ChatGPT Workflow Placement: Projects, Skills, Plugins, and Tools

Choose models and place workflows across Chat, Work, Codex, Projects, Skills, Plugins, existing GPTs, Scheduled Tasks, memory, and Library.

Start with the workflow layer, then choose the ChatGPT surface

Choose between Chat, Work, and Codex, then select the available model and reasoning controls. Place persistent context in Projects, procedures in Skills, connected capabilities in Plugins, and files in Library or the relevant source. Maintain existing GPTs while preparing migration.

Choose the ChatGPT experience first

Start by choosing the experience that matches the work. Then select the reasoning level, tools, persistent context, reusable workflow surface, and external integrations required by the task.

Chat

Use Chat for questions, conversation, brainstorming, quick analysis, search, file review, and tool-assisted work that remains centered in a conversation.

Work

Use Work for longer, more involved tasks that require research, connected apps or files, active steering, approval points, and finished documents, spreadsheets, presentations, reports, or Sites.

Codex

Choose Codex when you need developer views, diffs, code review, and technical execution details. Work can also run code and use accessible repositories; Codex can also create research and documents. Choose between them by the required tools and review experience.

Use the OpenAI API when the workflow must run outside ChatGPT

Use the API when the workflow must run inside a website, application, backend service, internal system, CI pipeline, or controlled production automation.

Open the API placement map →

Speed, model tier, and reasoning controls

Select the model, reasoning effort, and speed separately where supported. GPT-6 Astra appears as GPT-6 Pro in Chat and as Astra in Work and Codex. Available controls depend on the experience, plan, workspace, and rollout.

Standard Chat: choose a speed and reasoning level

Standard Chat speed and reasoning levels
OptionUse forModel
InstantEveryday questions and short drafts.GPT-5.6 Sol on eligible paid plans; GPT-5.6 Luna on Free and Go.
MediumPlanning and analysis.GPT-5.6 Sol.
HighComplex, multi-step work.GPT-5.6 Sol.
Extra HighThe greatest thinking effort within Sol.GPT-5.6 Sol on eligible plans.
ProDemanding tasks and extended reasoning.GPT-5.6 Sol Pro or GPT-6 Pro, powered by GPT-6 Astra, where available.
Plan access
Plus includes Medium and High. Pro, Business, and Enterprise also include eligible Extra High and Pro options. GPT-6 Pro is available on Pro $100, Pro $200, Business, and Enterprise, subject to workspace permissions. Free and Go use Luna, including their Think option.
Automatic switching
On Plus and Pro, select the thinking level explicitly; Instant no longer switches to thinking for complex requests. Safety-related switching can still occur. Business manages automatic reasoning through Settings > General > Higher intelligence. Enterprise and Edu routing is controlled through workspace model settings.
Managed-workspace labels
Enterprise and Edu may show Pro Standard and Pro Extended. In Business, Standard and Premium are seat types; Pro is a model option.
Picker placement
Use the composer on web or the picker at the top of the conversation on mobile. Enterprise workspaces may retain earlier controls during rollout.

Work and Codex: choose a model and reasoning effort

Start with the available Power default. Use Advanced for explicit model, effort, and speed choices. Astra rollout options vary by account; Sol with Medium is not a universal default.

Models and execution controls
Control Type Meaning Availability boundary
GPT-6 Astra Model Demanding work across research, code, and apps requiring sustained reasoning and multiple tools. Confirm access on the selected surface.
GPT-5.6 Sol Model Complex, ambiguous work requiring analysis, judgment, or polish. A model choice, not a reasoning level.
GPT-5.6 Terra Model Everyday work with reasoning and tool use. Choose according to task requirements.
GPT-5.6 Luna Model Clear, repeatable tasks such as extraction and classification. Available through Advanced where supported.
Reasoning effort Per-model control Adjusts reasoning depth within the selected model. Light (Low in CLI), Medium, High, and Extra High where supported.
Max Reasoning effort More reasoning time for one difficult task. May require enabling in app settings.
Ultra Multi-agent mode Uses subagents for parallel work. Where supported, enable the desktop picker option in Settings → Configuration.
Fast mode Speed control Separate speed control; Astra consumes credits at 2.5× the Standard rate where available. ChatGPT sign-in on desktop, Codex CLI, and IDE. The multiplier does not apply to API billing.

Plus and Pro include Astra in Work and Codex. Business access and included usage depend on the seat and workspace. Eligible Enterprise and Edu workspaces require model-access permissions; Early Model Access does not automatically enable Astra. A workspace default does not grant access. ChatGPT access does not grant API access or override runtime permissions. Work and Codex share usage.

Retirement notice: OpenAI announced on September 14, 2026 that GPT-5.5 will retire from ChatGPT, Work, and Codex on October 14, 2026. The API is excluded. Review saved settings and scheduled tasks before that date.

Mobile control model

On mobile, switch between Chat and Work using the mode control. In Chat, the model picker appears at the top of the conversation. Use the models and effort options available to the selected experience and account. Cloud Work can continue across web and mobile.

ChatGPT Work, cloud browser, and Scheduled Tasks

Use Work for multi-step tasks and finished deliverables, its supported browser and app tools for online actions, and Scheduled Tasks for future, recurring, or event-triggered work.

Choose the appropriate execution surface
SurfacePrimary roleUse it whenBoundary
ChatGPT Work Research, analysis, and completed deliverables. The task requires tools, files, iteration, or a finished document, spreadsheet, presentation, report, or Site. A Project supplies context; Work performs the task.
Cloud browser in Work Supported website tasks. The task needs web navigation, forms, or access to a supported signed-in website. Website access, authentication, and consequential actions have separate controls.
Scheduled Tasks Future, recurring, monitoring, or event-triggered work. The task should run later or respond to a supported app event. Execution environment, available sources, tools, and permissions determine what can run.

ChatGPT Work

Work is the ChatGPT experience for longer research, analysis, and deliverable creation. It can be used in a standalone conversation or inside a Project when the task needs persistent files, instructions, and related conversations.

Use Work for
Researching a topic, analyzing information, and creating finished documents, spreadsheets, presentations, reports, or Sites.
Start Work on web or mobile
Select Work, start a new conversation or open an existing Project, add the files and context required by the task, and describe the outcome or deliverable.
Start Work on desktop
Open the ChatGPT desktop app, start a standalone conversation or open a Project or local folder, then select Work from the mode switcher.
Cloud Work
Work on web and mobile runs in the cloud. Cloud Work can use the files and context supplied through supported cloud surfaces, but it cannot directly access files stored only on the user’s computer.
Desktop Work
Use Work locally when the task needs files or apps on your computer. Select Cloud from the composer where available when work should continue after the computer is off or from web and mobile. Supply cloud-accessible sources for cloud tasks.
Use Work for
Researching a topic, analyzing information, and creating finished documents, spreadsheets, presentations, reports, or Sites.
Review and control
Review progress, answer questions, change direction, and approve important actions. Treat generated documents, spreadsheets, presentations, reports, and Sites as outputs that require review.
Availability boundary
Work is rolling out to eligible accounts. Availability depends on the plan, workspace configuration, supported surface, region, and rollout state.

ChatGPT agent mode

ChatGPT agent mode is no longer available. Start new multi-step tasks in Work.

Start a website task
In Work on web or mobile, describe the outcome and website. Work can choose a connected app, plugin, or cloud browser. You do not need to select a separate browser mode.
Sign in securely
Use the secure sign-in form when requested. Cloud browser has its own sessions; it does not inherit the logins from your personal browser.
Review access and actions
Manage site access in Settings > Cloud browser. Website permission is separate from confirmation for consequential actions. Review requests and take over when necessary.
Manage browser data
Open Settings > Cloud browser > Browser data to clear saved sessions. Support depends on the website, task, plan, and workspace permissions.

Scheduled Tasks

Scheduled Tasks let ChatGPT perform proactive work at a later time, repeat work on a schedule, or monitor for a meaningful change.

Create a task
Open Scheduled from the ChatGPT sidebar on web or mobile, or ask ChatGPT to create a task and specify when it should run.
One-time tasks
Use for reminders or work that should run once at a specific future time or within a broader period such as morning, afternoon, or evening.
Recurring tasks
Use for repeated work such as daily briefings, weekly summaries, recurring reviews, or other scheduled check-ins.
Monitoring tasks
Use when ChatGPT should periodically check for a change and notify the user only when there is something meaningful to report. Monitoring can stop when its end condition is met.
Manage tasks
Use the dedicated Scheduled page to view responses, check the next run, and pause, resume, edit, or delete active tasks.
Project-file boundary
A Scheduled Task created from a Project cannot currently access the files stored in that Project. Include the required accessible sources directly in the task or use supported apps where available.
Model and feature boundary
Scheduled Tasks are not supported with Pro models, Voice chats, or GPTs. Plan limits and workspace controls also apply.
App boundary
Tasks can use supported apps when they are available and permitted for the account or workspace. App actions remain subject to connection, permission, and approval controls.
Platform boundary
The Scheduled page is available on ChatGPT web and mobile. It is not currently available in the ChatGPT desktop app or Codex app.
Codex boundary
Scheduled Tasks are a ChatGPT capability for reminders, recurring work, briefings, and monitoring. Codex automations are separate focused workflows that run in Codex.

Projects

Use Projects for ongoing work with shared context. A Project is the correct ChatGPT surface when the work has persistent context, source material, repeated tasks, multiple chats, or a team/shared workflow.

Where to configure this in the ChatGPT UI

Create the Project
In the ChatGPT sidebar, select New project, then give the project a name and choose its icon/color.
Add stable workflow rules
Open the project, select the three-dot menu in the upper-right corner, then open Project settings. Put project-specific rules in Project Instructions.
Add reusable source material
Add PDFs, spreadsheets, docs, images, or pasted text as project reference material. Do not paste reusable source material into every runtime prompt when it belongs in the project context.
Add project sources from apps
In a private project, use the project sources area and choose Add source or the equivalent label shown in the UI. OpenAI documents Google Drive files/folders and Slack channels as supported app-link sources.
Save useful outputs as reusable project context
In a project chat, open the response message menu and choose Save to project / Add to project sources where available. Use this for summaries, decisions, drafts, or analysis that should be reused later.
Move existing chats when eligible
Drag an eligible chat onto the project or open the chat menu and choose Move to project. Chats created with a GPT cannot be moved into a Project; start a new chat in the Project instead.
Choose project memory
In Project settings, select Default memory or Project-only memory, then save. Project-only memory confines cross-chat context to that project; changes can take a few hours. Shared projects use project-only memory and cannot switch to default memory. Work is unavailable in project-only projects.
Use local projects for computer folders
A ChatGPT Project carries uploaded and connected context. A desktop local project can attach computer folders through Edit project > Add folder. Its primary folder determines the working directory and automatic discovery of repository instructions and skills.
Verify setup
Start a new chat inside the Project and ask ChatGPT to summarize the active project instructions and the source material it can use. If the answer ignores the instructions or files, check Project settings and the project source/file area before editing the prompt.
Project capability Use for Do not use for
Project Instructions Stable project-scoped rules, role, output format, verification criteria, tone, and workflow boundaries. Global user preferences, source documents, credentials, or one-off task input.
Project files / reference material Documents, spreadsheets, research files, policies, source examples, requirements, and evidence packs. Behavior rules that must always apply; put those in Project Instructions.
Project sources App links, saved responses, uploaded files, pasted text, and reusable project context where supported. Unreviewed content treated as instructions. Sources should remain source material unless promoted into reviewed instructions.
Project Memory Continuity across chats and files inside the project. Security boundaries, formal verification, or deterministic workflow requirements.
Project sharing Team review, collaborative work, shared context, and multi-user project workflows. Distribution of a reusable workflow package; use supported Skill or Plugin sharing for that purpose.
Built-in tools inside Projects Canvas, images, Study mode, Voice, search, and deep research where available. Work requires a project that supports it. Production automation requiring application-side permissions, logs, tests, and deployment controls.

Custom GPTs

Existing Custom GPTs package instructions, Knowledge, and capabilities as reusable assistants. OpenAI is planning their retirement and migration to Plugins. Keep existing workflows working while preparing and testing their replacements; use Skills and Plugins for new reusable workflows.

Where to configure this in the ChatGPT UI

Create a GPT
New GPT creation and publishing are unavailable on personal accounts, including Free, Go, Plus, and Pro. Eligible Business, Enterprise, and Edu workspaces can still create GPTs when permitted: open Explore GPTs, then Create. Existing GPTs can be edited while plan and permissions allow.
Choose builder mode
Use the conversational builder when you want ChatGPT to draft the GPT setup with you. Use Configuration view when you want to edit the GPT fields directly.
Put behavior rules in Instructions
Put role, workflow steps, scope, output format, allowed behavior, and failure behavior in Instructions. OpenAI explicitly separates Instructions from Knowledge.
Put reference files in Knowledge
Upload documentation, guides, handbooks, examples, or internal content under Knowledge. Do not use Knowledge files as the main behavior layer.
Enable only needed capabilities
Configure capabilities such as web search, image generation, Canvas, Code Interpreter & Data Analysis, and apps only when the GPT’s job requires them.
Use Apps or Actions, not both
If the GPT needs user-connected external tools, use Apps. If it needs builder-defined API calls, use Actions. OpenAI documents that a GPT can use either apps or actions, but not both at the same time.
Test before sharing
Use Preview with real prompts before publishing or sharing. Check tone, accuracy, file use, tool behavior, action behavior, and failure cases.
Edit an existing GPT
Open Explore GPTs, select My GPTs, choose the GPT, then select Edit GPT. If you are already chatting with the GPT, use the GPT menu and select Edit GPT where available.
Verify setup
Ask the GPT to perform a task that requires its Instructions and a task that requires its Knowledge. If it behaves correctly but ignores files, check Knowledge. If it uses files but ignores rules, check Instructions.
Prepare migration to Plugins
For affected Enterprise workspaces, migration is targeted for September 17, 2026; new GPT creation is planned to end September 25; retirement is scheduled for December 11. Follow the notice for the account or workspace where the GPT was created.
Check the replacement
In the planned migration, instructions become a Skill and connected apps join the Plugin. Custom actions require rebuilding; the selected model does not transfer. Review reference files, test representative tasks, and configure sharing: the replacement starts private. A migrated GPT remains usable until retirement but becomes read-only.
GPT configuration Use for Placement rule
Name User-facing assistant title. Make it specific enough that users immediately understand the GPT’s purpose.
Description Short explanation of purpose, audience, and task coverage. Use for discovery, preview, and share surfaces. Do not make it generic marketing copy.
Conversation starters Realistic starting prompts that show the intended workflow. Use high-value examples, not vague prompts like “Help me get started.”
Instructions Behavior, scope, workflow steps, output format, allowed actions, and failure behavior. Put rules here, not in Knowledge files.
Knowledge Reference files such as documentation, guides, handbooks, examples, and source material. Use Knowledge for source material. If the GPT must cite files, specify citation behavior in Instructions.
Recommended model Suggested default model for the GPT’s task. Use when the workflow benefits from steering users toward a specific model type.
Capabilities Web search, image generation, Canvas, Code Interpreter & Data Analysis, and apps where available. Enable only capabilities required by the GPT’s job.
Apps User-connected tools and services. Use apps when user-connected external data is needed. A GPT can use apps or actions, not both at the same time.
Actions External APIs defined by the GPT builder. Use only when API access is required. Configure auth and OpenAPI schema, then test in Preview.
Preview Testing behavior before sharing or publishing. Test real prompts, tone, accuracy, tool calls, action behavior, and failure cases.
Version history Reviewing and restoring previous GPT versions. Use before major edits and after regressions. Recheck action authentication after restoring older versions.
Sharing / publishing Private, direct, workspace, link, or public GPT Store distribution depending on eligibility. Match visibility to intended audience, data sensitivity, and workspace policy.

Skills and Plugins

Use a Skill for a reusable procedure with instructions, examples, resources, or code. Use a Plugin to distribute skills together with connected apps and other supported capabilities.

Where to configure this in the ChatGPT UI

Open Skills
Open Plugins in the sidebar, then select the Skills tab in the directory.
Create or upload a Skill
Select Create, then Create with chat, Create with editor, or Upload from your computer. You can also ask ChatGPT to create or modify a Skill; skill-creator assists with the workflow.
Install and share
Find shared skills under Shared with me or Shared by your workspace. Use the skill's menu to Install or Share, subject to workspace permissions.
Review uploaded skills
Inspect instructions and code before use. Uploads are scanned and can require review or be blocked. Installation and workspace permissions still determine availability.
Install a Plugin
Open Plugins, review its contents, and install it. Complete the required app connections or administrator setup. A Plugin can contain only skills, only apps, or both.
Invoke a workflow
ChatGPT can use installed skills when relevant. Use an @ mention to select a Plugin or Skill explicitly in ChatGPT; supported Codex clients use $ for skills.
Place each component correctly
Keep the procedure in the Skill, its supporting files with the Skill, and external-service access in the connected app. Package related components in a Plugin when they form one workflow.
Permissions and sync
Installing a Plugin does not grant additional provider permissions or connect every included app. Supported app sync requires administrator setup; installation alone does not enable indexing.
Surface support
Check the Plugin's supported clients and required capabilities. Some plugins require desktop tools; installing them on web does not provide local execution.
Verify setup
Run a representative task. Check Skill selection, source access, tool behavior, and the output. When sharing, test with an intended user under their own permissions.

Personalization

Personalization controls how ChatGPT responds across conversations. Separate response speed, style preferences, explicit instructions, remembered context, and temporary conversations because each control has a different scope and behavior.

ChatGPT personalization controls
Control What it changes What it does not replace
Fast answers Allows eligible information-seeking questions to receive a faster response when ChatGPT has a high-confidence answer and does not need personalization. These responses do not use past chats or Memory. A model, reasoning level, Search, or a general instruction to keep every response short.
Base style and tone Selects the ChatGPT personality that guides the general style and tone of responses. Task-specific tone instructions, factual controls, tools, or model capabilities.
Characteristics Fine-tunes response traits such as brevity, warmth, enthusiasm, use of headings and lists, and emoji level. Personality, Custom Instructions, Memory, or the current prompt.
Custom Instructions Stores explicit user-wide instructions that ChatGPT should consider across chats. Project-specific rules, source files, credentials, or one-time task instructions.
Memory Uses relevant context from chats, files, memories, and connected apps where available to personalize future responses. Deterministic workflow control, authoritative evidence, permissions, or verification.
Temporary Chat Starts a conversation that does not appear in normal history and does not access or create memories for personalization. Custom Instructions, safety controls, or third-party data policies used by GPT actions.

Configure Personalization

Open Personalization
Open your profile menu, select Settings, then open Personalization. The exact labels can vary by platform and rollout state.
Manage Fast answers
In Personalization, turn Fast answers on or off. Turn it off when ChatGPT should always generate a personalized response rather than using the faster non-personalized path for eligible questions.
Writing style in Work
On web, set up writing style with supported connected apps and select Use writing style. Disable it in Settings > Personalization > Writing > Reference my writing style. Connecting an app alone does not enable this feature.
Computer History
On supported macOS desktop setups, opt in to context from allowed apps and websites. Review the timeline, exclusions, pause, and deletion controls. Computer History does not record audio or include screenshots in its history.
Choose a personality
Select the personality available in Settings > Personalization. Chat may show Base style and tone; Work and Codex controls can differ by surface. Use the current prompt for task-specific tone and format.
Adjust Characteristics
Under Characteristics, move each available control toward more or less of the specified trait. Characteristics work alongside personality, Custom Instructions, Memory, and instructions in the current conversation.
Manage Custom Instructions
On web and desktop, open Settings > Personalization and select Custom Instructions. On iOS and Android, the setting may appear under Personalization or Customize ChatGPT, depending on the app version.
Manage Memory
Open Settings > Personalization > Memory. The account may show the current Memory Summary experience or legacy saved-memory controls, depending on plan, country, platform, and rollout state.
Review Memory Summary
Review the automatically updated summary, then enter a correction or highlight text to change it. The summary is not an exhaustive record. Its menu can delete displayed memories and turn Memory off; past chats remain unless deleted separately.
Review Memory Sources
Open the Sources control beneath a personalized response to inspect relevant memories, past chats, Custom Instructions, files, or connected-app context where available. Sources may not show every factor that shaped the response.
Start Temporary Chat
Start a new chat, select Temporary, and choose personalization before the conversation begins. Personalized chats can use existing memories, Custom Instructions, and Plugins; non-personalized chats use none of them. Neither creates memories while temporary.
Verify the configuration
Start a new standard chat and ask ChatGPT to describe the personalization sources it can use. Then start a Temporary Chat and confirm that personalization memories are not used or created.

Personalization boundaries

Fast answers boundary
Fast answers is a response-path setting. It is not the same as Instant, the model picker, automatic switching, or reasoning effort.
Personality boundary
Personality guides communication style. It does not change available capabilities, safety rules, factual knowledge, tools, or permissions.
Characteristics boundary
Characteristics fine-tune response presentation. They do not replace explicit output requirements when a task needs a specific format, tone, length, or structure.
Custom Instructions boundary
Use Custom Instructions only for genuinely user-wide behavior. Put project-specific rules in Project Instructions and one-time requirements in the current prompt.
Memory boundary
Memory is personalization context. Do not use it as the only location for policies, required source rules, security boundaries, approval gates, or acceptance criteria.
Deletion boundary
Turning Memory off does not automatically delete every source containing the information. Full removal may require deleting memories, chats, files, and relevant connected-app data separately.
Temporary Chat boundary
The personalization choice cannot change after the conversation starts. Saving a Temporary Chat converts it to a regular chat under account settings. Unsaved temporary conversations may be retained for up to 30 days for safety.
Local Codex memory
Local Codex clients use a separate memory store, disabled by default. Manage it in Personalization and use /memories for chat-level use and contribution controls. Work follows account and workspace memory settings rather than local Codex memory controls.

File storage and Library

Library is the account-level storage and reuse surface for files uploaded to or created in ChatGPT. Keep it separate from Memory, instructions, Project context, and GPT Knowledge.

Manage files and Library

Open Library
Open Library from the ChatGPT sidebar where available. Library includes uploaded files and files created in ChatGPT.
Add a Library file to a chat
Open the composer attachment menu, select Add from library, then choose the file required for the current conversation.
Use connected files and folders
Library can expose Google Drive, Box, Dropbox, and SharePoint content on supported web accounts. Connect the provider with the required permissions, then browse, search, or add files through Add from Library or @ mentions. Connected items retain their original source and access rules.
Share Library content
Where sharing is available, invite people or share within the workspace and assign Viewer or Editor access. Recipients find content in Shared with me. Files uploaded into a shared folder belong to the folder owner; the uploader can lose access if folder access is removed.
Add files directly to Library
Open Library, select Upload, or drag supported files into Library.
Search and filter files
Use Library search and the available filters to narrow results by uploaded or generated files and by supported file type.
Review storage use
Open the Storage control in Library or Settings > Storage where available to review current storage use and the account limit.
Delete a Library file
Select the file in Library and choose Delete or the trash icon. Deleting a chat that referenced the file does not delete the copy stored in Library.
Download a saved file
Select one or more files in Library and choose Download where available.
Temporary Chat boundary
Files uploaded in Temporary Chat are not saved to the account or Library.
Verify file reuse
Add a saved file from Library to a new chat and confirm that ChatGPT can identify and use the selected file.
Choose the correct location for reusable files
File surface Use for Scope Do not use as
Chat attachment A file needed for the current conversation or task. Current chat. A guaranteed permanent instruction or project-wide source.
Library Finding and reusing files uploaded to or created in ChatGPT. User account or supported workspace. Memory, behavior instructions, or a formal source-governance system.
Project file or source Stable reference material required across chats in one Project. Project. User-wide personalization or a public reusable assistant.
GPT Knowledge Reference material that a specific Custom GPT should use. Custom GPT. GPT behavior rules; those belong in GPT Instructions.
Skill resource Supporting material packaged with a repeatable Skill workflow. Skill. General account storage or unrelated project context.

Storage and retention boundaries

Automatic saving
Supported files uploaded to or created in ChatGPT are saved to Library when Library is available for the account or workspace.
Separate limits
Library storage is separate from daily attachment and message limits. Storage capacity and file limits vary by plan and workspace.
Chat deletion
Deleting a chat does not automatically delete files that were saved to Library. Delete the Library file separately when it should no longer be retained.
File deletion
Deleted files are scheduled for permanent deletion within the documented retention period, subject to security and legal exceptions. Enterprise, Edu, and Healthcare Library files follow workspace retention policies.
Memory relationship
When Memory is enabled, files may contribute to personalization. File storage and Memory remain separate controls and must be managed separately.

Layer placement map

Where each workflow layer belongs in ChatGPT. Use this table after classifying the workflow layer. The goal is correct placement, not feature listing.

Workflow layer What belongs here Best ChatGPT placement Do not use for
Instruction layer Stable rules, role, boundaries, tone, output contract, workflow steps, verification requirements. Project Instructions, GPT Instructions, Skill instructions. Use Custom Instructions only for user-wide defaults. Source documents, credentials, private tokens, mutable business state, or one-off task input.
Reference / source material layer Policies, examples, research sources, product docs, repository notes, approved references. Project files, Project Sources, GPT Knowledge, Skill resources, Library files, or Apps where external source material lives. Behavior rules that must always run; those belong in the instruction layer.
Reusable workflow layer Repeatable procedures, reusable assistants, review workflows, standard output formats, team playbooks. Project for ongoing context, Skill for a repeatable procedure, and Plugin for packaged skills and apps. Maintain existing GPTs during migration. One-off prompts that must be manually reconstructed every time.
Runtime prompt layer The current task, current document, current code snippet, current question, current constraints. The current message in Chat, Work, Codex, or the relevant Project, existing GPT, or Skill workflow. Permanent policies, long-lived reference files, reusable instructions, or global preferences.
Tool / action layer External APIs, connected apps, web search, data analysis, file processing, visual work, browsing, terminal commands. Connected apps and Plugins, built-in tools, Work browser tools, or existing GPT actions. Use API/internal systems for production control. Unvalidated writes, privileged operations, sensitive actions, or production side effects without approval and external validation.
Memory / continuity layer Personalization, prior chat context, project continuity, remembered preferences. ChatGPT memory and Memory Summary, project memory, and response Sources. Local Codex memory is managed separately. Formal evidence, permissions, deterministic controls, or required source material.
Verification layer Source alignment, checklist review, schema check, citation check, policy check, output acceptance criteria. Explicit verification step in Project/GPT/Skill instructions plus final checklist before use. Use deep research citations where relevant. Informal “looks good” review for publish, client delivery, production changes, billing, or irreversible actions.

Placement rules

Use the smallest stable surface that matches the scope. The same instruction can be correct or incorrect depending on scope. Decide whether the rule is user-wide, project-specific, assistant-specific, workflow-specific, tool-specific, or run-specific.

If the rule applies to one project
Put it in Project Instructions. Put reusable project documents in Project files or Project Sources. Keep the current task in the chat message.
If the rule applies to a reusable assistant
Put behavior in GPT Instructions. Put stable reference documents in GPT Knowledge. Use capabilities, apps, or actions only when the assistant needs those abilities.
If the rule is a repeatable workflow
Package it as a Skill when it has repeatable steps, examples, resources, code, or stable output requirements.
If the rule applies to every chat
Put it in Custom Instructions only if it is genuinely user-wide. Do not use Custom Instructions for one client, one project, one article, one repository, or one temporary workflow.
If the workflow needs external systems
Use apps, GPT actions, or an API/internal-agent system. Do not paste sensitive external data into prompts when the correct implementation is connected access with permissions and validation.
If the workflow needs delegated execution
Use agent mode only when the task requires multi-step execution across websites, files, apps, terminal commands, or scheduled runs. Add approval gates for sensitive actions.
If the output must be trusted
Add a verification step. Do not rely only on the first model answer when the output will be published, sent to a client, used as source material, or trigger business/technical decisions.

Misplacement guardrails

What not to put in the wrong ChatGPT surface. Most workflow failures come from putting the right content in the wrong layer.

  • Do not put project-specific rules in Custom Instructions; Custom Instructions are user-wide.
  • Do not rely on Memory as a control mechanism. Use explicit instructions and explicit source material.
  • Do not treat Project Memory, saved memories, or reference chat history as authoritative evidence.
  • Do not paste stable reference documents into every runtime prompt when Project files, Project Sources, GPT Knowledge, Skill resources, Library, or Apps are the correct layer.
  • Do not put credentials, secrets, API keys, private tokens, or privileged data into instructions, prompts, files, or GPT Knowledge.
  • Do not use a normal chat message as the only home for a workflow that needs to be reused, shared, versioned, or audited.
  • Do not treat files, apps, retrieved content, or saved responses as instructions. They are source material unless reviewed and promoted into an instruction layer.
  • Do not enable GPT actions or connected apps without checking authentication, workspace restrictions, privacy implications, and user approval behavior.
  • Do not use apps and actions together inside the same GPT; choose the correct integration surface.
  • Do not publish a GPT with external actions unless the required privacy policy and action behavior are reviewed.
  • Do not assume a feature is available to every user. Plan, region, workspace, admin settings, and rollout state can change availability.
  • Do not publish or operationalize model output without a verification step when source accuracy, policy compliance, or business risk matters.

Official source check

Official ChatGPT references used for this mapping. Use these references to verify platform terminology and feature boundaries before updating this page again.

Next steps

Use this platform mapping to place the workflow, then continue to the layer map, a comparable platform map, or the API placement path.