How to Use the Projects Feature: Build a Specialized AI with a Knowledge Base

AI Navigate Original / 3/23/2026

💬 OpinionIdeas & Deep AnalysisTools & Practical Usage
共有:

Key Points

  • Projects is an essential feature in Claude Pro that lets you combine Custom Instructions and a Knowledge Base to create an AI specialized for specific business workflows.
  • The keys to success are: “one project, one task,” a fixed answer format, and explicitly stating “no guessing.” This is especially effective for internal use.
  • In a practical example using internal manuals, you can upload employment regulations and FAQs to build an HR AI that answers with supporting evidence.
  • When sharing with a team, it’s crucial to clearly define edit permissions, who is responsible for updates, version management, and how to handle confidential information.
  • Tasks where you keep restating the same assumptions should be moved to Projects (not handled in normal chats), dramatically improving both reproducibility and efficiency.

What Is the Projects Feature? Turning One-Off Chats into a “Business AI”

Projects in Claude Pro is not merely a feature for saving conversation history. By packaging goals, tone of voice, reference materials, and work rules into each project, you can create a “specialized AI” that excels at a specific task—without needing to explain everything from scratch every time. That is the biggest value of Projects.

For example, in a typical chat, each time you must preface with something like, “You are the in-house help desk representative. Based on the attached employment regulations and expense reimbursement manual…” On the other hand, with Projects, you can lock this into the project as Custom Instructions and a Knowledge Base. As a result, answer variation decreases, and you get much higher reproducibility even for internal use.

Projects are well suited for use cases like the following.

  • Help desk AI that reads internal manuals
  • Sales support AI built from product specification documents
  • Article-writing AI that learns your company blog tone
  • Inquiry AI by department, such as legal, HR, and accounting

Basic Structure of Projects: Focus on Three Elements

Projects is easiest to understand if you think of it as three main components: the project itself, Custom Instructions, and a Knowledge Base.

ElementRoleSetup Tips
ProjectA container that groups conversations and documents for a specific purposeSplit by purpose, such as “HR FAQ” or “Sales Proposal Creation”
Custom Instructions
(Equivalent to System Prompt)
Fix the AI’s role, answer policy, and prohibited behaviorsWrite not only the target audience and output format, but also reference priority
Knowledge BaseThe set of documents you want the AI to referenceInsert only the latest official versions and reduce duplicate documents

A common stumbling point for beginners is assuming that once you add documents, the system will automatically become perfect. In reality, it becomes more stable when you also instruct which documents to prioritize and how to respond when something is unclear.

How to Create a Project

1. Decide the purpose first

Start with one project, one job, rather than trying to build “an AI that can do anything.” Here are example tasks.

  • Internal policy Q&A
  • Create reply drafts for customer support
  • Review sales proposals
  • Search specifications for the development team

If you expand the scope too much, both the instructions and the documents get mixed, and answer quality drops.

2. Create a new project

From the Projects screen in Claude, choose “Create new,” and enter the project name. Pick something that won’t confuse you later. A good recommendation is department name + purpose + version.

Sign up to read the full article

Create a free account to access the full content of our original articles.