Task understanding
Translate natural-language goals into task signals before matching products.
A focused research brief with checked claims, source notes, uncertainty and a review date.
Start step one ↓My learning →Prompt library →
A question about a low-stakes topic, access to original sources and a notes app. A search assistant such as Perplexity is optional; paid deep-research features are not required.
These guides are free. Use the free/manual route for practice; optional upgrades are your choice. Account access and app screens can vary.
Choose one starting tool. You do not need every product here. Check its current plan before starting; these are editorial matches, not measured product rankings.
For working from documents you select; open citations and check the original wording.
For finding web sources; open original pages and check dates and support.
For drafting a summary of supplied text; verify each point against the source.
0 of 3 steps checked
A useful research brief has a boundary. “Tell me everything” makes it hard to judge when the work is finished.
Research scope Question: What paper characteristics should a beginner check for pencil practice? Audience: Adult beginners Needed: Verified characteristics and trade-offs Outside scope: A universal “best” brand Finish: Three checked points and remaining uncertainties
A search assistant can suggest pages. You still need to check the source, its context and whether different pages repeat the same claim.
Source record Claim: __ Original page and URL: __ Author/organisation: __ Published or updated date: __ / not shown Relevant passage: __ Evidence type and limitations: __ Independent of the other source? __
Good research can end with uncertainty. Your brief should help someone understand what the evidence does and does not establish.
Evidence brief Question and scope: __ Checked point 1 + source: __ Checked point 2 + source: __ Checked point 3 + source: __ My inference, if any: __ Uncertainty: __ Review date or trigger: __
That is your three-step guide. Keep practising, or try the next level when you feel ready.
THE OTHER FEW — Build a small evidence brief you can update Level: advanced https://theotherfew.co.uk/learn/start/research/advanced STEP 1: Set a question you can actually answer A useful research brief has a boundary. “Tell me everything” makes it hard to judge when the work is finished. 1. Choose a narrow, low-stakes question, such as which paper characteristics matter for beginner pencil sketches. Define the audience and intended decision. 2. Write what evidence would help: original product specifications, a primary explanation or a clearly described comparison. Separate factual requirements from personal preferences. 3. Choose a stopping rule: a small set of checked claims and a visible uncertainty list. Do not equate a large source count with good evidence. EXAMPLE Research scope Question: What paper characteristics should a beginner check for pencil practice? Audience: Adult beginners Needed: Verified characteristics and trade-offs Outside scope: A universal “best” brand Finish: Three checked points and remaining uncertainties SELF-CHECK: My research has a clear question, boundary and finish line. STEP 2: Find sources, then inspect the originals A search assistant can suggest pages. You still need to check the source, its context and whether different pages repeat the same claim. 1. Search your question manually or with an assistant. Ask for original sources and open the links yourself; skip inaccessible material you cannot verify. 2. Record author or organisation, page title, relevant date, URL and the passage supporting each proposed claim. If no date is shown, record that honestly. 3. Check whether two sources are independent or copied from the same underlying source. Mark opinion, marketing and measured evidence separately. EXAMPLE Source record Claim: __ Original page and URL: __ Author/organisation: __ Published or updated date: __ / not shown Relevant passage: __ Evidence type and limitations: __ Independent of the other source? __ SELF-CHECK: I opened the original pages and recorded support for the claims I plan to use. STEP 3: Write a bounded answer and a review plan Good research can end with uncertainty. Your brief should help someone understand what the evidence does and does not establish. 1. Write a short answer with a source reference beside each important factual claim. Keep preference and inference clearly labelled. 2. List disagreements, missing evidence and conditions that could change the answer. Remove any claim whose original support you cannot locate. 3. Set a review date or trigger, such as a changed specification. Save the brief, checked source list and decision together so another person can retrace them. EXAMPLE Evidence brief Question and scope: __ Checked point 1 + source: __ Checked point 2 + source: __ Checked point 3 + source: __ My inference, if any: __ Uncertainty: __ Review date or trigger: __ SELF-CHECK: My saved brief can be traced back to original sources and has a clear review plan. Self-review only; this is not a qualification.
Saved only in this browser when storage is available. Clearing browser data removes it.
Try the same process on your next project. Use the evidence you collect to choose the next small improvement.
Our examples and practice tasks are original. These references support the platform instructions. Checked 17 October 2026; screens and account features may change.
Workspace and creative photography from Unsplash.
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.
Recently added to our catalogue, with a reason to explore each one.
Editorial alternatives with a specific reason to consider them.
Describe the outcome, not the software. The Other Few turns the job into a practical stack, keeps overlaps visible, and explains the trade-offs.
We'll break it into jobs, choose the fewest sensible tools and show the trade-offs.
The shortlist now explains the fit, the trade-offs and what to do next.
Translate natural-language goals into task signals before matching products.
Show why a tool fits this search instead of presenting a permanent product score.
Move naturally from shortlist to profile, alternatives, compare and saved tools.
Browse editorial collections when you want to explore rather than solve one task.
The recommendation layer connects tasks, constraints, products, alternatives, workflows and evidence without turning the catalogue into a popularity ranking.
These are the relationships the engine can reason over as the catalogue grows.
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.