Free preview. This lesson is part of a paid course that earns the ETA Specialist: Perplexity credential. About this course
Welcome: research with an answer engine, the ADAPT way
In this lesson you'll
- Explain how Perplexity finds sources and writes an answer
- Describe why a citation shows where a claim came from but doesn't prove it
- Apply ADAPT to decide when Perplexity is the right research tool
Welcome
Welcome to Perplexity for Research at Work from the Enterprise Technology Association (ETA). Perplexity is an answer engine: you ask a question, it searches the web (and any files you allow), reads what it finds, and writes an answer with numbered citations. It can also run longer Deep Research tasks that produce reports, keep research organized in Spaces, and work inside its own browser, Comet.
This course assumes you've completed Level 1: Foundations of the ETA Certified AI Empowered Professional.
- Step 1: Assess
Is this a good task for AI, and what's at stake?
- Step 2: Direct
Brief the AI clearly: goal, context, constraints, done criteria.
- Step 3: Assure
Check the output before you rely on it.
- Step 4: Protect
Keep people, data and your organization safe.
- Step 5: Tune
Iterate, then save what works for next time.
Use the steps in order on every task, and loop back to Tune when results fall short.
How an answer is made
- Search. Perplexity turns your question into searches and collects pages.
- Read. A language model reads parts of those pages.
- Write. The model writes an answer and links sentences to the sources it used.
Each step can go wrong. Searches can miss the best source. Pages can be old, biased or wrong. The model can misread a page, merge two facts, or attach a citation to a sentence the source doesn't support. That's why the most important habit in this course is: a citation shows where to check; it doesn't prove the claim.
When Perplexity is the right tool
| Good fit | Poor fit |
|---|---|
| Getting oriented on an unfamiliar topic fast | A legal, medical or financial decision with no expert review |
| Finding sources to read, with links | Questions only your internal records can answer (unless connected and allowed) |
| Comparing public information across vendors or regions | Anything where one wrong fact causes real harm and you can't check it |
| Tracking recent news and changes | Confidential questions your policy keeps off external tools |
Protect: what you type is data too
Your questions can reveal confidential plans: "acquisition targets in Ohio for Q2" tells a story even with no file attached. Follow your organization's AI policy on which tools are approved and what can go in a query, and check your account's privacy settings.
Passwords, access codes, security keys and other credentials
- Personal information
Social Security numbers, birth dates, home addresses, personal phone numbers
- Health information
Diagnoses, medical leave details, patient records
- Financial account details
Bank and card numbers, individual pay records
- Student records
Grades, discipline and other student information
- Confidential business and client information
Unreleased results, pricing, contracts, legal matters, anything under a confidentiality agreement
Some organizations approve specific tools for some of this data. That decision belongs to your organization, not to you. If you're unsure, treat it as off-limits and ask. You rarely need real details: redact, substitute or generalize.
Workplace example: an economic development agency
Priya, a business attraction manager, used Perplexity to scan public information on battery suppliers expanding in the Midwest. The answer named five companies with links. When she opened them, two links were press releases from 2022 about plans later cancelled. Her final list, checked source by source, had three companies, and her memo said how she checked.
Try it
Ask Perplexity a question in your field where you already know the answer well. Then open every citation and mark each sentence supported, partly supported or not supported by its source. How many were fully supported?
What are the main requirements of [a rule, standard or process you know well]? Cite official sources where possible.Key takeaways
- Perplexity searches, reads and writes; each step can introduce errors.
- A citation tells you where to check; it doesn't prove the claim.
- Your questions are data too; follow your policy on tools and topics.