Fast decisionswith Jev

Jev takes a state (a page outline, a ticket, a workflow result) and named questions of three kinds. A yes-or-no question comes back as a probability. A pick-one question comes back as the option chosen and a probability for every option. A rate-it question comes back as a position on a scale you define. Several questions about the same state ride one call, so asking more costs no extra wait. It never produces a sentence, so it cannot be talked into one.

• Three question kinds: yes or no, pick one of up to 255 options, rate on a scale of up to 10 levels
• Every answer carries its probability, and Plexon acts only above a bar set per use
• Released by TypeSafe on 15 September 2026; Plexon pins one version and re-tunes when it moves
• Our own open-source Go client, jev, is what Plexon calls it with

Anywhere a full chat turn was too slow or too expensive for a small choice. The browser and desktop loops are the visible ones: give the page one whole goal and Jev picks each next control from the outline. The rest happen behind the chat, and each falls back to what Plexon did before the moment Jev is unavailable, so nothing waits on it.

• Browser steps and page collection: which control next and its target in one call, whether the step about to be taken finishes the job, and whether a feed has been read to the end. A sequence of steps the AI already knows goes as one batch and spends no decision
• Desktop steps: the same loop over a window in Desktop Automation, from the window text alone
• Plexonaki: whether this is a good moment to speak, what is on your screen when you ask, and a whole job in an app window in one go
• Answers as cards and tables: repairing a mismatch and drawing a placeholder while the real one loads
• Workflows: a Decide step, and a cheap first pass for the Judge step
• Dashboards: widgets that answer questions about other widgets, a check before an alert interrupts you, and the Trader Cockpit tape (both below)
• Long chats: dropping unrelated tool results before a condense, kept text stays word for word
• Memory: the notes that answer your message go along with it, unrelated ones left out
• Update from documents: which documents look unrelated to the bundle, which new version changed only cosmetically, which passages rested on a document you removed, and which staged edit to read first
• Code review: the riskiest change first in the review queue, and in automatic review
• Choosing a specialist, walking your memory, shortlisting files, and an optional check before a risky command
• With Auto Routing on: how hard the request is, which model family, and how deep to think

A dashboard widget can ask questions about another widget's data and draw the answers as a chart. Up to 8 questions go in one call, each a yes or no, a pick-one or a rating. The reason printed under an answer is a sentence the board's author wrote for that option, never text the model made up, and it stays blank when the answer is not sure enough. The widget runs when its source updates, at most once every 5 minutes, and one board makes no more than 60 decisions an hour across all its widgets. The author also picks which fields of the source go out, so the rest of that data stays on your computer.

• Five boards ship with one. Global Intelligence reads a disruption level and the crypto mood, System Monitor gives a health verdict and says when a cleanup would help, Engineering Cockpit flags the errors that need attention today and rates ship risk, Clinic Front Desk rates the day's load from counts alone, and Trader Cockpit reads the trend
• A threshold alert on a monitored board can check first whether the value is worth interrupting you. A clear no holds that one alert back; when no answer comes, the alert fires anyway
• An AI widget on a timer can skip a refresh when a fast decision says nothing has changed. A refresh you click is never skipped
• The watchlist's unusual-move alert asks only once a stock has moved at least 2% and 1.5 times its usual daily move
• Reopening a board within 5 minutes reuses the last answers and spends nothing
• With decisions off or used up, a widget keeps showing its last answers

The Trader Cockpit streams the featured symbol live: Coinbase for crypto, Finnhub for US stocks once you add a Finnhub key, and delayed Yahoo prices for the rest. Press Start on Fast decisions read and, every 15 or 30 seconds, it reads whether the next five minutes go up, down or flat, with a probability for each. A confident read trades a simulated $10,000 paper account. The fills are meant to be unflattering: a buy fills at the ask and a sell at the bid, after the time the call took, never at the midpoint. Beside the profit and loss, a table shows how often each confidence level came true, which says more about the read than one lucky afternoon. Nothing on the board places a real order. It is there to learn from.

• Pro reads one symbol every 30 seconds. Premium reads one every 15 seconds, or up to three every 30
• A position closes at five minutes or at its stop, and the account halts for the day after a 3% loss
• The tape uses at most 35% of a window's decisions and pauses when fewer than 20% are left, so chat and the browser keep theirs
• It spends nothing until you open the board and press Start, and stops within 45 seconds of the board closing. Keep reading with the board closed is a switch in Settings, off from the start
• What goes out is relative market figures: recent moves, the spread, buying and selling volume. Never a brokerage account
• The Stock Trader's four scheduled scans ask a fast decision first and run the full AI check only when it is unsure or off

There is nothing to sign up for and nothing to pay on top. The decisions come with your plan: 1,500 every 5 hours on Pro, 4,000 every 5 hours on Premium, where they run on priority keys. Account usage shows the Decisions row beside messages and images.

• Pro: 1,500 decisions every 5 hours
• Premium: 4,000 decisions every 5 hours, on priority keys
• No TypeSafe account and no key of your own
• The allowance counts calls, not questions, so batching questions is free

Your computer calls TypeSafe directly, so a decision does not go through our server and wait there. The key that lets it do that is handed over encrypted under a key made for your account, lives in memory for ten minutes, and is forgotten. It is never written to a file, never put in a setting, and never shown. Signing out forgets it at once.

• A lease of ten minutes, then a fresh one, with the old key wiped
• Sealed on the server under a master key that never leaves it
• Usage is reported back per lease, so the allowance is counted where the plan lives
• Our server keeps nothing about the decision itself

Two uses send text from an app to TypeSafe: the browser loop sends the page outline, and the desktop loop sends the text of the one window you named. Never a screenshot, never a password field, and a value you asked it to type is masked before it goes. A third, Update from documents, sends short extracts of the documents you are folding and of the edits it staged, never a whole file, and it has a switch of its own. Nothing about a decision is logged, not on your computer and not on our server: the log holds the model name and a request id, and that is all.

• Page text and window text only, for the two loops, and only while they run
• A password field hands the page back to you instead of typing
• The pet reads your screen only with its own switch on, and only when you ask
• Update from documents sends the first 1,200 characters of a document, a short diff of a changed one, the passages that cite a removed one, and at review time the first 800 characters of each staged edit's diff
• A dashboard widget sends only the fields its board names, and none of it is written to a file or a log
• Nothing typed into a page is ever kept