# Prompts for Perplexity: grounded answers from the web

> How to write Perplexity prompts for the Agent API presets (fast, low, medium, high): specific questions that seed better searches, capped lists, honest 'not found' answers, and filters as parameters instead of prose.

Source: Promptea — https://www.promptea.me/en/guides/perplexity-prompt-guide · Language: English · Last updated: 2026-11-14

## What makes Perplexity different

- Perplexity searches the web before answering and returns the sources it used, so you can check each claim against the page it came from.
- It runs as an agent loop: on each step it can search, read the results, and decide whether to search again or answer. Your prompt shapes the searches, not only the final text.
- It handles current events, prices, product specs, and fast-changing facts far better than a model answering from training data alone.
- Use it when freshness or verifiable sources matter: recent releases, current regulations, live pricing, 'what changed since…' questions.
- Avoid it for creative writing, long-form drafting, or tasks where web retrieval adds noise rather than grounding.

## Sonar is gone: which preset to pick

- Perplexity ended support for Sonar Chat Completions on September 27, 2026 and recommends the Agent API for all new work. In the API you now choose a preset instead of a Sonar model.
- fast — single-fact lookups, definitions, and quick summaries. Write one pointed question.
- low — everyday research with light multi-step lookups. Perplexity's recommended starting point.
- medium — multi-hop browsing that chains evidence across many sources. State the full analytical question.
- high — the broadest coverage and longest reasoning. Write a research brief, not a question.
- Perplexity also documents an xhigh preset, its most capable, for open-ended agentic work (running code, long tool-use loops). Use it when the task is a project, not a question.

## Patterns that work well with Perplexity

- Be specific and use the vocabulary relevant pages would use: 'energy efficiency ratings of heat pumps vs. gas furnaces for homes' beats 'which heating is better?'. Your question seeds the first search.
- Add two or three words of context when a term is ambiguous (a product name, a country, a year).
- Cap list lengths: 'the 5 most relevant…'. Without a cap, the length is arbitrary.
- Give it an explicit out: 'If the sources don't answer this, say so instead of guessing.' This is Perplexity's own advice for reducing hallucinations.
- Ask it to flag near-misses: 'If results are about a different year, a parent company, or a similar product, state the mismatch first.'
- Describe the structure you want instead of pasting example answers; example content pulls the search toward its own topic.

## Constraints: parameters beat prose

- In the API, put hard limits (allowed domains, date ranges, region) in the web_search filters, not in the prompt. Filters apply on every search; prose may not carry through every step of the loop.
- In the Perplexity app there are no filters, so a short prose constraint ('prefer official announcements') is fine, but treat it as a preference, not a guarantee.
- Don't ask for URLs in the answer text. Sources come back separately; the model can mistype a URL it writes out.
- Keep custom instructions short: they are re-read on every step. In the API, setting instructions replaces the preset's built-in system prompt, so only override it when you need app-specific behavior.

## Templates

### Current-state research with sources

```text
What are the 3 most important developments in [specific topic, with the terms an expert would use] between [start month year] and [end month year]?

For each development:
- What changed, who it affects, and why it matters (3–4 sentences).
- Cite the sources that support it, preferring official announcements and primary documents.

Finish with one short paragraph on what is still uncertain or disputed.

If the sources don't cover part of this, say so instead of filling the gap. If a result is about a different period, product, or organization than the one I asked about, state the mismatch before using it.
```

[Open in Promptea](https://www.promptea.me/en/analyzer?prompt=What+are+the+3+most+important+developments+in+%5Bspecific+topic%2C+with+the+terms+an+expert+would+use%5D+between+%5Bstart+month+year%5D+and+%5Bend+month+year%5D%3F%0A%0AFor+each+development%3A%0A-+What+changed%2C+who+it+affects%2C+and+why+it+matters+%283%E2%80%934+sentences%29.%0A-+Cite+the+sources+that+support+it%2C+preferring+official+announcements+and+primary+documents.%0A%0AFinish+with+one+short+paragraph+on+what+is+still+uncertain+or+disputed.%0A%0AIf+the+sources+don%27t+cover+part+of+this%2C+say+so+instead+of+filling+the+gap.+If+a+result+is+about+a+different+period%2C+product%2C+or+organization+than+the+one+I+asked+about%2C+state+the+mismatch+before+using+it.&purpose=text&target=perplexity)

### Deep-research brief (high preset)

```text
Research brief: [topic]

Scope: [what is in / what is out]
Period: [start] to [end]
Geography: [countries or markets]
Analysis dimensions:
1. [dimension 1, e.g., current pricing models]
2. [dimension 2, e.g., regulatory changes]
3. [dimension 3, e.g., main providers and how they differ]

Report structure (at most 5 sections, most relevant first):
- Executive summary (5 bullets max)
- One section per dimension, with sources for every factual claim
- Open questions and conflicting evidence

Where sources disagree, show both positions. Where no reliable source exists, write "not found" instead of estimating.
```

[Open in Promptea](https://www.promptea.me/en/analyzer?prompt=Research+brief%3A+%5Btopic%5D%0A%0AScope%3A+%5Bwhat+is+in+%2F+what+is+out%5D%0APeriod%3A+%5Bstart%5D+to+%5Bend%5D%0AGeography%3A+%5Bcountries+or+markets%5D%0AAnalysis+dimensions%3A%0A1.+%5Bdimension+1%2C+e.g.%2C+current+pricing+models%5D%0A2.+%5Bdimension+2%2C+e.g.%2C+regulatory+changes%5D%0A3.+%5Bdimension+3%2C+e.g.%2C+main+providers+and+how+they+differ%5D%0A%0AReport+structure+%28at+most+5+sections%2C+most+relevant+first%29%3A%0A-+Executive+summary+%285+bullets+max%29%0A-+One+section+per+dimension%2C+with+sources+for+every+factual+claim%0A-+Open+questions+and+conflicting+evidence%0A%0AWhere+sources+disagree%2C+show+both+positions.+Where+no+reliable+source+exists%2C+write+%22not+found%22+instead+of+estimating.&purpose=text&target=perplexity)

## Frequently asked questions

### When should I use Perplexity instead of ChatGPT or Claude?

Use Perplexity when the answer depends on facts that change — current prices, recent product releases, today's news, updated regulations — or when you need sources you can check. Models answering from training data have a cutoff and can give stale information with confidence. Use ChatGPT or Claude for tasks where reasoning over material you provide, long-form writing, or nuanced judgment matter more than freshness. A common workflow is to gather sourced facts in Perplexity and paste them into another model for drafting.

### I used Sonar or Sonar Pro in the API. What do I switch to?

Perplexity's migration docs include a table recommending a preset for each former Sonar model; use it as a starting point and confirm on a sample of your own queries, since Perplexity says presets are tuned over time. Support for Sonar Chat Completions ended on September 27, 2026; Perplexity says synchronous and streaming requests are being reformulated as Agent API requests gradually, while asynchronous Sonar requests are no longer supported. The prompt advice in this guide applies to all presets; what changes most between them is how much research you ask for in one prompt.

### How do I check if Perplexity's sources are reliable?

Open the cited sources, especially for important decisions. Perplexity surfaces what it can find and access — that isn't the same as editorial curation, and pages behind logins or paywalls may be missing. For medical, legal, or financial decisions, treat the output as a starting point for your own source review, not a final answer. Asking it to say when sources don't answer the question, and to flag near-miss results, makes gaps visible instead of hidden.
