Persistent custom instructions
DocumentedUser-authored preferences can apply across ChatGPT conversations.
View source detailAgent intelligence
Official ChatGPT evidence covers model selection, custom instructions, projects, memory, and tools without establishing a published full system prompt.
ChatGPT is documented as a multi-surface product with selectable models, cross-conversation custom instructions, project-scoped context, controllable memory, and product tools. The selected official sources do not publish a complete current base system prompt or one universal runtime configuration.
Scope: ChatGPT web · ChatGPT apps · Selectable OpenAI models · reviewed Aug 11, 2026
Reviewed product surfaces
Each layer links to the detailed evidence map. Its state applies only to the reviewed evidence.
Source-backed answers
Each answer is scoped to the selected evidence. “Not established” means the evidence does not support the claim; it does not assert absence.
User-authored preferences can apply across ChatGPT conversations.
View source detailProjects can carry instructions alongside chats and uploaded files.
View source detailMemory is separately controllable, with temporary-chat and project-boundary distinctions.
View source detailSearch, research, files, data analysis, images, voice, and canvas are documented product capabilities.
View source detailThe selected official sources do not publish a complete current ChatGPT base system prompt.
Review evidence scopeEditorial guidance
These conservative editorial implications come from the linked evidence. They add no vendor claims or generic prompt advice.
Custom instructions can apply across conversations, while Projects combine project-specific instructions, chats, and uploaded files.
Supporting evidenceMemory has its own controls and boundaries; temporary chats and project settings affect whether it participates.
Supporting evidenceModels, tools, modes, plans, and surfaces can vary, and the selected evidence does not establish the complete base prompt.
Supporting evidenceUseful next actions
Product scope
Evidence status
Official OpenAI help documentation covers product capabilities and user-facing context layers. The review does not claim a complete current ChatGPT system prompt.
Detailed instruction layers
The map separates the unestablished base prompt from custom instructions, project context, memory, model selection, and product tools.
The selected official sources do not publish a complete current ChatGPT base system prompt.
Source detailUser-authored preferences can apply across ChatGPT conversations.
Source detailProjects can carry instructions alongside chats and uploaded files.
Source detailMemory is separately controllable, with temporary-chat and project-boundary distinctions.
Source detailSearch, research, files, data analysis, images, voice, and canvas are documented product capabilities.
Source detailSupporting instruction evidence
Official sources document the product but do not support a standalone public system-prompt page.
Evidence-backed capabilities
Each capability links to its supporting instruction section and keeps its stated confidence level.
| Capability | What the source establishes | Confidence | Evidence |
|---|---|---|---|
| Selectable models | Official documentation distinguishes the ChatGPT product from the models paid users can select. | high | Source detail |
| Custom instructions | Users can provide persistent response preferences through product settings. | high | Source detail |
| Project context | Projects organize chats, files, and project-specific instructions. | high | Source detail |
| Memory controls | Memory can be managed separately, and temporary chats do not use or create memories. | high | Source detail |
| Product tools and modes | Search, deep research, images, files, data analysis, voice, and canvas are documented capabilities. | high | Source detail |
Version evidence
The selected evidence establishes no compatible first-party full-prompt snapshots. Help-center updates are not treated as prompt versions.
Provenance
Every source lists its origin, retrieval date, completeness, publication limits, and rights separately.
Describes product capabilities and model selection, not one universal runtime configuration or prompt.
Open primary sourceDocuments custom instructions, not the complete product prompt or context assembly.
Open primary sourceDocuments project context but not the underlying base system prompt.
Open primary sourceDescribes user-facing memory behavior; implementation details and a complete runtime context are not established.
Open primary source