ChatGPT - Projects

Projects keep related conversations, files, and instructions together in the University of Maine System (UMS) ChatGPT Edu workspace, so you don't have to re-explain your work every time you start a new chat.

What Projects are

A Project groups related conversations, files, and instructions into one workspace. Instead of dozens of disconnected chats in your sidebar, everything for one piece of work stays in one place, with shared context across every conversation in it.

Think of a Project as a folder that also remembers what you're working on. When you start a new chat inside a Project, ChatGPT already knows the background, can use your reference files, and follows the instructions you set.

Why use Projects

In a regular conversation, context resets with each new chat. That's fine for one-time questions, but it slows you down on work that runs over days or weeks. You end up:

• Uploading the same files again
• Re-explaining your goals
• Restating formatting preferences
• Hunting for the conversation that has a specific output

Projects solve this with:

• Shared context across related conversations
• One place for reference files
• Instructions that apply to every conversation in the Project
• An organized workspace that keeps related work together

Create a Project

Step 1: Start a new Project

In the ChatGPT sidebar, select Projects or the + next to it. Give the Project a clear name, such as:

• Fall 2026 Course Redesign
• Annual Report Drafting
• HRIS Data Cleanup

Step 2: Add instructions

Every Project has an instructions field for context and rules that apply to all its conversations. Use it to explain:

• What the Project is about
• What role ChatGPT should play
• What tone or writing style to use
• What formatting to follow
• Any rules or limits

For example, instructions for a grant-writing Project might say:

This Project is for drafting and revising an NSF grant proposal for our research on adaptive learning systems. When I ask for help with writing, use a formal academic tone appropriate for NSF reviewers. Keep paragraphs concise and evidence-driven. When I upload data, help me summarize findings in a way suitable for inclusion in the proposal narrative. Always flag claims that would need a citation.

You set the instructions once, and they apply to every conversation in the Project.

Step 3: Upload reference files

Files you upload to the Project are available in every conversation in it. You can add PDFs, Word documents, spreadsheets, text files, images, and other supported files, up to 40 files per Project.

Useful Project files include:

• Style guides or templates
• Policy documents or handbooks
• Datasets you are working with
• Earlier drafts of a document
• Research papers or technical specifications

Project files stay available in every conversation in the Project. Conversation files are available only in the conversation where you uploaded them.

Step 4: Start conversations

Create new conversations inside the Project as you need them. Each one uses the Project's instructions and files. You might keep separate conversations for outlining, data analysis, drafting, revision, planning, and final review. They're separate chats, but they share the same Project context.

Step 5: Share the Project (optional)

To work on a Project with colleagues, open the Project and select Share, then add people from the UMS ChatGPT Edu workspace. Projects can't be shared with people outside the UMS workspace. Share only files and instructions that everyone you add should see.

Tips and examples

Tips

• Name your conversations. ChatGPT creates a title automatically, but a clear name makes outputs easier to find as the Project grows.
• Keep instructions focused. Avoid instructions that are too broad, conflict with each other, or cover unrelated work. If you're doing two very different tasks, use two Projects.
• Keep files current. When a draft, dataset, policy, or template changes, replace the old file. ChatGPT uses whatever files are in the Project now.
• Use Projects for recurring work. Weekly reports, monthly data reviews, ongoing documentation, and regular meeting prep all benefit from a standing Project.
• Don't overload one Project. If it starts covering unrelated topics, the instructions and files can work against each other. Split the work into separate Projects.

Examples

Course development

A faculty member creates a Project to redesign an introductory biology course.

They upload:

• The current syllabus
• Department learning outcomes
• Accessibility guidelines

The instructions tell ChatGPT to focus on active learning and backward design. Over several conversations, they write new learning objectives, draft assignments, and build a revised schedule, all with the same shared context.

Research

A researcher creates a Project for a study that runs several months.

They upload:

• Literature review notes
• Data collection instruments
• Early datasets

Separate conversations cover refining the methods section, exploring the data, and drafting the results. The instructions keep an academic tone and remind ChatGPT to flag statistical claims that need checking.

Department reporting

An administrative team creates a Project for an annual report.

They upload:

• Last year's report
• This year's data summaries
• The required reporting template

The instructions set the format, section headings, and word counts. The team shares the Project so each person can draft their section with the same files and instructions.

IT documentation

A technical team creates a Project for runbooks and knowledge base articles.

They upload:

• The team's documentation style guide
• Existing articles as examples
• Current procedures and technical references

When a system or process changes, they start a new conversation in the Project to draft updated documentation that follows the team's standards.

Event planning

A staff member creates a Project for a campus conference.

They upload:

• The venue contract
• Last year's schedule
• Speaker biographies
• The event budget spreadsheet

Across several conversations, they draft the agenda, write speaker introductions, create attendee messages, and work through budget scenarios, with every conversation aware of the event details.

Projects or plugins

Custom GPTs are retiring December 11, 2026. Plugins replace them. If you built a GPT, see the ChatGPT Edu FAQ for how to move it to a plugin.

Projects and plugins do related but different jobs.

Use a Project when

• The work is ongoing
• You need several related conversations
• You want shared files and instructions across them
• You need an organized space for one piece of work

Use a plugin when

• You repeat the same task often
• You want consistent results every time
• You want others to run the task the same way
• The task needs the same files or apps each time

You can use both. Work out a process in a Project, then turn what you learned into a plugin for broader use.

Limitations

File limits

A Project holds up to 40 files, and very large files can hit size limits. Keep the most important reference material and remove outdated files.

Instruction length

Keep Project instructions focused. If they run to several pages or need complex setup, a plugin may fit better.

Context limits

ChatGPT can only consider so much in one conversation, even with Project files and instructions. Very long conversations may lose earlier details. When that happens, start a new conversation in the same Project and add a short summary of the earlier work.

Questions about Projects?

Start a chat Call 1-800-696-4357

Prefer to stop by in person? Check Service Desk Hours and Availability for current hours, phone, email, chat, and walk-up locations.

Environment

• University of Maine System (UMS) ChatGPT Edu workspace
• Projects
• Eligible UMS students, faculty, and staff
• Web browser at chatgpt.com, plus the ChatGPT desktop and mobile apps