Case wall
Jev AI Agents cases
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.
@joeharris76 points at the reviewer and says you can see it reviewing itself in the PRs, at https://github.com/joeharris76/theseus/pull/98. Jev sizes each PR, from trivial to max, picks routine versus deep capability and the review template (standard, deep, or gate), and decides whether to retry, escalate, or stop when a reviewer fails.
FWIW, here is the reviewer and you can see it reviewing itself in the PRs. https://github.com/joeharris76/theseus/pull/98 Jev sizes each PR (trivial…max), picks…
@tanishqk asks whether Jev demos are still cool. He writes that more coding agents are going toward a “one manager” thread, naming @cursor_ai projects and @AmpCode spaces, and that the old problem is the classic iMessage problem: simultaneous unrelated conversations and back-and-forths in the same thread. He built a demo using Jev that automatically determines whether it should fork the current chat, switch to a previous chat, or stay in the current one.
are jev demos still cool? More and more coding agents are going towards the "one manager" thread approach: @cursor_ai projects, @AmpCode spaces, etc. but the pr…
@shreyabiradar_ says alert fatigue is real during production incidents: they all look equally urgent, and the question is which one to act on first. She introduces alert-triage, to identify the alerts with the highest user impact first, using Jev, a System One model. She links her blog, https://medium.com/@shreyabiradar/how-to-triage-alerts-with-a-system-one-model-94c76c654134?sharedUserId=shreyabiradar.
Alert fatigue🚨is real during production incidents. They all look equally urgent. Which one do you act on first? Introducing alert-triage to identify the alerts…
@jmurray10_ says he wanted one memory for every model, session and bot he uses. He built one, and @typesafeai Jev does a lot of the heavy lifting. The post shows Grok Bot and Claude Code sharing one brain.
I wanted one memory for every model, session and bot I use. So I built one, and @typesafeai Jev does a lot of the heavy lifting. Grok Bot and Claude Code sharin…
@sydneyrunkle says they use @typesafeai's Jev in their software factory Slack app to decide if the agent should respond. It is especially helpful in multiplayer threads, where people are talking to each other and the agent should jump in only when someone actually loops it in.
we're using @typesafeai's jev in our software factory slack app to decide if the agent should respond it's especially helpful in multiplayer threads, where peop…
@kevintheo says he uses a closed choice model, Jev by @typesafeai, as a prompt-injection guard for his email agent. On one test of 1,102 texts it found 82.6% of attacks and 40 of 40 indirect ones, with 0.7% false alarms (old keyword filter 27.3%).
I use a closed choice model, Jev by @typesafeai, as a prompt injection guard for my email agent. In one test on 1,102 texts it found 82.6% of attacks and 40 of…
Quoted @sundarpichai
@MarstonConnell has a custom Slack connector for their agent Gilles. Whenever a thread is responded to, they hand the message to Jev from @typesafeai to check whether it was meant for the agent, so they do not spam the agent in large threads.
Found a really cool use-case for jev from @typesafeai. I have a custom slack connector for our agent Gilles, and any time a thread is responded to, we hand it o…
@PatrikNordinHR says Grok Bot from @cursor_ai coordinates the work, while @claudeai and Codex from @OpenAI work on the tasks together. Jev from @typesafeai helps decide which agent should take the next step. Reason Network from @reasonmachines passes the task and its context, so agents can be switched without briefing the next one from scratch.
Grok Bot from @cursor_ai coordinates the work in my AI setup, while @claudeai and Codex from @OpenAI work together on the tasks. I use Jev from @typesafeai to h…
@kaif9998 used Treg to pull 20 niche YouTube videos and Jev to sort the top 10 into opinion/demo/tutorial for about $0.00112.
MY AI AGENT'S RESEARCH BUDGET: $0.00112 Treg pulled 20 YouTube videos in my niche. Jev sorted the top 10: opinion, demo, tutorial. Top opinion video: 319K views…
@_sarant says the Convex Discord mod bot now uses Jev for moderation decisions and costs less than 10 cents, updating a bot Ian started two years ago.
The @convex Discord bot is a special cookie, Ian built a strong foundation for it two years ago. We updated it recently, added Jev @typesafeai, and bam, we got…
@ericosiu runs recruiting outbound bots from Slack across five sourcing channels. After do-not-contact, title, and tenure checks, interested candidates get seven questions and Jev scores the answers. A daily funnel report lands in Slack; campaigns auto-pause above a 2% bounce rate.
Our talent bots run recruiting outbound 7 days a week from 5 sourcing channels (and any campaign that bounces over 2% pauses itself) I broke down how it works ↓…
@franzbruckhoff had a marketing agent use Treg’s Jev-powered social API to classify TikTok comments about nature sounds for sleep.
I asked my marketing agent working on social media observation to try Treg's new Jev-powered social-api to monitor what people are saying on TikTok about using…
@nicky_sap says Trivy files new findings as Linear tickets, and a Jev classifier on the @cvedotnow feed decides whether a CVE touches their stack. If it does, an agent opens a fix branch and auto-merges when review is green.
How we're handling the deluge of CVEs: Trivy triages new findings into Linear tickets, and we stream the @cvedotnow feed into a Jev classifier that decides in n…

Phone-to-desktop computer use. Jev hands off to Claude when the step is complex. GPT realtime carries the session.
guys…I DID IT! there is no better feeling than watching something you’ve built work this well on camera (even with the rough edges)! this is full scale Claude/C…
A lead-gen agent used Jev to list live Data Engineer roles with salaries: 127 pages, 5 calls, $0.13.
used a lead gen agent to job hunt and it's honestly better at it. 127 pages of live Data Engineer roles with the salary on every row. Snowflake's pay bands IC1…
Lightpanda’s browser agent uses Jev to pick username, password, and submit. 0.53s / 2 calls vs Haiku 7.83s / 8 calls.
Things are getting serious @typesafeai Jev now handles logins in Lightpanda's agent. It picks the username field, password field and submit button from the page…
@hussi9 asks whether Claude uses the skills you installed. In his listing, 43 of 764 had descriptions and 721 were names only. He built SkillRouter: Jev routes to relevant skills, Doctor flags library issues, and a dashboard shows actual loads. It is open source; comment “skill-router” for GitHub.
Does Claude use the skills you installed? My listing: 43/764 had descriptions; 721 were names only. I built SkillRouter: → Jev routes to relevant skills → Docto…
@dgalarza uses Jev / OpenAI Decisions API so Slack agents reply only when a response is warranted.
I've been having fun with Jev / OpenAI decisions API use case. My favorite place to work with my agents is Slack. One thing that has been tricky to fine tune is…
Itential FlowAI note: Jev is either an MCP tool for an agent, or the agent itself, returning typed judgments in one pass.
More on how I've integrated @TypeSafeAI Jev into Agentic Operations with @Itential FlowAI Agents ! System One Design: Inspired by Daniel Kahneman's concept of f…
Zendesk teardown on four review sites in 21 Jev calls via Monid: G2 4.3, Capterra 4.4, Trustpilot 1.8, $0.20.
competitor teardown of Zendesk, four review sites, 21 calls: 4.3 on G2. 4.4 on Capterra. 1.8 on Trustpilot. 91 reviews say "expensive". 20 alternatives, 15 rate…

@Sumanth_077 on JevAgentHarness: Jev gates tool/arg/done calls; AgentDecision-4B cuts cost 81–89% in-loop.
Jev as a decision layer for LLM agents! LLM agents make a lot of small decisions between the bigger reasoning steps: which tool to call, which argument to use,…
@KaranVaidya6 introduces Composio Firewall. Every agent action is evaluated with Jev and custom SLMs; it checks actions and information coming back. Live at composio.dev/firewall.
Agents have a trust problem. Today’s models can do most work. What they need is the right boundaries. In traditional software, those were set at build time. Wit…
@_its_boris says their own gateway was blocking their own agents. A real headline, "When the Guardrail Leaks PII", tripped the security scanner. With Jev as a cheap second opinion, 19 of 20 false alarms cleared, and 0 of 114 fresh attacks were let through. He says that one is ready.
Our own gateway was blocking our own agents. A real headline, "When the Guardrail Leaks PII", tripped the security scanner. With Jev as a cheap second opinion:…