Session replay to bug fixes (X)

Post on X

Views: 100,914
Likes: 837
Reposts: 31

Read from X on 24 Sep 2026. Counts change daily.

Reported by the author

3M events: 40s, $2.17In 40 seconds, it watched 3,247 sessions, caught 132 rage clicks, 116 dead clicks and 95 JavaScript errors, and opened 213 draft PRs to fix them. All for just $2.17.x.com

Taras’s demo feeds Jev 3 million session-replay events, the recorded clicks, errors and page events from real user sessions, and has it look for signs of a broken experience: rage clicks, where a user clicks repeatedly out of frustration, dead clicks that trigger nothing, and JavaScript errors.

Taras reports that in 40 seconds it went through 3,247 sessions, caught 132 rage clicks, 116 dead clicks and 95 JavaScript errors, and opened 213 draft pull requests to fix them, for $2.17 in total. The post says it can also flag abandoned forms, rank every issue by severity, count how many sessions each bug hit, and write repro steps for a team. It is described as coming soon to Flowsery and through MCP, a standard way for AI agents to call outside tools.

Open on X

View the post on X

PrimitivesScore

Use casesComposite scoring

jev-trader

Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. The public deployment runs in dry-run mode with a mock model.

jarrodwattsOpen

2.2k starsLoop, mock model p50 100 msDecision window ~300 ms/block

ProjectConfidence-gated actions+1

Introducing System One Models and Jev (Hacker News launch thread)

The 1,978-point, 513-comment launch thread. The top comment calls the speed comparison misleading, since Jev only returns structured output, and disputes the cannot-hallucinate claim because a valid type can still hold a wrong value. Others note ordinary LLMs can already be forced into structured output.

albelfioOpen

DiscussionIntent and model routing+3

DSPy: programming, not prompting, language models

Declares typed input/output Signatures for LLM modules and optimizes the underlying prompts and weights against a metric. Its Signature abstraction is the closest widely-used open equivalent of Jev's typed-question interface. Star count is GitHub's rounded display figure.

stanfordnlp38k starsOpen

AlternativeStructured extraction+3

newsjack

Open source skills that read a morning's news feed with Jev and tell a list of brands which stories to act on. In a demo run it read 384 headlines and matched them to 15 brands in 24.9 seconds for $0.19, against 4 of 384 for $0.77 on Claude Opus 5 over the same feed.

Elvis (@elvissun)Open

851 starsCost $0.19vs Opus/headline ~390x cheaper

ProjectComposite scoring

decider: one-pass typed decisions with calibrated probabilities (Qwen3.5-2B)

Open reproduction of the System One model class, fine-tuned from Qwen3.5-2B-Base, returning a probability distribution per typed question in a single forward pass. Serves TypeSafe's POST /v1/systemone wire format so TypeSafe SDKs work unchanged by repointing TYPESAFE_BASE_URL.

Mapika348 starsOpen

AlternativeIntent and model routing+3

pg-jev

PostgreSQL extension that lets you filter, rank and classify rows with plain-language conditions, such as WHERE jev(tickets, 'the customer is angry'). Adds jev_prob, jev_choice and jev_score functions that compose with joins, GROUP BY and ORDER BY, with no index or embeddings. Published on PGXN.

realZachiOpen

329 stars2k rows, cold ~3.5s, $0.0122k rows, cached ~50ms

ProjectSupport inbox triage+1

Menu