Jev workflow patterns from working reports
The sources describe several ways to divide work between Jev and a language model. Each arrangement has a different handoff and a different test of whether it helped.
Start with the question the application needs answered
TypeSafe’s API uses state and typed questions. Choice selects among supplied options, Score evaluates a rubric, and Noul gives a probability for a statement. Choice and Score have a confidence field; Noul does not have a separate one. A probability about the answer and confidence in a distribution are not interchangeable fields.
The documentation recommends selecting thresholds according to the domain and the consequence of an action. A result that fits the output type can still be the wrong decision.
Sources:[1] TypeSafe AI[2] TypeSafe AI
A confidence-based handoff to Kimi K3
In Hassan’s email demo, Jev makes a first pass over 100 examples. The application sends 31 cases below a 95% confidence threshold to Kimi K3. The reported combined result is 96 correct decisions in 16 seconds, compared with 1.42 seconds for Jev’s stage alone.
This supplies a concrete handoff rule and a full-pipeline measurement. It does not establish a production fraud policy. TypeSafe’s threshold guidance is domain-specific, so the demo’s 95% boundary should not be copied as a general guarantee.
Sources:[19] Hassan[2] TypeSafe AI
Read the Jev + Kimi reportPruning Claude’s tool history
fast-jev-compaction asks whether old tool calls and their results still matter. Its output keeps user and assistant text verbatim while pruning or shortening tool material. Calls remain paired with results, and recent messages are protected.
This use of Jev changes the context supplied to Claude rather than routing a user question to another model. The plugin falls back to Claude Code’s built-in compaction on errors or insufficient reduction. Its authors caution that a probability does not prove a result is safe to remove.
Sources:[8] tamaratran
Read the Jev + Claude reportSelecting browser actions before generating text
Jev Ultrafast builds an indexed table of observed browser elements. Jev chooses an operation and a compatible target; the agent asks a separate language model for text only when it needs to type. The project documents configurable text helpers, including DeepSeek and Gemini.
The executor checks page freshness and whether the selected target is still usable. The project requires independent outcome verification even when Jev selects DONE. Its README also lists unsupported features, including frames, uploads and pop-up tabs.
Sources:[24] Browser Use
Read the Jev + DeepSeek reportRouting needs information about the candidate models
Jing Wang’s router experiment changed its selected model after another candidate was added. Wang points out that the context supplied no direct price or performance information. This small test cannot establish a cheapest-model policy or a stable quality ranking.
For implementation details, follow the linked project documentation and test its current API behavior. The reports here do not present unexecuted SDK snippets as working integrations.
Sources:[21] Jing Wang
Sources and implementation references
TypeSafe AI
Source checked:
[1] Jev and the Choice, Score and Noul primitives
The documentation describes Jev as a System One model that evaluates state and typed questions. Choice selects an option, Score evaluates a rubric, and Noul returns a probability for a statement.
API behavior documented by the provider. This page does not establish a universal latency, accuracy or cost advantage.
TypeSafe AI
Source checked:
[2] Confidence, probabilities and fallback decisions
Choice and Score include confidence derived from their probability distributions. Noul does not have a separate confidence field. TypeSafe recommends choosing thresholds for the domain and consequences of an action.
Implementation reference. A confidence value is not a guarantee that an individual decision is correct.
Hassan (@nutlope)
Published:
Source checked:
[19] Jev first-pass email screening with Kimi K3 fallback
Hassan tests 50 legitimate and 50 fraudulent emails. Jev classifies them in 1.42 seconds; 31 cases below a 95% confidence threshold go to Kimi K3. The full pipeline takes 16 seconds, gets 96 of 100 correct and costs about $0.07.
Author-reported demonstration, not independently rerun here. The stated cost split is $0.003 for Jev and $0.068 for Kimi. The 1.42-second figure excludes the Kimi stage.
tamaratran
Source checked:
[8] fast-jev-compaction implementation and limitations
The plugin scores tool calls and results, preserves user and assistant text in its output, and keeps calls paired with their results. Its hook falls back to built-in compaction on errors or insufficient reduction.
The README documents early-access Claude Code function hooks, estimated token sizes and a scripted native demo. It explicitly warns that a probability does not prove a result is safe to delete.
Browser Use
Source checked:
[24] Jev Ultrafast action selection and text generation
The agent builds an indexed element table, asks Jev for an operation and compatible target, and calls a text model for TYPE_TEXT. The README describes an OpenAI-compatible helper configurable for Gemini, GLM and DeepSeek.
Project documentation, not a reproduction of Yanhua’s setup. The checked README defaults to Mercury 2.5, requires independent outcome checks, and lists unsupported browser features.
Jing Wang (@jingwangtalk)
Published:
Source checked:
[21] A model-routing experiment sensitive to the candidate list
Wang experiments with a Jev router over DeepSeek, GLM, Kimi, GPT and Claude candidates. Adding Claude Opus 5 changes the selected model from DeepSeek Flash to Claude Sonnet 5. The author says price and performance information was missing from the supplied context.
A small exploratory test. A candidate model appearing in the list does not demonstrate a completed integration with that model, or establish an optimal routing policy.