Level 2 · Guide 07
Research with Claude and verify every source
Before starting Web Search or Research, define the scope, cutoff date, and preferred primary sources. Treat Claude’s synthesis as a starting point and open the cited originals to verify context, date, and every claim used in a decision.
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. Begin with a research brief
Good research starts with a question and source hierarchy, not a broad request to search. Primary sources support decisions; secondary sources help discover context; unresolved disagreement remains visible. In this guide, the first observable move is to define scope, cutoff date, and preferred primary sources.
2. Prioritize primary sources
Map every decision-relevant claim to an opened original source. 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 search results can be current but low quality.
3. Build a claim-to-source matrix
Cross-check conflicts and record what remains unresolved. Record the decision and the remaining uncertainty instead of hiding it in polished prose. The review must explicitly test whether a citation can be real yet out of context.
4. Use citation status, not citation count
Treat the possibility that two sources may use incompatible definitions or dates as a required test case. The intended result is a claim, source, date, and cross-check research table, 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 strategy team compares three policy options using only public material. It sets a cutoff date, prioritizes official pages, opens each citation, and records where two sources use different definitions.
The scenario is newly written for this guide and is neither a customer case nor a performance claim. Its specific deliverable is a claim, source, date, and cross-check research table. 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.
Step 1. Define scope, cutoff date, and preferred primary sources
Define scope, cutoff date, and preferred primary sources. 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.
Step 2. Map every decision-relevant claim to an opened original source
Map every decision-relevant claim to an opened original source. 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.
Step 3. Cross-check conflicts and record what remains unresolved
Cross-check conflicts and record what remains unresolved. 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.
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.
- Search results can be current but low quality
- A citation can be real yet out of context
- Two sources may use incompatible definitions or dates
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 scope, cutoff date, and preferred primary sources
- Step 2. Map every decision-relevant claim to an opened original source
- Step 3. Cross-check conflicts and record what remains unresolved
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 claim, source, date, and cross-check research table.”
- 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.
Authorship and review
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.