Perplexity basic search in a browser, with a free account if prompted, and somewhere to keep your notes. No Pro Search, file upload, paid model or API key is needed.
Stay on the free route
Stay with basic search rather than Pro, Research or paid creation features. Search answers and citations can be wrong or incomplete. If a source cannot be opened or does not support a claim, leave the claim unverified instead of guessing.
Original practice lesson · Official references checked 14 October 2026 · Button names may differ between app versions.
A narrow question gives you something concrete to verify. We will research file formats rather than ask the tool to choose an entire business strategy.
Create a note headed “PNG and JPEG for a website”. Write the question below and record today’s date.
Define the intended output: three practical points for choosing between the formats. Keep it about published format characteristics, not legal, medical or investment advice.
Open basic Perplexity search and ask the question. If a paid mode is selected, switch back to the ordinary search option.
Practice example
For a beginner making website images, compare PNG and JPEG. Explain transparency, lossless versus lossy compression, and why the best file size depends on the image. Prefer primary documentation such as MDN or the format maintainers. Link the original sources and flag anything uncertain. Keep it to three points.
STEP 2 · ABOUT 7 MIN
Open the sources behind two claims
Read the original pages, rather than treating the generated answer as the final source.
Open the citation for the transparency claim. Find the passage that discusses the relevant format and write a short paraphrase in your own words.
Open the compression claim’s citation and check whether it distinguishes lossless from lossy compression. Record the source title, publisher, URL and access date.
Prefer documentation from the format or platform maintainers. A source label is useful context, but it does not prove that a particular sentence supports the answer.
Practice example
Claim: [one precise sentence]
Source title and publisher: [from the original page]
URL: [direct source link]
Supporting passage: [location or a short note in your own words]
Accessed: [date]
Status: supported / unclear / unsupported
STEP 3 · ABOUT 5 MIN
Test an overconfident conclusion
Good research also asks where an answer stops being reliable.
Ask the follow-up below. Compare it with the first answer instead of assuming the newer response is better.
Do not accept a universal file-size winner: content, dimensions and export settings affect the result. Mark any claim without accessible support as unverified.
If a citation is broken, search for the document title and publisher. Use a working original source or leave that point out.
Practice example
Which part of your answer depends on the image or export settings? Would it be justified to say PNG always produces a smaller website file than JPEG? Identify the evidence and separate established properties from recommendations.
STEP 4 · ABOUT 4 MIN
Write and save your own three-point brief
Turn the research into a small reusable explanation with evidence attached.
Write three points in your own words, with a source link next to each supported factual claim. Leave out any point you could not verify.
Add a final line: “For a real image, export both suitable formats and compare size and visible quality.” Keep research notes distinct from a tested result.
Save the brief and the question template. Reopen one source link from your saved copy to confirm you can retrace your work.
TRY IT YOURSELF · ABOUT 5 MIN
An old article appears in a current comparison
You are checking a tool’s current free export limit. A two-year-old review gives a number; the provider’s current plan page gives a different number.
Original fictional scenario · choose an answer, then read the explanation.
See a worked example and review checklist
Claim table: allowance | exact current provider plan URL | relevant tier and billing conditions | date read | confirmed or still unclear. Do not treat a search snippet as the full evidence.
The source supports the exact claim.
I checked the relevant plan and conditions.
I recorded source dates and unresolved questions.
Try it with a new example: Find one question the current page still does not answer and mark it unconfirmed in the brief.
This checks one practice decision, not your real work. Answers save only in this browser when storage is available.
MAKE THE LESSON YOURS
Keep your practice notes
Record what you made, what you checked and what you want to improve. These notes stay in this browser; they are not sent to us or synced to another device. Clearing browser data removes them.
Optional · up to 2,000 characters.
YOUR NEXT SMALL STEP
Put your practice to work
Repeat the task with a fresh brief. Check the result before using it for a real project.
Checked 14 October 2026. Tool plans can change; consult the provider before choosing an upgrade. These beginner exercises have not been presented as certified or exhaustive product testing.
Progress saves in this browser. No site account needed.
THE OTHER FEW
Find the few things worth knowing.
Explore AI tools, software and technology through official sources, clear trade-offs and practical comparisons, so you can find the few that matter to your task.
Finder · live intelligence
Tell us what you are trying to do. Add constraints when they matter — they are applied before fit is scored.
Popular searches:
🔥 Fresh Few
Recently added to our catalogue, with a reason to explore each one.
💎 Hidden Gems
Editorial alternatives with a specific reason to consider them.
📊 Popular Categories
More from The Other Few
Personal Few
Build the few tools that work together.
Describe the outcome, not the software. The Other Few turns the job into a practical stack, keeps overlaps visible, and explains the trade-offs.
Stack suggestions are task-fit decisions, not product rankings. Commercial relationships must never change compatibility.
READY
Tell us the outcome.
We'll break it into jobs, choose the fewest sensible tools and show the trade-offs.
Evidence-first: current pricing, feature availability and platform support should be shown only when verified from an appropriate source.
THE OTHER FEW · INTELLIGENCE LAYER
From task to decision.
The shortlist now explains the fit, the trade-offs and what to do next.
PERSONALISED FIT
✦
Task understanding
Translate natural-language goals into task signals before matching products.
GoalUse caseConstraints
◎
Compatibility
Show why a tool fits this search instead of presenting a permanent product score.
PlatformExperiencePriority
↗
Decision path
Move naturally from shortlist to profile, alternatives, compare and saved tools.
ExploreCompareSave
DISCOVERY
Go beyond the shortlist.
Browse editorial collections when you want to explore rather than solve one task.
Fresh FewOnly products with a genuine freshness signal.Explore →
Hidden GemsInteresting products that deserve a closer look.Explore →
Popular CategoriesStart with the job, then narrow to the Few.Browse →
VERIFIED SOURCES · EDITORIAL FIT · NO PAID RANKING
THE OTHER FEW · CHANGE RADAR
Know what changed.
Freshness should mean something. Change Radar separates verified catalogue facts from unverified change signals, so a “new” badge never becomes a guess.
Catalogue freshness
18 / 18
published products with verification records
Important: this prototype does not invent product changes. A product only becomes “Changed” when an evidence-backed change event is supplied by the verification pipeline.
THE OTHER FEW · WORKFLOW INTELLIGENCE
Build the few tools that work together.
Start with an outcome, break it into jobs, then build the smallest sensible workflow. The engine highlights overlap and trade-offs instead of stuffing every possible tool into the stack.
What are you trying to accomplish?
Describe the outcome in plain English. Don't worry about naming tools.
Decision rule: one tool can cover multiple jobs where the fit is strong. We prefer a smaller stack when the extra tools don't add enough value.
Start from a workflow
Templates are starting points, not rankings.
Your workflow
Build a workflow to see the jobs, tools, overlap and trade-offs.
Nothing built yet.
RECOMMENDATION GRAPH
See why the Few connect.
The recommendation layer connects tasks, constraints, products, alternatives, workflows and evidence without turning the catalogue into a popularity ranking.
GRAPH ACTIVE
EXAMPLE DECISION PATH
1 · GoalBuild a website for a small business.
2 · ConstraintsBeginner · web · low-code · ease.
3 · Candidate setReplit · Lovable · Claude — narrowed before presentation.
4 · Trade-offLovable favours simplicity; Replit offers more control; Claude is broader rather than purpose-built for the build.
Compatibility is task-specific. It is not a permanent product rating.
Graph signals
These are the relationships the engine can reason over as the catalogue grows.
Important: the graph does not invent evidence. Unsupported claims remain unsupported until verified.
PERSONAL DECISION LAYER
Make the decision smaller.
Bring your goal, saved tools, workflows and fresh changes together. The Other Few narrows the decision without pretending there is one universal winner.
● Decision context ready
Launch a businessBuild a websiteCreate videosResearch & decide
GoalWaiting
ConstraintsWaiting
Your FewLocal saves
ChangesFreshness ready
Start with the outcome.
We'll turn it into a smaller, clearer decision using the intelligence already built into The Other Few.
Fit is contextual. Editorial judgement, evidence and commercial relationships remain separate.Private on this device.
Intelligence Core
Make the catalogue smarter, not just bigger.
The intelligence layer now treats products, tasks, constraints, alternatives and workflows as connected evidence. Expansion is staged into verification lanes rather than filling the catalogue with unverified entries.
18 core records · verification-first
18Core records
7Categories covered
14Relationship types
0Fabricated records
Connected catalogue
Core products are connected to the tasks and categories they are already structured to serve.
Expansion lanes
These are research lanes, not unpublished product claims. A lane becomes catalogue data only after source verification and taxonomy review.
Editorial rule: catalogue breadth never outranks evidence quality. A product can enter the research queue without entering the public Few.
Intelligence Core
One brain. Every decision.
The catalogue, Finder, Decision Engine, workflows, Your Few and freshness signals now have a shared conceptual layer. The goal is not more results — it is better decisions with fewer tools.
● CORE MODEL READY
Decision graph
The same product can play different roles depending on the user's outcome and constraints.
18core products
7active categories
0saved tools
0watched tools
GoalOutcome
IntentTask
ConstraintsFit limits
ProductsCatalogue
DecisionFew
Help us understand what’s useful
With your permission, we use Google Analytics cookies to measure visits and interactions, such as page views, project progress, downloads and link clicks. This sends usage information to Google. You can reject analytics and still use the site, or change your choice using Analytics settings at the bottom of any page.