🚧 TreeTestAi is being rebuilt. You're welcome to sign in and look around — but creating studies and collecting responses is paused right now, so anything you start won't be saved yet. We'll be back soon with a faster version.
✦ AI-Powered · Free to use · Built by students

We needed to run a tree test.
So we built the tool

How a student IA study became a free research pipeline for everyone.

See the whole story, not just a score
Each stage produces a different view of how people actually think about your content. Stack them, and a hunch — "this navigation might work" — becomes an answer with receipts.
01
Card sort
How do people actually group your content?
→
02
Site map
AI proposes a structure in participant language.
→
03
Tree test
Can people find things in that structure?
→
04
Refine
AI suggests fixes. You re-test.
01 · Card sort analysis

What participants think belongs together

Before you design the menu, ask your users how they'd organize it. Three views turn raw sort data into the shape of their mental model.
Similarity matrix
Percentage of participants who placed each pair in the same group.
The darker blocks along the diagonal are the natural clusters hiding in your content — items that belong together whether you planned it or not.
Category label cloud
The group names participants typed, sized by how often they appeared.
Gives you the exact words users reach for — often different from the jargon your team defaulted to. Copy these into your nav labels.
Item confusion table
Each item's top group, second-choice group, and how many groups it ended up in.
Flags orphans — items that never found a consistent home. These are the navigation risks to resolve before a tree test.
02 · AI site map

Sort data becomes an editable tree

✦ AI Insights
Clustered 43 items into 5 top-level groups. Flagged "Comic Books" — split across 3 sorts — suggested elevating to its own branch.
Card sort clusters
Books & Paper12
Collectibles8
Toys & Games14
Home & Kitchen9
AI
Proposed site map
Home Books & Paper Collectibles Toys & Games Home & Kitchen Textbooks Fiction Figurines Sports Vehicles Board games Cookware Décor
Clusters feed directly into a proposed tree. You review, edit, and approve — then AI writes tasks with every correct path verified against the tree.
03 · Tree test dashboard

Did people find what they were looking for?

Six linked views — each answering a different question about the same responses. Together they separate "wrong answer" from "right answer, wrong path" from "right path, felt terrible."
Success rate by task
Direct success, indirect success, and failures stacked per task.
The headline chart stakeholders recognize. Anything under 70% is worth investigating — the color split tells you which fix to try first.
First-click heatmap
Where each participant's first click landed on every task. Green outlines mark the correct top-level branch.
First click is the single strongest predictor of task success. If people don't choose right on click one, it rarely recovers.
Path dendrogram
Every route participants actually took through the tree, with branch thickness weighted by traffic.
Shows the wrong turns, not just the wrong answers — where people got close but derailed. Often more actionable than a success percentage.
Success × time scatter
Each task plotted by median completion time (x) and success rate (y).
Top-left is intuitive, bottom-right is structural issues — different failure modes with different fixes.
Time distribution
Min, quartiles, median, and max completion time per task.
Averages hide outliers. A task with huge variance means some people breezed through and some got stuck — often worth more than the mean.
SEQ ease scores
Single-Ease-Question self-rating (1–7) averaged per task.
Behavior tells you what they did; SEQ tells you how it felt. Tasks that succeed but feel hard are fragile — small friction, big downstream cost.
04 · AI refinement loop

From data to a decision you can act on

A dashboard on its own doesn't tell you what to change. The final step reads the data and writes the edits — so one round reliably becomes two.
↻ Round 2 → Round 3
Success rate up +24% after applying the suggested edits. Tasks T3 & T4 moved red → green.
Problem areas
HighMath Text Book33%
HighDiecast Car17%
MedVintage Camera8%
AI
Suggested edits
↗Elevate "Books" to top-level category
↗Move "Diecast" into Vehicles & Models
↗Relabel "Antiques" → "Vintage & Antiques"
The AI reads the dashboard and writes plain-English edits with severity. Approve, re-run, and the iteration counter tracks success-rate lift across rounds.
Card sort to validated navigation in one pipeline
Every step of the research process — from raw content items to a tested site map — runs inside one tool. AI handles the overhead. You handle the research.
Card Sort
Upload your content, pick open, closed, or hybrid, and share one link. Participants sort in their browser — no software, no account, no install.
AI Site Map
AI reads your sort data and proposes a tree in participants' own language. You review, edit, and approve before the test runs — the AI doesn't ship anything without you.
Tree Test
AI writes realistic tasks with paths verified against your tree, so you never ship a test that asks for something the sitemap can't answer. Collect unmoderated responses and read the full dashboard.
Rich Dashboards
Similarity matrices, first-click heatmaps, confusion tables, path dendrograms, SEQ scores — every view the paid platforms give you, and none of the paywalls.
AI Insights
AI reads the full dashboard and writes a plain-English summary: what's failing, what's working, and what to change. Each recommendation ships with a severity badge — no jargon, no guessing which chart to weight.
Iterate & Improve
Apply the suggested edits, re-run, compare rounds. The iteration counter tracks success-rate lift between tests — so you can show, not claim, that the navigation got better.
Why we built this
Rigorous IA research shouldn't depend on your budget
Every researcher deserves infrastructure that matches their methodology, not their institution's software budget. These tools provide data granularity, but sit behind paywalls that researchers at student budgets can't reach.
01 · Budget
Free, not a trial
Maze starts at $99/mo. Optimal Workshop runs $199/mo. UserTesting climbs to $40k/yr. TreeTest AI runs in your browser on your own API key — Gemini's free tier (1,500 requests/day, no credit card) is more than enough for a semester of research.
02 · Repeatability
Built to run more than once
Paid tools charge per study, so student and indie projects usually end up with one "hope it worked" round. TreeTest AI is built around the iteration loop: apply AI suggestions, re-run, compare rounds. The point isn't one clean report — it's reaching a navigation that actually works.
03 · Accessibility
For designers, not methodology PhDs
AI helps you do the parts paid tools assume you already know — writing unbiased tasks, reading SEQ scores, interpreting first-click heatmaps. You stay on the decisions; the AI handles the vocabulary.
API key
Unlock AI insights with your own key
AI features run through your API key, not ours. No shared quota, no queue, no credit card on our side — you keep direct control of usage and cost.
01 · What it is
A personal key, pasted once
An API key is a personal token that lets TreeTest AI talk to an AI model on your behalf. Paste it in settings once and every AI feature — sitemap clustering, task writing, dashboard insights — routes through your own account.
02 · Recommended✦ Best fit
Claude, by Anthropic
We've had the most reliable results with Anthropic's Claude. Task writing is sharper, sitemap suggestions stay closer to the actual data, and dashboard summaries land with less editing. Gemini's free tier also works and costs nothing.
03 · What it costs
Under $1 for 50+ runs
Negligible. All the testing we did to build this platform cost less than a dollar total, across 50+ AI runs on Claude. A full research cycle — clustering, tasks, insights — lands in pennies.
Get a Claude API key → Or use Gemini (free tier)
Paste the key in Settings → AI. It stays on your device — we never see or store it.
Built by
KB
Kate Besel
katebesel.com kate@katebeseldesign.com
DD
Drake Durflinger
drakedurflinger.com drakedurf@gmail.com
TreeTest AI · Built at SCAD · No tracking, no ads, no paywall
New Study
Step 1 of 7

Study details

Give your study a name, describe what you're testing, and optionally add a research plan so AI can write better tasks.

Study name
Study description (helps AI write better tasks)
Research plan (optional — research questions, user goals, hypotheses; AI uses this for task generation)
Usability Test · Stimulus

What are participants testing?

Pick how your prototype is delivered. Click + mouse-move heatmaps work everywhere; fidelity is highest when we serve your HTML from our own domain.

Usability Test · Tasks

Write the scenarios participants will work through

A good usability task sets a goal without naming the exact button — that way you measure findability, not reading comprehension. Let AI draft from your study brief + prototype, then edit any task to taste.

✦ Generate tasks with AI
Tasks are drafted using your study description, research plan, and the prototype's actual content, applying Nielsen Norman / Krug / Sauro guidelines. Requires an AI key — paste one in AI Settings (top right). Once set, Generate is always one click away.
What makes a good usability task? (Nielsen Norman · Krug · Sauro)
  1. Scenario + Goal structure. Set a realistic situation, then state the goal.
  2. Never name a UI element (no "click Settings", "use the search bar"). Describe the NEED.
  3. Use the participant's vocabulary, not the product's. Real people say "a place to leave a review", not "Feedback Hub".
  4. Second person ("You want to…"). Avoid "I want to…" — it telegraphs intent.
  5. One goal per task. Don't chain unrelated actions.
  6. Measurable success — there's an objectively correct end state.
  7. 1–3 sentences max. Long scenarios get skimmed.
  8. Mix difficulty — some easy targets, some 2–3 steps deep.
  9. Realistic motivation. Give the participant a reason to care.
  10. Ground in the prototype. Don't invent features the product doesn't have.
Tasks 0
Drag to reorder · edit inline · ✕ to remove.
No tasks yet. Use ✦ Generate above, or click + Add task to write one manually.
Usability Test · Share & Collect

How do participants take this test?

Pick one or both. Remote sharing is async — anyone with the link can take the test. On-device is for moderated or in-classroom sessions where the participant takes it on your screen right now.

REMOTE
Share a link
Async, anywhere — best for recruiting beyond the room.
A short, opaque link participants can open in any modern browser.
ON DEVICE
Launch on this machine
Moderated — sit next to the participant and watch them work.
Opens the same runner participants would see, tagged so the response is grouped under the label you pick.
Responses so far
Live count — updates as participants finish. Open Results & Insights for the heatmap and AI friction analysis.
0
Usability Test · Results & Insights

What participants did

Loading responses…

Heatmap by task
Hotspots are anchored to the page — scroll the prototype and they stay locked to whichever element was actually interacted with.
Participants 0
Each row is one completed session. Click to expand.
Card Sort Setup

Define your card sort

Choose how participants will categorise items, then add the cards they'll be sorting.

Card sort type
Choose how participants will categorise your items.
OP
Open
Participants create their own category names
CL
Closed
You define the categories; participants sort into them
HY
Hybrid
You provide seed categories; participants can rename or add
Define categories
Add the categories participants will sort into. Assign hierarchy levels to define primary vs. secondary groupings.
0 categories added
Content items
These are what participants will sort into groups. Type each item and press Enter.
0 items added
Or import items
Paste a list (one per line or comma-separated), upload a file, or drop a screenshot for AI to extract items from.
Add at least 5 items to continue
Step 2 of 7

Your card sort is ready

AI has built a hybrid card sort activity with your items. Share the link — participants will group items in whatever way makes sense to them.

—
Items to sort
0
Seed categories
Closed — fixed categories
0
Responses so far
Share with participants
We recommend 15–20 responses for reliable clustering. The link stays open until you close it.
Live responses
Collecting
Waiting for first response…
Step 3 of 7

Card sort results

Here's how participants grouped your items. Review the analysis below, then generate your site map.

0
Participants
—
Agreement score
—
Avg. completion
✦ AI Insights Card sort analysis
No responses yet. Summary will appear once participants complete the sort.
Problem areas
Strengths
Item confusion table
Items placed in the most different categories — highest ambiguity first.
Item # Groups Top group 2nd group
Top participant category names
Co-sort heatmap
Items frequently sorted together by the same participants.
Co-sort similarity matrix
% of participants who placed each pair in the same group. White = 0%, deep blue = 100%.
✦ AI Insights Card sort analysis
No responses yet. Insights will appear once participants complete the sort.
Step 4 of 7

Proposed site map

AI has clustered your card sort data into a navigation structure. Review and edit any labels, then approve it to generate your tree test.

Import a site map
Paste indented text, upload a CSV, or drop a screenshot.
Indent with 2 spaces (or tabs) per level. JSON tree also accepted.
Site map structure
Click any label to rename. Use "+ child" to nest, × to remove.
Step 5 of 7

Tree test is ready

Your tasks are ready to share. Every path is verified against your site map. Review them below, then share the link.

0
Tasks generated
—
Branches covered
0
Responses so far
Generated tasks
Share with participants
We recommend at least 15 responses for reliable tree test data.
Step 6 of 7

Tree test results

Here's how well participants found items in your navigation. Tasks below 70% success are worth investigating.

0
Participants
—
Overall success
—
Avg. SEQ score / 7
Task success breakdown
■ Found it directly   ■ Found it (with backtracking)   ■ Didn't find it
Participant responses 0 participants
✓ Direct   ~ Indirect   ✗ Fail   ○ Skip
PID Timestamp T1 T2 T3 T4 T5 T6 T7 T8 T9 T10 Score
First-click matrix
Heatmap of where participants first clicked per task. Darker = more clicks. ✓ = correct category.
SEQ scores by task
Mean perceived ease per task (1–7). Dashed line = 5.5 benchmark.
Success x Time matrix
Each dot = one task. Top-left = slow & unsuccessful. Bottom-right = fast & successful.
Time on task
Box = Q1–Q3, centre line = median, whiskers = min/max.
Navigation paths
Tree structure showing paths participants navigated. Thicker lines = more traffic. Red = incorrect path. Green = correct path.
✦ Insights Tree test analysis
Overall assessment
Waiting for responses…
Problem areas
Strengths
Prioritised recommendations
Step 7 of 7 · Iteration 1

AI's suggested improvements

Based on the tree test data, here's what AI recommends changing. Apply what you agree with, then run another round to confirm the improvements.

1
Refinement round · waiting for results
Updated site map
Changes pending
Export study data
Download raw data from each phase for further analysis.
AI Settings
AI Provider
API Key
—
Enter an API key to test the connection.
Your key is stored only in this browser. It is never sent to any server other than your chosen AI provider.
Working…
This takes about 10–15 seconds
Import site map from CSV
Review the file and choose how to parse it.
file.csv
File preview (first rows)
Generate tree test tasks
AI will read your site map, study description, and research plan to write realistic scenarios.
Number of tasks
10 is the standard. Each task targets a specific node in your site map — you can edit, add, or remove tasks after generation.