On July 9, 2026, OpenAI launched ChatGPT Work and merged Codex into a unified ChatGPT desktop app. If you already know what it is, the real question is: what do you do with it on Monday morning? This hands-on guide covers three success principles, mode selection tables, a universal 5-step workflow, copy-paste prompts for six roles, Scheduled Tasks recipes, usage optimization, pitfalls, and a 30-day onboarding roadmap. For launch context and Claude Cowork comparison, read our ChatGPT Work launch guide.
01

Before You Copy a Prompt: 3 Principles That Decide Success

ChatGPT Work is not regular Chat. It plans, connects apps, runs for hours, and ships finished files. Three principles separate productive users from wasted quota.

PrincipleWhat it meansPractical tip
Describe outcomes, not stepsWork mode plans its own pathNot "Open Salesforce, export, then…" — instead "Build a weekly pipeline PPT from @Salesforce deals in the last 30 days, flagging at-risk opportunities"
Connect tools firstPlugins are Work's data layerAuthorize Gmail, Slack, Drive before starting; use @AppName to pin sources
Plan Mode is your brakeReview the plan before executionFor high-stakes deliverables (external emails, financial reports, client docs), approve every step

Pick the right mode — using the wrong one wastes usage:

Your needUseWhy
Quick Q&A, brainstorming, single-turn copyChatLightweight, fast
Multi-app projects, finished deliverables, hours-long tasksWorkPlugins + Plan Mode + Computer Use
Code review, PRs, multi-repo developmentCodexDeveloper-native workflows
Recurring background automationWork + Scheduled TasksTriggered or scheduled execution

OpenAI's onboarding advice: Start with a task you already know well — month-end variance analysis, a campaign brief, or sales meeting prep — because you can verify quality fast.

02

Universal 5-Step Workflow, Prompt Formula & Desktop vs Web

Every role follows the same skeleton. Master it once, then swap prompts by department.

01

Connect plugins — authorize Gmail, Slack, Drive, CRM, and any other data sources in the Plugins Directory.

02

Write goal + output format — state the deliverable, not the manual steps.

03

Review Plan Mode — approve, edit, or reject steps before execution starts.

04

Steer mid-flight — pause and correct if context drifts or data looks wrong.

05

Accept deliverable & iterate — save what works, refine the prompt, then automate with Scheduled Tasks.

Work mode prompt formula:

prompt
[Role] + [Data sources @plugins] + [Task] + [Output format] + [Constraints] + [Acceptance criteria]

Example skeleton:
You are a [role]. Pull [data type] from @Salesforce and @Gmail for [time range].
Complete [action], output as [Google Docs / Excel / PPT / Sites].
Constraints: [do not modify source data / two decimal places / no external email].
When done: [Slack me / save to folder].

Plan Mode review checklist — confirm before you approve:

A

Are data sources correct (right account, right month)?

B

Any high-risk actions (send external email, delete, overwrite files)?

C

Does output match your team's template?

D

Can any steps be removed to save usage?

E

Do you need a human approval checkpoint?

Desktop vs Web: pick the environment that matches your workflow.

ScenarioRecommended environment
Local file read/write, Computer Use, Free-tier trialDesktop (Mac / Windows)
Team collaboration, monitor task progress anywhereWeb / mobile (Plus and above)
Sales meeting briefs + email notifications on scheduleWeb Workspace Agent + scheduled runs
Local Excel reconciliation, folder batch processingDesktop Work mode
03

6 Role-Based Workflows with Copy-Paste Prompt Templates

Templates below draw on OpenAI case studies, early adopters (Zapier, Nvidia, Virgin Atlantic), and the Workspace Agent Cookbook. Replace @plugin names with your stack.

Sales

A

Daily meeting briefs (scheduled): Pain — reps spend 1–2 hours daily assembling client background. Work scans calendar, pulls CRM notes, searches news, archives briefs.

prompt
Create a scheduled task running every weekday at 4pm:
1. Check tomorrow's customer meetings in @Google Calendar (exclude internal-only)
2. For each: pull 30-day account notes from @SharePoint / @Salesforce, search 30-day company news
3. Write 2–3 sentence background per external attendee
4. Generate 2–3 page brief per meeting, save to @Google Drive
5. Email summary via @Gmail with links (subject: "Tomorrow's Client Briefs — [date]")
B

Live account command center (Sites + daily refresh): Pain — account intel scattered across CRM, email, Slack. Work builds a live Sites dashboard with daily refresh.

prompt
From @Salesforce data for [Account Name]:
1. Build interactive account command center (Sites): pipeline overview, 7-day signals, prioritized next actions
2. Schedule daily refresh at 8am weekdays
3. Slack me on major changes via @Slack
Constraints: do not send external emails; amounts from CRM source data only.
C

Lead review & pipeline repair: Pain — thousands of leads monthly; follow-up gaps hide seven-figure pipeline loss.

prompt
Analyze @Salesforce leads from last 30 days cross-referenced with @Gmail outreach.
Find: 48h+ follow-up gaps (by source), broken handoff points, estimated pipeline loss.
Output: Excel detail table + 1-page executive PPT + repeatable weekly review workflow for Scheduled Tasks.

Marketing

A

Research → Brief → multi-market assets: Pain — research, brief, and regional assets lose context across handoffs. One instruction carries context end-to-end.

prompt
Using uploaded research / @Google Drive materials:
Phase 1: Campaign Brief (Docs) with messaging pillars and channel recommendations
Phase 2: Email, 3 LinkedIn posts, landing page outline → save to Drive "Campaign / [product]"
Phase 3: Adapt for US, EU, APAC with localization and compliance notes
Pause after each phase for my approval before continuing.
B

Slack / Teams → meeting agenda sync (weekly scheduled): Pain — weekly agendas go stale; someone manually scans channels.

prompt
Every Monday 7am:
1. Summarize last 7 days from @Slack #product-launch and @Microsoft Teams GTM channel
2. Extract decisions, open questions, blockers for the meeting
3. Update "Weekly Agenda" Google Doc (preserve history)
4. Post ≤5 bullet summary to @Slack #leadership
Constraints: public discussions only; no confidential messages.

Finance

A

Month-end variance analysis (OpenAI-validated): Pain — close and forecast adjustments take days. Work locates source data, reconciles in Sheets, drafts narrative, builds slides.

prompt
Complete [Month] budget variance analysis:
1. Pull actuals and forecast from @Google Drive Finance folders
2. Build reconciliation workbook in @Google Sheets (flag >5% or >$50K variances; preserve source formulas)
3. Draft narrative explanations (Docs) by revenue / cost / opex
4. Build 5–8 slide management deck matching attached template style
5. List 3 judgment calls requiring human sign-off
Do not modify source files. Cite all numbers with source cells.
B

Invoice vs payment register reconciliation: Pain — AP teams manually spot mismatches across registers.

prompt
Compare payment register and invoice list from @Google Drive.
Flag: >2% amount differences, missing tax IDs, duplicate invoice numbers, vendor name mismatches.
Return review table only (vendor | invoice | amount | suggested action). Do not initiate payments.

Operations

A

Daily dashboard morning briefing (scheduled): Pain — ops leads manually diff dashboards each morning.

prompt
Every weekday 6:30am: visit [dashboard URL / @SharePoint report], compare to yesterday's snapshot.
Flag >10% swings or new red indicators. Generate 1-page brief (TOP 3, metric table, owners).
Email ops-leads@company.com via @Gmail.
If dashboard unreachable, stop and notify — do not fabricate data.
B

Customer feedback clustering → product priorities: Pain — feedback scattered across Slack, email, ticket exports.

prompt
Monitor 14-day feedback from @Slack #customer-feedback, @Gmail NPS-Detractor, Drive ticket exports.
Cluster into 5–8 themes with sample quotes. Rank by frequency × impact × effort.
Output prioritized product review doc. Schedule weekly Friday refresh.
Anonymize all customer references.

Product

A

Launch readiness review (Jira + GTM cross-check): Pain — launch checks span engineering, marketing, and support; manual audits miss blockers.

prompt
Launch readiness for [Feature]:
1. @Jira: Epic / Story completion and open blockers
2. @Google Drive GTM plan: milestone check
3. @Slack #product-launch: unresolved discussions (last 7 days)
Output: Red/Yellow/Green readiness report with blocker list and Go/No-Go recommendation.
Do not auto-update Jira. Flag high-risk items for human decision.

Engineering — Work + Codex in the same app

A

PR review → release notes → team announcement: Codex handles code; Work formats docs and drafts comms.

prompt
Codex mode: Review PR #123 in [repo/name], side-panel comments on security/performance/tests, draft release notes.
Work mode: Format for @Confluence, draft @Slack #engineering post (do not auto-send).
B

Multi-repo weekly engineering summary: Uses Codex multi-repo capability plus Work for reporting.

prompt
Codex mode: Cross [frontend-repo] + [backend-repo] — merged PRs, open P0/P1 issues → Markdown weekly report.
Work mode: Convert to Google Docs, pull burndown from @Jira. Schedule Fridays 5pm.
04

Scheduled Tasks Recipe Library & Setup Workflow

OpenAI recommends four high-frequency automations. Adapt triggers and channels to your team.

RecipeTriggerActionBest for
Monday agenda refreshMon 7:00Slack digest → update agenda docMarketing / Ops
Daily metrics briefWeekdays 6:30Dashboard diff → email reportOps / Finance
Feedback clusteringFri 16:00Multi-channel → priority listProduct
Account daily refreshWeekdays 8:00CRM changes → update Sites dashboardSales

Scheduled Task prompt pattern:

prompt
Set up Scheduled Task:
- Frequency: [daily / every Monday / 1st of month / when @Slack keyword appears]
- Time: [timezone + exact time]
- Action: [workflow description]
- Notification: [Slack channel / email / none]
- Human approval: [which steps need my sign-off first]

Six-step setup workflow before you go unattended:

01

Run manually 2–3 times — validate output quality and Plan Mode steps before scheduling.

02

Limit plugin scope — connect only the tools the recipe needs.

03

Disable auto-external-send unless the workflow explicitly requires it.

04

Set output archive path — avoid overwriting shared team files.

05

Confirm Enterprise agent network policy with your admin if applicable.

06

Choose runtime environment — desktop tasks need device awake; web Workspace Agents run in the cloud for true background execution.

Safety rule: Never schedule a workflow you have not manually verified. Treat the first three runs as a pilot, not production.

05

Usage Optimization, Pitfalls, Roadmap & Three Data Points

ChatGPT Work shares a metered usage pool with Codex. The same workflow can cost 5× more depending on design.

FactorImpact on usage
Task step countMore steps = higher consumption
Context sizeMore emails and documents pulled = higher input tokens
Output lengthOutput tokens cost roughly 6× input
Cache hitsRepeated reads of same doc ≈ 1/10 fresh input cost
Model choiceGPT-5.6 deep reasoning costs more than lightweight tasks need

Seven cost-saving tactics:

01

Draft in Chat first, then hand a tight brief to Work.

02

Trim Plan Mode steps, especially duplicate data pulls.

03

Reuse template docs in Scheduled Tasks for cache discounts.

04

Request concise outputs — table + 3 bullets beats a narrative report.

05

Split large projects into phases to avoid expensive re-runs.

06

Free users: test small desktop tasks before scaling automation.

07

Enterprise: set workspace / group / individual limits in Admin Console.

Pre-launch usage test:

workflow
1. Pick a real task you know the human time cost of (e.g. variance table, usually 2 hours)
2. Run once in Work with Plan Mode, note step count
3. Check consumption against your plan's included usage
4. Extrapolate daily / weekly / monthly cost
5. Optimize per tactics above and re-run to compare

Common pitfalls:

IssueCauseFix
Codex projects missingIncomplete app migrationUpdate Codex app → becomes ChatGPT desktop; clean reinstall from chatgpt.com/download if broken
Plugin connected but no dataInsufficient scope or wrong @nameRe-check plugin permissions; use explicit @Salesforce not "the CRM"
Good plan, wrong outputStale context or AI inferencePause and steer; attach explicit source files
Scheduled task didn't fireDevice asleep / logged outUse web Workspace Agents for background; desktop needs device online
Usage higher than expectedVerbose output, redundant pullsApply optimization tactics above; set Admin Console limits
Work vs Cowork confusionDifferent workflow typesCloud SaaS → Work; local folder batch → Cowork (see launch guide)

30-day onboarding roadmap:

WeekGoalAction
1Single-task fluencyRun 3 manual Work tasks you can quality-check; practice Plan Mode review
2Plugin depthConnect 3 core tools (email + collaboration + files); complete 1 cross-app deliverable
3AutomationConvert Week 1 task to Scheduled Task; verify 3 trigger cycles
4Team rolloutDocument role-specific prompt library; Enterprise teams set admin limits

Three citeable data points for ROI conversations:

01

Days → hours: OpenAI's internal month-end close and forecast workflow compressed from days to hours using Work mode.

02

24 hours vs weeks: OpenAI sales teams turned a Discovery conversation into a customized PoC proposal in 24 hours — a process that traditionally took weeks.

03

5× cost spread: The same workflow can consume 5× more quota depending on prompt design, step count, and output verbosity — optimization is not optional.

Desktop Scheduled Tasks need an awake, logged-in machine; personal Macs sleep and interrupt long Work sessions; macOS VMs break EULA and Xcode signing. For persistent desktop agents, iOS CI/CD, and production automation that runs while you are offline, KVMNODE dedicated Mac Mini M4 cloud rental is usually the better host: Apple Silicon unified memory, 7×24 uptime, flexible daily/weekly/monthly terms. See the pricing page, help center, or order directly.

Last updated: 2026-07-11 · Sources: OpenAI Blog, OpenAI Cookbook, ChatGPT Learn Changelog, SiliconANGLE