Gain the landscape.

Start Here

Alcony is not a to-do app and not a prediction market. It's a place to think through real decisions using the best of decision science (which involves lots of maths). Think a trade you're watching, a job change, a big purchase: by unpacking the paths you're weighing and the specific uncertainties, you can track the nuance and the changing environment for the right (probabilistic) time to act.

The app puts you into a structured decision-making framework, ensuring you're using best practices from decades of decision science. The fundamental building block is borrowed from professional forecasters — the forecasting question: instead of one gut-feel answer ("I think I should stay"), you break the decision into specific, checkable questions ("Will I get a promising interview in 60 days?"), make an actual prediction on each, and revisit it as evidence comes in. That turns a vague worry into something you can watch get clearer over time.

What brings it all together is the Landscape. The Landscape lets you see these forecasting questions across time, linked to the action paths you can take. Probabilities, AI, and all the maths are built in for you, so all you have to focus on is seeing the big picture.

Why the Balcony?

The name comes from a saying we used in business whenever we were stuck in the weeds: "Let's get up on the balcony!" Three things Alcony is fixing, in order:

Purpose of a Landscape

A landscape is the container for one real situation: it holds the paths you might take (action paths), the events and inputs you need to track (questions), and anything you've learned along the way (evidence, including documents). You don't need to fill all of it in before it's useful — most people start with one question and grow into a full landscape.

What Is a Landscape?

How Forecasting Fits

Two entry points, same underlying tool:

Create a Landscape

Goal: turn a messy situation into a working landscape in a few minutes.

1. From the Dashboard, click New Landscape.
2. You'll land on a blank prompt: "What's on your mind?" Type the situation in your own words — messy is fine. Click Tell Alcony.
3. Alcony may ask a few follow-up questions, then proposes a scope. It prompts you through the rest of the components: a set of action paths, a first round of forecasting questions as editable cards, and a way to link the questions and actions.
4. Keep what's useful, edit or delete what isn't, then confirm to automatically create the landscape.
5. It's quick and everything can be modified later, so just brainstorm away freely — getting started is the most important step.

Once created, the landscape detail page shows three stat boxes (Questions, Actions, Decision Readiness), a Context panel (Notes / Assumptions / Constraints — collapsible, empty until you fill it in), and a Timeline of your questions colored by Open / Resolved / Awaiting outcome.

You can add questions to an existing landscape later with + Add question, or attach a question you already created elsewhere with Link existing.

Read the Action Trigger Matrix

Goal: see which action path is actually ready, and what's still missing.

Every landscape has an Action Trigger Matrix — a grid with your forecasting questions down the side and your action paths across the top. Each cell answers one thing: what does this question need to show for this action path to make sense? It's the piece that turns a pile of forecasts into a "so what do I actually do."

Reading a cell

• Green — the trigger condition is already met.
• Dark orange — informed, and the forecast is trending toward the trigger (probable).
• Light orange — linked and informed, but not close yet.
• Tan — linked, but no predictions yet, so there's nothing to judge.

Hover any filled cell for the question text, the exact trigger — a threshold for number questions, an answer for yes/no, an option for multiple choice — and the current urgency. Each action path column also shows a small readiness gauge: an overall read on how close that path is to being triggered, across every question linked to it.

Editing the matrix

1. Click the pencil icon to enter edit mode (requires ownership on the landscape).
2. Click any cell to open the link dialog. For number questions, set a threshold and direction (e.g. "greater than 5,000"); for yes/no or multiple choice, pick which answer point is relevant to the action. For example, "When CPI rises above 3% it is relevant to my action to sell."
3. Add a new action path with the button at the bottom of the matrix. Remove an action path or a question with the × above its column or row. Warning: removing either one breaks all the links and thresholds you've set for it.

Create and Track a Question

Goal: turn one uncertainty into something you can predict on and revisit.

1. From Questions, click New Question (or + Add question from inside a landscape).
2. Type a rough version of the question. Alcony suggests the question type (yes/no, multiple choice, or a number), an end date, units, and categories — all editable.
3. Create is disabled until the question validates (it needs a clear end date and, for number/category types, units or categories filled in).

Reading a question card

• The badge shows type — Continuous (a number), Categorical (multiple choice).
• The thin bar across the top of a dashboard card shows time elapsed, not answer quality: green means more than 7 days left, amber means 3 to 7 days left, red means 3 or fewer days left.
• A Closed badge means the question has resolved.

Your Dashboard groups questions into three sections

Make and Update a Prediction

Goal: record what you currently believe, and update it as things change.

1. Open a question, click Make Prediction (or Update Prediction if you already have one).
2. Enter your estimate — a probability, a number, or a category, depending on the question type.
3. Every prediction you and others make shows up in the Predictions table (Predictor, Outcome, Confidence, Explanation, Date) — human and AI Analyst predictions sit side by side.
4. The AI Composite Score panel next to the table shows the aggregated view across everyone who's predicted, plus an uncertainty percentage.

Revisit a question whenever something changes: new information, a closer deadline, or a friend or AI Analyst disagreeing with you.

Invite a Collaborator

Goal: bring in another perspective without it feeling like "share this app."

1. Open the question and click Invite.
2. Your invitee gets that specific question to predict on — and they offer their view before seeing anyone else's, which keeps the comparison honest.
3. Optionally let collaborators upload their own documents to the question, via a toggle on the question page.

Collaborator invites draw from the same 30-invite beta budget as everything else — see Invite People.

Use AI Analysts

Goal: get a structured second (or eighth) opinion, not a magic answer.

1. On a question, click Add AI Analyst and pick from the roster. Each analyst approaches the question from a different angle — some map what limits the outcome, some follow incentives, some watch how beliefs spread, some hunt for the surprise scenario (see Meet the AI Analysts). Add as many as you want; toggle each Active or Disabled.
2. Click Run AI Analysts. The button shows the live credit cost before you confirm — each enabled analyst costs 1 credit. If your balance is too low, the button disables itself and tells you so.
3. Results land as new rows in the same Predictions table as human predictions — no separate report or chat view. A Recent AI Analyst Runs list shows each run's status (queued, running, succeeded, failed, refunded).

Meet the AI Analysts

Every analyst looks at the same question but starts from a different place. The best results come from picking two or three with different viewpoints and comparing their reasoning. Analysts marked (numbers) answer number questions with a point estimate; the rest weigh in on yes/no and multiple-choice questions.

Set an Outcome

Goal: close the loop once you know what actually happened.

1. Open the question once you know the answer (it doesn't have to have hit its end date).
2. Click Set Outcome, choose the real result.
3. The question moves to Closed / Completed, and your score updates based on how your predictions tracked the eventual outcome.

Add Context: Documents

Goal: ground a question or landscape in real information instead of memory.

1. Go to Documents and drag a file in, or click to pick one — PDF, DOC, DOCX, TXT, CSV, or XLSX, up to 50MB.
2. Each file shows a status badge — Queued → Processing → Ready (or Failed) — that updates on its own every few seconds.
3. From a question page, use Find Documents to link an existing file, or Upload a Document to add one directly. A question can also allow invited collaborators to upload their own documents, via a toggle on the question page.

Invite People

Goal: invite friends to Alcony and share what you're working on.

Three separate flows, sharing one invite budget:

All three draw from the same capped quota — beta accounts get 30 accepted invites total, shown as "X of 30 beta invites used." Once that's hit, sending more requires a support-side limit increase; there's no in-app way around it.

Track Credits

Goal: understand what's costing you credits and how many you have left.

1. Credits shows your live balance plus a transaction history (Welcome Credits, AI Prediction, Refund, Admin Grant).
2. The only thing that spends credits today is running an AI Analyst (1 credit per analyst run). Everything else — creating landscapes/questions, making your own predictions, uploading documents — is free.
3. There's no in-app way to buy more credits during beta — but we're also not charging for them. You'll get monthly refreshes.

Cost & Pricing

Goal: know how pricing works, so costs is not a surprise.

Alcony runs on a credit system: AI Analyst runs and research refreshes (upcoming feature) cost credits. Creating landscapes and questions, making your own predictions, and uploading documents stay free. Our subscription tiers:

Need more without changing your subscription? À la carte credit bundles ($5, $10, $20) never expire and top up any plan.

Quickstart: Create Your First Landscape

More Quickstarts

Common Questions