← Back

Shliff Guide: How to Structure and Validate Your Ideas

This guide walks you through the brainstorming app step by step: from your first voice capture, through structuring with AI and sharpening on the idea map, to scoring, validating and exporting as a PDF. For an overview of the features, see the Shliff homepage.

1. What is Shliff — and who is it for?

Shliff turns a vague idea into a branched idea map — so you build the right thing, not the first thing. Every map is an idea tree: you speak or write an idea, branch it out and score its viability.

Shliff is for everyone who has lots of ideas but needs to decide which ones are truly worth pursuing: founders, indie developers, product people — or simply anyone who wants to structure their thoughts. The common thread is always the same: Brainstorm → Sharpen → Validate → Decide.

2. Onboarding: setup on first launch

On first launch, a short onboarding walks you through the core idea of the app (“From spark to decision”, “Speak or write”, “Sharpen & decide”). Then comes the setup — both parts are optional and can be changed later in the settings:

Inside the app, a guided tour and contextual hints (coachmarks) also accompany you right where you need a feature for the first time. You can replay the onboarding at any time from the settings.

Connecting an AI key in the settings
Connect your own AI key — stored securely in the device keychain

3. Capturing an idea: speak or write

The fastest way: press and hold the microphone and describe your idea in one sentence — releasing ends the recording. Alternatively, you can enable “Tap to record (stop/play)” in the settings: tapping the microphone once starts the recording, the stop button ends it.

If you like, speech recognition runs entirely offline on your device (setting “Offline speech recognition (Whisper)” — the model ships with the app); when it's off, the operating system's speech recognition is used instead.

Prefer typing? Choose “Write” and enter your idea as text.

Voice recording of an idea in Shliff
Recording — speak your idea

4. Structure: raw text becomes a root node

After recording (or writing) you see your raw text. Tap “Structure” — the AI turns it into a clear node with a title, description and fitting sub-ideas. “Save” places the root node on the map; from there you keep branching your idea.

Structure: AI generates a title and sub-ideas
“Structure”: title + sub-ideas from your raw text

5. The idea map: sharpening nodes

Every idea lives as a tree on an idea map. Tap a node once to bring it into preview mode; a second tap opens the actions on the node — there you can sharpen it: mark, edit or score it.

Idea map in tree layout
Tree layout: the idea tree at a glance
Idea map in radial layout
Radial layout: the same map, arranged in a circle

6. Triage chips: Important · Maybe · Discard

Use the triage chips to sort your nodes: important, maybe or discard. This way you always know which branches matter, even in large trees. Discarded nodes aren't gone: you can reactivate them later. When discarding, you decide whether only this node or the entire sub-branch is discarded (“Discard this node only” / “Discard including sub-branch”).

Triage chips on a node
Triage chips: Important · Maybe · Discard

7. Branching nodes

You branch new nodes directly off the selected node — via “Write” for text or via the microphone as a voice note. The new sub-idea then hangs as a child of the chosen node. This lets you develop individual aspects of your idea deliberately, branch by branch.

Branching a new sub-idea off a node
“New sub-idea”: a new node branches off the selected node (screenshot shows the German UI)

8. Candidate & Evaluate

Once a branch has proven promising, use the node menu to “Make it a candidate”. The candidate's context is frozen in the process (“Candidate · context frozen”) — from now on, investigation and validation refer to exactly this state. There is only ever one active candidate per map; use “Revoke candidate status” to release it again.

“Evaluate” creates an evaluation of this branch: it summarizes the branch down to the root so you can score it and pursue it further. An evaluation node cannot have child nodes of its own and cannot be included in a synthesis — it is the result, not another branch.

Candidate node on the idea map
The candidate: context frozen, ready to evaluate

9. Research & Questions

On the candidate, two tools help you sharpen the idea further:

In addition, “Prompt” generates fitting AI prompts for the node; with the chat toggle enabled, you can chat with the AI directly. If a candidate's context is updated later, investigation & validation are reset — so the results always match the current state.

Investigation: guided questions about the candidate
Investigation: guided questions, topic by topic
Research view for the candidate
Research: checking assumptions against facts

10. Validate & Score

The investigation first produces an evaluation — the risk map: it names the riskiest assumption and suggests kill criteria. From there, Validate and Score let you check how viable the idea really is.

The rating assigns a score across several dimensions — such as market viability, effort and costs — and condenses them into the overall viability, comparable with other ideas on the map. You can enter the assessment yourself or have it pre-filled via “AI pre-fill”.

The validation plan takes the idea through several phases all the way to a decision — from the criteria (deadline and target values) through launch and measuring to the verdict. You define kill criteria with target and actual values; the overall score (0–100) shows how many criteria are met. At the end there is a clear recommendation: “Pursue”, “Park or discard” or “Consider a pivot”.

Validation plan with phases and kill criteria
Validation plan: phases, deadline, kill criteria, verdict
Evaluation as a risk map with the riskiest assumption and kill criteria
Evaluation: risk map with the riskiest assumption & kill criteria (screenshot shows the German UI)

11. Synthesis: merging branches

Good thoughts are often scattered across different branches. Long-press a node to start multi-select, then tap additional nodes — more than two is fine. “Merge” combines the selected nodes into a new synthesis node. A synthesis only works between different branches — and needs at least two source branches. Discarded source nodes must be reactivated before a synthesis.

Multi-select of two nodes and merging into a synthesis
Two nodes from different branches selected — “Merge” creates the synthesis (screenshot shows the German UI)

12. Library & collections

The library (“All maps”) is the home of all your ideas. There you create a map as an idea collection or as a concrete idea (“New idea” / “New folder”). Long-press to move concrete ideas between collections, or keep them unfiled; double-tap or “Open” takes you inside — “Open idea” opens the idea as its own idea tree.

Library with maps and collections
Library: all maps, collections and concrete ideas

13. Export as PDF

“Export” creates a PDF of your idea or collection. The export contains the idea tree with its nodes, the summary, the initial investigation, the evaluation, questions, research, rating and the validation (including met and missed criteria) — your entire decision basis in one document.

Exporting an idea as PDF via the menu
Via the “…” menu: “Export” generates the PDF (screenshot shows the German UI)