page copy outline
- Save to @Google Drive "Campaign / [Product Name]" folder

Phase 3 — Regional adaptation:
- Adapt core assets for US, Europe, and APAC (language, cultural references, compliance wording)
- Flag sensitive phrasing requiring human review in each version

Pause after each phase and wait for my confirmation before proceeding.

Scenario B: Slack / Teams activity synced to meeting agenda (Scheduled Task)

Set a scheduled task to run every Monday at 7:00 AM:

1. Summarize important discussions from the past 7 days in @Slack #product-launch and @Microsoft Teams "Go-to-Market" channel
2. Extract: decisions made, open questions, blockers needing alignment in the meeting
3. Update the "Weekly Meeting Agenda" document in @Google Drive (preserve version history)
4. Post a summary of 5 items or fewer in @Slack #leadership

Constraints: only cite publicly discussed content; do not leak messages marked confidential.

3.3 Finance

Scenario A: Month-end variance analysis (OpenAI internal validated scenario) — OpenAI internal result: month-end close and forecast workflows compressed from "days" to "hours."

Help complete [month] month-end budget variance analysis:

1. Pull corresponding spreadsheets from @Google Drive "Finance / Actuals" and "Finance / Forecast"
2. Create a reconciliation workbook in @Google Sheets:
   - Summarize actual vs forecast variance by department
   - Flag line items with variance >5% or >$50K
   - Preserve all original formulas; do not overwrite source files
3. Draft performance commentary (Google Docs), categorized by Revenue / COGS / OpEx with possible explanations
4. Build a 5–8 page management report PPT (with charts, following attached template style)
5. List 3 key judgment points requiring manual finance confirmation when done

Constraints: do not modify any source data; cite source cell for every number.

Scenario B: Invoice and payment reconciliation (first AP automation gate)

You are an accounts payable specialist. Compare the following two datasets:
- Payment register: [@Google Drive link]
- Invoice list: [@Google Drive link]

Flag the following anomalies (return as a table):
| Issue type | Vendor | Invoice # | Amount | Recommended action |
- Amount variance >2%
- Missing tax ID
- Duplicate invoice number
- Vendor name mismatch

Do not initiate payments automatically; output review table for manual verification only.

3.4 Operations

Scenario A: Daily dashboard change monitoring (Scheduled Task)

Auto-run every weekday at 6:30 AM:

1. Access [internal dashboard URL / @SharePoint report page]
2. Compare to yesterday's snapshot; extract significant changes (>10% swing or new red indicators)
3. Generate a 1-page morning brief (Google Docs) structured as:
   - TOP 3 items needing attention today
   - Metric change table
   - Recommended follow-up owners
4. Send via @Gmail to [email protected]

If the dashboard is inaccessible, tell me during Plan phase — do not fabricate data.

Scenario B: Customer feedback clustering → product priority

Monitor new customer feedback from the past 14 days across:
- @Slack #customer-feedback
- @Gmail label "NPS-Detractor"
- @Google Drive "Support Tickets Export"

1. Cluster feedback into 5–8 themes (with representative quotes)
2. Prioritize by Frequency × Impact × Implementation difficulty
3. Output product evaluation backlog (Notion / Google Docs format)
4. Set a Scheduled Task to auto-refresh the document every Friday

Constraints: anonymize feedback quotes; no customer names.

3.5 Product

Scenario A: Cross Jira + GTM launch readiness review (adapted from Nvidia case)

Run a launch readiness review for [product/feature name]:

1. Pull linked Epic / Story completion status and open blockers from @Jira
2. Pull the corresponding GTM plan from @Google Drive "GTM Plans" and check key milestones
3. Extract unresolved discussions from the past 7 days in @Slack #product-launch
4. Output Launch Readiness report (Google Docs):
   - Readiness score (Red / Yellow / Green)
   - Blocker list (Owner | Due date | Risk level)
   - Recommended Go / No-Go judgment with rationale

Do not auto-modify Jira status; flag high-risk items requiring human decision.

3.6 Engineering — Work and Codex together

Engineering scenarios work best when Codex handles code implementation and Work handles cross-team documentation. Both modes live in the same desktop app — no tool switching required.

Scenario A: PR review + release notes

In Codex mode:
1. Review PR #123 in [repo/name], focusing on [security / performance / test coverage]
2. Leave line-by-line review comments in the PR sidebar
3. If approved, generate Release Notes draft

Then switch to Work mode:
4. Format Release Notes as a @Confluence page
5. Draft @Slack #engineering announcement (do not auto-send)

Scenario B: Multi-repo issue summary weekly report (Codex multi-repo capability)

In Codex mode, across [frontend-repo] and [backend-repo]:
1. Summarize merged PRs this week and open P0/P1 Issues
2. Generate engineering weekly report in Markdown

Switch to Work mode:
3. Convert to Google Docs and insert this week's burndown chart (pull from @Jira)
4. Set a Scheduled Task to auto-generate every Friday at 5:00 PM

SECTION 04 Scheduled Tasks Automation Recipes and 6-Step Setup Guide

Set up a Scheduled Task:
- Frequency: [daily / every Monday / 1st of month / when keyword appears in @Slack channel]
- Time: [timezone + specific time]
- Action: [specific workflow description]
- Notification: [Slack channel / email / none]
- Human confirmation: [which steps require my approval first]

Safety checklist before unattended runs:

• Plugin access scope limited to necessary tools only
• Auto-send externally disabled unless explicitly required
• Output archive path set to avoid overwriting others' files
• Enterprise users: confirm admin-approved Agent network policies
• Run manually 2–3 times first, then switch to scheduled

6-step Scheduled Task setup:

1. Pick a recipe: Choose the workflow closest to your daily repetitive work from the table above or Section 03 role templates.
2. Manual single run: Execute the full workflow once in Work mode; confirm output format and data sources.
3. Trim Plan Mode steps: Remove duplicate pulls and redundant searches to reduce usage on future scheduled runs.
4. Write the scheduled Prompt: Use the template above; specify frequency, timezone, notification channel, and human confirmation checkpoints.
5. Choose runtime environment: For true unattended background runs, use Web Workspace Agent; for local file tasks, use desktop and keep the device awake.
6. Observe 3 consecutive triggers: Confirm stable execution before expanding scope or adding new recipes.

SECTION 05 Usage Optimization, Citable Data, Pitfalls, and 30-Day Onboarding Roadmap

ChatGPT Work and Codex share a usage billing pool (not a fixed monthly feature allotment). The same workflow can cost 5× more depending on design.

Seven cost-saving practices:

1. Draft in Chat mode first, then hand a trimmed version to Work for execution
2. Delete redundant steps in Plan Mode, especially repeated pulls from the same data source
3. Reuse the same template document in Scheduled Tasks to leverage cache discounts
4. Keep output concise: "table + 3 bullet summary" beats "full narrative report"
5. Split large tasks: Phase 1 confirm direction → Phase 2 generate deliverable; avoid one heavy run that requires rework
6. Free tier users: Run small tasks on desktop first; measure consumption before scaling
7. Enterprise teams: Set workspace / group / individual quotas in Admin Console

Citable technical facts:

• Launch date: July 9, 2026 — OpenAI launched ChatGPT Work; Codex app merged into ChatGPT desktop.
• Month-end efficiency: OpenAI internal validation: month-end variance analysis workflows compressed close from "days" to "hours."
• Usage multiplier: Workflow design differences can cause roughly 5× consumption variance; output token cost is roughly 6× input; cached input costs roughly 1/10 of fresh input.
• Prompt length guidance: 150–400 words, focused on data source + output format + constraints — no step-by-step micromanagement.

The following is compiled from OpenAI official releases and the Cookbook. Re-open links after future releases to verify latest policies and features.

OpenAI Blog — ChatGPT Work Launch

OpenAI Cookbook — Sales Meeting Prep Agent

ChatGPT Learn Changelog

Many teams run ChatGPT Work Scheduled Tasks on personal laptops — lid closed means stopped; true 24/7 unattended operation is impossible. VM alternatives add hypervisor overhead and iOS/macOS toolchain compatibility friction. For engineering and operations teams that need stable Codex multi-repo reviews, local Excel batch processing, or Agent scheduled tasks, MACNOX dedicated physical Mac nodes are often the better production choice: 100% genuine Apple hardware, full root access, zero hypervisor overhead, flexible daily/weekly/monthly ordering — keeping Work mode Computer Use and scheduled tasks running on dedicated hardware. See physical node isolation recommendations in our AI Agent production hardening guide.

SECTION 06 FAQ