Agents & automation · 01
PrototypeRoute incident reports from Box
Aaron Levie demonstrates an agent reading an incident report from Box, judging whether customers are affected and how severe the incident is, then moving the file to an escalation, monitoring or review folder.
The decisionWhich queue should this incident enter, and how urgent is it?
The useful boundary is between a short classification and the workflow that acts on it. Folder moves and metadata updates stay in application code.
Agents & automationSupportChoiceScore
Community example · X post
Search & ranking · 02
PrototypeScreen secondhand listings before bidding
In a Spanish-language demo, Alan Daitch pairs Playwright with Jev to review used-item listings. Jev answers checks about the item and its fit; the surrounding workflow discards, bids or asks the seller for missing details.
The decisionDoes this listing match the buyer’s size, budget and other requirements?
The post’s follow-up describes five yes-or-no checks on page text. Browser navigation, offers and seller messages are separate actions that need review rules and safeguards.
Search & rankingAgents & automationPersonal toolsNoul
Community example · X post · Spanish
Personal tools · 03
PrototypeBring up the right slide as someone speaks
Rinte’s Japanese-language demo selects a presentation slide that matches the current spoken topic, without the presenter touching a pointer or keyboard.
The decisionWhich prepared slide best matches what is being said now?
This is a selection task over existing slides. Speech capture and the slide display are parts of the application around Jev; the demo does not show Jev generating slides.
Personal toolsAgents & automationChoice
Community example · X post · Japanese
Track how a conversation is progressing
Kaneko’s Japanese-language prototype updates three meeting signals after each utterance: exploration or convergence, resolved or pending, and disagreement or agreement.
The decisionWhere is the conversation on each of these three axes?
Repeated, bounded judgments can make a live discussion easier to follow. The prototype is a visualization, not proof that the labels accurately represent every participant’s intent.
SupportPersonal toolsChoice
Community example · X post · Japanese
Agents & automation · 05
PrototypeSteer a computer-use workflow with Jev
In a Chinese-language demo, Sac combines Codex and Jev to add a Mac calendar event, showing the same task with and without the Jev-assisted workflow.
The decisionWhich available computer action should follow the current state?
The side-by-side video makes responsiveness visible, but it is one creator’s comparison rather than a controlled speed benchmark. The app still executes and verifies each action.
Agents & automationEngineeringPersonal toolsChoice
Community example · X post · Chinese
Search & ranking · 06
PrototypeMatch news to relevant brands
A Chinese-language demo runs Jev over a stream of news items for 15 brands, assigning structured intent labels and identifying stories that may be relevant to each brand.
The decisionIs this story relevant to a brand, and which intent label fits?
The creator reports a fast batch run. Replies point out visible classification errors, so editorial review and a measured accuracy check matter before using the output for PR decisions.
Search & rankingEngineeringChoiceNoul
Community example · X post · Chinese
Agents & automation · 07
PrototypeChoose a model before the expensive call
Duncan shows a router that asks Jev which model fits an incoming request, then sends the request to that model. Jev makes the routing decision; another model handles the open-ended response.
The decisionWhich available model should handle this request?
A bounded choice can sit ahead of a generative model. The router still needs fallback rules and evaluation against real requests.
Agents & automationSearch & rankingChoice
Community example · X post
Agents & automation · 08
TutorialTurn spoken commands into browser actions
Moritz Kremb builds a voice-controlled browser in a longer tutorial. Speech is transcribed first; Jev then judges the intended action and target among the current page elements.
The decisionIs this a command, and which visible action should run?
Jev is one stage in the loop. Speech recognition, browser state, safety checks and the actual click are handled outside the model.
Agents & automationPersonal toolsSDK & examplesChoiceNoul
Community example · YouTube video
Engineering · 09
Live featureMap mismatched data fields in one click
Bannerbear describes a live feature that maps source fields to template fields even when their names differ, such as avatar to photo or full_name to name.
The decisionWhich source field belongs in each template slot?
This is a compact semantic matching task with a fixed set of candidate fields. A product should still let users inspect and correct a proposed mapping.
EngineeringPersonal toolsChoice
Community example · X post
Engineering · 10
PrototypeRate spreadsheet rows by meaning
Nader Dabit shares a predictive spreadsheet demo: entering a heading such as “Urgency” makes the sheet judge the meaning of each row, rather than only recalculate numeric formulas.
The decisionHow urgent is this row, given its contents and column intent?
A score can augment a spreadsheet when the useful signal is semantic. The demo is a prototype, so its ratings still need testing before operational use.
EngineeringPersonal toolsSupportScore
Community example · X post
Filter a feed with a natural-language rule
Marcel Pociot demonstrates a browser extension that hides or collapses X posts matching a rule written in ordinary language. The extension acts on the returned judgment while the user browses.
The decisionDoes this post match the user’s filter rule?
A yes-or-no decision can make a personal content filter responsive. False positives matter here, so a reversible “collapse” action is safer than silently deleting content.
SafetyPersonal toolsNoul
Community example · X post
Personal tools · 12
PrototypeSort downloads with a decision rule
Marcel Pociot shows a macOS app watching the Downloads folder. It judges whether a new file is an invoice, then files and renames matching documents according to a configured rule.
The decisionIs this file an invoice that belongs in the configured folder?
The creator says low-confidence files stay in place for manual review. That threshold and duplicate detection matter more than making every file move automatic.
Personal toolsEngineeringNoulScore
Community example · X post
Escalate uncertain email classifications
Hassan shows a pipeline that first classifies a batch of emails with Jev, then sends uncertain cases to another model. The example separates a fast first pass from closer review.
The decisionIs this email suspicious enough to escalate?
The valuable design choice is the uncertainty threshold. The creator’s reported accuracy applies to that demo batch, not to every inbox or fraud pattern.
SafetySupportAgents & automationNoulScore
Community example · X post
Engineering · 14
PrototypeScreen pull requests with typed checks
Paolo Rosson feeds a code diff into Jev and receives a set of judgments about possible secrets, SQL injection, authentication changes, missing tests and other review signals.
The decisionWhich risks should a reviewer inspect in this diff?
These are review prompts, not proof that code is safe to merge. Keep human review and deterministic scanners in the loop for consequential changes.
EngineeringSafetyNoulScore
Community example · X post
Pick the next turn in Pac-Man
Duncan sends the maze state as JSON and lets Jev choose a direction when Pac-Man reaches a junction. The game engine then applies that bounded decision in real time.
The decisionWhich legal direction should Pac-Man turn next?
Games make repeated, time-sensitive decisions visible. The demo illustrates the control loop, not a general claim that Jev sees or understands raw game video.
GamesChoice
Community example · X post
Search & ranking · 16
Live featureScore draft posts before publishing
Rob Hallam presents a SuperX demo that asks many fixed questions about each post and uses the answers to rank drafts. It is an example of using scores to guide editing rather than generate the post.
The decisionWhich draft has the strongest signals for this audience?
Ranking is only useful if it correlates with later outcomes. Treat the creator’s performance figures as a demo claim until independently reproduced.
Search & rankingScoreChoice
Community example · X post
Search & ranking · 17
PrototypeTag a competitor’s ad library at scale
Stav Zilbershtein demonstrates classifying a large ad library by customer-journey stage and creative style, then using those labels to inspect a competitor’s campaign mix.
The decisionWhich funnel stage and style describe each ad?
Consistent labels make a large collection easier to compare. The post’s timing and cost are creator-reported; the deeper account analysis is part of the wider workflow, not necessarily a Jev output.
Search & rankingEngineeringChoice
Community example · X post
SDK & examples · 18
TutorialCompare Choice, Score and Noul in three apps
Riley Brown walks through Jev’s three output shapes and shows several small applications, including routing a request to a model and triaging email.
The decisionWhich answer shape fits the decision your app must make?
Start with the contract: pick an option, rate a value or answer a yes-or-no question. The surrounding application remains responsible for acting on the result.
SDK & examplesAgents & automationSupportChoiceScoreNoul
Community example · YouTube video
SDK & examples · 19
TutorialWatch the TypeSafe team explain Jev live
TypeSafe DevRel Allie Laabs joins ThursdAI to explain System One models and the Choice, Score and Noul primitives. The segment includes a tweet classifier and a live game demo.
The decisionWhich typed question should replace an open-ended generation step?
This is useful background from the team, with demonstrations and open questions. Performance and price figures discussed in the interview are the speakers’ claims.
SDK & examplesGamesChoiceScoreNoul
Community example · YouTube video