Skip to main content

Using Projects

A Project gives you a pre-configured workspace where the context is already established before you type the first message. The model knows what it's working on, what tools it has, and what constraints apply - because you defined all of that once in the project setup.

Starting a conversation​

Type in the chat input on the project home page and send. The model receives your message along with everything assigned to the project: the system instructions, the list of available tools, and any knowledge bases configured as reference.

You don't need to re-establish context each time. A project for customer support already knows it's helping the support team. A project for engineering already knows the coding standards and has access to GitHub.

Using @ mentions​

Type @ in the project chat input to open a picker showing everything assigned to the project: prompts, workflows, scripts, databases, and connectors. Select any item to direct the model to use it.

Use @competitor-analysis to research Acme Corp,
then pass the findings to @briefing-generator

All assigned tools are available to the model at all times - but @mentioning a tool is an explicit directive. The model is instructed to always invoke a tool you've @mentioned by name. This is the difference between "the model might choose to use this" and "use this now, specifically."

You're not limited to one @ mention per message - name several and describe the order you want them applied.

Chaining prompts and workflows​

Because a project has multiple tools available simultaneously, you can chain them in conversation:

  • Research with one workflow, then summarize with a prompt
  • Extract data using a script, then format it with a template prompt
  • Run a competitor analysis, then pass the findings to a briefing generator

Each step's output is available in the conversation context for the next step. You're orchestrating a sequence without writing any code - just describing what you want in natural language and referencing the tools by name.

Building on accumulated knowledge​

If you've assigned a memory folder as Reference, the model automatically draws on it when relevant. If you've assigned one as Output, workflow results get saved there over time.

This means a project can build institutional knowledge across sessions. A research project that saves findings to a memory folder gets smarter with every run - later conversations can draw on everything that's been captured before.

A practical example: a competitive intelligence project that runs a research workflow weekly (saving to a "competitors" memory folder), and whose chat always has that folder as reference. When someone asks "what do we know about Company X?", the model searches the accumulated folder rather than starting from scratch.

Sharing and team access​

Set the project to Shared and every org member can open it and work inside it. They see the same tools, the same system message, the same knowledge base. Individual conversations are still private unless shared explicitly.

This is how teams standardise how they work with AI - everyone working in the same project uses the same tools and follows the same instructions, without each person needing to remember to set things up the right way.

What the model sees​

When a project chat starts, the model receives a context block structured as:

  1. Project owner instructions - your system message, framed as high-priority directives the model must follow
  2. Built-in tools - web search and web fetch, if enabled
  3. Integrations - each connected MCP server by name
  4. Prompts and workflows - each assigned tool listed with its name and description
  5. Knowledge bases - each assigned folder listed with its role (reference, output, or both)

The model can use any assigned tool without you @ mentioning it - it reads the context and decides what's relevant. @ mentioning a specific tool is an explicit instruction: "use this one now."

Writing good tool descriptions matters. The model picks tools based on their names and descriptions. "Competitor Analysis: Research and summarize a company's positioning" is more useful than "Analysis Tool: runs the analysis workflow."