Case wall
Jev AI Agents cases, page 5
107 public posts filed under Agents. English summaries on this page, with a link to each case.
Last updated
These are the public posts filed under the Agents category.
No posts match these filters.
@0xkaushik_k built JevScope, which watches an agent and asks Jev whether each step is aligned, progress, repetition, or stuck, then plots that over time. They describe a coding agent stuck on a race condition where the curve shows it and no log line says “I’m stuck.” Code is said to be coming.
Got early access to @typesafeai Jev and spent a few hours building on it. The problem I keep hitting: agent traces tell you which tool ran, how long it took, wh…
Quoted @CompleteSkeptic
@Mnilax put Jev between GPT and themselves to kill drafts that broke their rules. Jev then stopped answering, and the agent treated silence as safer and sent nothing until a second agent unstuck it. They list branches for a quiet checker: pass it tagged unverified, hand the span to a big model, queue and retry, or wake a human if the action is irreversible.
it's f*cking insane Jev sat between GPT and me, killing every draft that broke my rules before i saw it. good setup. then Jev did not answer. the agent decided…
Quoted @Mnilax
@ashutoshftw built a semantic circuit breaker so agents that try different actions from the same wrong assumption still get stopped. In one stuck run they report 12 model calls down to 4 and 19.9K tokens down to 5.1K.
Jev unlocked a new way to stop AI agents from spinning. Agents do not always repeat the same action. Sometimes they try different things based on the same wrong…
@Mnilax wired Jev into the routing layer of a build that had been running on Astra and says the same task finished 37 minutes sooner with no malformed responses to retry. The post also cites TypeSafe’s published figures: $0.042 per million input tokens with free output, 67.8% matching Sonnet 5 on their eval at 294x less cost and 195x the speed, 0.114s versus 8.566s for GPT-5.6 Terra on the same demo, and about 10 decisions per second in the Doom demo.
man who co-invented ChatGPT just shipped a model that does in 0.114 sec what GPT Astra does in 8.5. i wired Jev into the routing layer of a build i was running…
Quoted @CompleteSkeptic
@keiranhaax told a Hermes agent to test the TypeSafe Jev model on an iOS app they are developing. Hermes recorded the screen and sent it on Telegram. They say more testing will follow.
Told my hermes agent to test the @typesafeai Jev model on an iOS app I’m currently developing for OSS Hermes recorded the screen and sent it to me on telegram I…
Quoted @trycua
@King_of_Calera posts a slowed-down demo asking whether Jev can run multi-agent swarms that self-heal live productions before clients refresh. The text does not spell out the implementation.
Yes, but can Jev do multi-agent swarms? Enterprise solutions that self-heal live productions before clients can even refresh their browsers? (Demo slowed down f…

@parcadei says to ask Jev whether the available state has enough evidence first, and to classify intent only after the evidence clears a calibrated threshold.
Ask Jev whether the available state has enough evidence first; classify intent only after the evidence clears a calibrated threshold.
@parcadei says to use Jev to find gaps in an active skill from incident reports, then replay past failures as evaluations before promoting an update.
Use Jev to find gaps in an active skill from incident reports, then replay past failures as evaluations before promoting an update.
@parcadei says that after a failed attempt, use Jev to judge whether the retry is meaningfully different; otherwise replan, escalate, or stop.
After a failed attempt, use Jev to judge whether the retry is meaningfully different; otherwise replan, escalate, or stop.
@parcadei says to check task drift at each state transition and to redirect, escalate, or pause the agent when it crosses a threshold.
Check task drift at each state transition and redirect, escalate, or pause the agent when it crosses a threshold.
@parcadei says to use Jev to select the right skill from names and short descriptions before the task reaches the main model.
Use Jev to select the right skill from names and short descriptions before the task reaches the main model.