Skip to content

Level 1 · Guide 02

Choose the right Claude mode for the job

Use Chat for short explanations and drafts, Web Search for current facts, extended thinking for complex reasoning without the web, and Research for multi-source investigation. Define freshness, source count, and reasoning depth first, then choose the simplest mode that meets them.

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. Start with information location

Tool choice begins with where the needed information lives. Current public facts need search, internal material needs supplied context, and complicated reasoning may need more thinking, but deeper settings never replace verification. In this guide, the first observable move is to classify five tasks by information location and error cost.

2. Then choose reasoning depth

Choose the least complex mode that meets each requirement. 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 using Research for a simple draft wastes time.

3. Select by passing criteria

Compare one task in two modes and document the switch condition. Record the decision and the remaining uncertainty instead of hiding it in polished prose. The review must explicitly test whether using Chat for current facts can produce stale claims.

4. Count time and review cost

Treat the possibility that a deeper mode can still produce unsupported conclusions as a required test case. The intended result is a mode-selection matrix for recurring work, not an unreviewed answer that merely looks complete.

Synthetic work scenario

How this applies at work

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

A fictional operations lead classifies five weekly tasks: drafting a notice, checking a current policy, comparing vendor pages, reasoning through a schedule, and summarizing an approved memo. Each task receives a mode and a switch condition.

The scenario is newly written for this guide and is neither a customer case nor a performance claim. Its specific deliverable is a mode-selection matrix for recurring work. 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. Classify five tasks by information location and error cost

    Classify five tasks by information location and error cost. 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. Choose the least complex mode that meets each requirement

    Choose the least complex mode that meets each requirement. 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. Compare one task in two modes and document the switch condition

    Compare one task in two modes and document the switch condition. 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.

  • Using Research for a simple draft wastes time
  • Using Chat for current facts can produce stale claims
  • A deeper mode can still produce unsupported conclusions

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. Classify five tasks by information location and error cost
  • Step 2. Choose the least complex mode that meets each requirement
  • Step 3. Compare one task in two modes and document the switch condition

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 mode-selection matrix for recurring work.”
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. Choose Web Search, Thinking, and Research · 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.