Skip to content

Level 2 · Guide 08

Design durable context with Projects and instructions

Claude Projects apply reusable knowledge and instructions across conversations for the same work. Include only relevant material, define purpose and output rules, and regularly remove sensitive, conflicting, or outdated context.

Product features may change. Check the last verified date and official sources.

Core concepts to know first

Focus on the decisions these terms support in real work rather than memorizing them.

Core concepts

1. A Project is a bounded work context

More context is not always better context. A Project should have one bounded purpose, named source priority, explicit output rules, and an owner who removes stale or conflicting information. In this guide, the first observable move is to define one Project purpose and its allowed source boundary.

2. Knowledge and instructions have different roles

Write instructions for source priority, output, and uncertainty. Preserve the approved input and the evidence behind the result so a reviewer can distinguish what the source says from what Claude inferred. This directly controls the risk that old files can silently override current policy.

3. Source priority resolves conflicts

Assign an owner and date for removing stale or conflicting context. Record the decision and the remaining uncertainty instead of hiding it in polished prose. The review must explicitly test whether unrelated context can distort the task.

4. Memory is supporting context, not authority

Treat the possibility that shared Projects can expose material to unintended users as a required test case. The intended result is a project context map with scope, sources, rules, and review dates, not an unreviewed answer that merely looks complete.

5. Context needs an owner and review cycle

For Design durable context with Projects and instructions, the final concept joins the earlier checks into an operating boundary: use approved inputs, expose evidence and uncertainty, and stop before a consequential action. Ownership and a reproducible review determine whether a project context map with scope, sources, rules, and review dates may move beyond training.

Synthetic work scenario

How this applies at work

This scenario was written for learning and is not a real customer case.

A fictional customer-success team builds a Project for approved onboarding drafts. It uses synthetic examples, labels the current policy as authoritative, archives an obsolete template, and assigns a monthly review.

The scenario is newly written for this guide and is neither a customer case nor a performance claim. Its specific deliverable is a project context map with scope, sources, rules, and review dates. A reviewer can reproduce the work from the synthetic inputs without access to customer, employee, health, contract, or confidential company data.

Try it yourself

Choose one small task and follow the steps. Confirm organizational policy and data boundaries before using sensitive materials.

  1. Step 1. Define one Project purpose and its allowed source boundary

    Define one Project purpose and its allowed source boundary. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

  2. Step 2. Write instructions for source priority, output, and uncertainty

    Write instructions for source priority, output, and uncertainty. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

  3. Step 3. Assign an owner and date for removing stale or conflicting context

    Assign an owner and date for removing stale or conflicting context. Use only approved synthetic material and record both the evidence and any remaining uncertainty.

    Verify: Confirm that another reviewer can reproduce the input, result, evidence, and stop point.

Completion checklist

Check only what you verified yourself. Every item must be checked before saving completion.

Completion checklist

Some items are still unchecked. Review the result again.

What could go wrong?

Plausible language does not guarantee accuracy. Compare the result with originals, calculations, permissions, and current information.

  • Old files can silently override current policy
  • Unrelated context can distort the task
  • Shared Projects can expose material to unintended users

Boundaries that require human review

Academy practice stops at draft, preview, or approval pending. Actions with real impact require separate owner approval outside Academy.

What AI can do

  • Step 1. Define one Project purpose and its allowed source boundary
  • Step 2. Write instructions for source priority, output, and uncertainty
  • Step 3. Assign an owner and date for removing stale or conflicting context

What a person must approve

  • Applicable law, contract, organizational security policy, and explicit approval boundaries take priority. Stop and ask the responsible owner when they conflict.
  • Academy exercises never send, publish, purchase, delete, execute contracts, or change permissions. A responsible person performs any real action through a separate process.

This guide is educational and does not replace legal, security, or privacy judgment for your organization.

Questions about this guide

When is this guide complete?
It is complete when the stated outcome is ready and another reviewer can retrace the inputs, evidence, boundaries, and decision. The target outcome is “A Project context map with scope, sources, rules, and review dates.”
May I practice with real company data?
No. Use synthetic material in the Academy. Real data requires a separate review of policy, legal basis, contracts, minimization, retention, deletion, and the approved environment.
What if the product screen differs from this guide?
Product behavior can change. Check the verification date and official sources, then retest the current account and plan with a small, low-risk example.

Official sources and further reading

Recheck the current product and policy status in these primary sources.

  1. Create and manage Projects · Claude Help Center

Authorship and review

Author
QJC
Last verified
2026-07-23
Update sensitivity
High
Tested product surface
Official documentation and QJC training scenarios using synthetic data
Tested plan
Reconfirm feature and account availability in official sources on the day of use

Save progress

Completion and checklist items are saved only in this browser. They do not sync to other devices or browsers.

Academy does not collect or store work materials, prompts, or outputs. It runs no separate analytics scripts beyond basic server access logs.

QJC Claude Academy is unofficial educational content independently created and operated by QJC. It is not an official course operated, sponsored, certified, or affiliated with Anthropic. Claude and Anthropic are trademarks of Anthropic PBC.