Small decisions. Interesting possibilities.Submit a project / videoSubmit
Explore what's possible

Agent tooling with Jev

Tools that help agents and command-line users choose their next command, tool, memory, route or safeguard.

98 inspired projects
Agent tooling

Jev Prompt Difficulty

A prompt composer classifies task difficulty when the user finishes typing and offers a faster mode for simple requests.

Runs on demand
Added
X post ↗
Agent tooling

A usage router for Grok Bot

Jev + GrokBot is the best AI agent system I’ve built in my life It just made my setup CHEAPER and FASTER than what 95% of people are running... setup takes literally 7 minutes: prompt → GrokBot → Jev decision → GrokBot execution → result step 1 → open @typesafeai , create API key (keep it off chat paste) step 2 → tell…

Runs on demand
Added
See how it works →X post ↗
Data & analysis · Agent tooling

Seven more SEO and GEO workflows

Jev killed 7 more SEO/GEO workflows 👇 1/ Assess which competitor pages to copy -> It scores every competitor page on answer, depth, proof and freshness, then checks its rank in Google and ChatGPT to show which ones are worth copying 2/ Identify which page elements to change to get cited -> It reads the title, meta…

Runs on demand
Added
See how it works →X post ↗
Agent tooling

Launching agents on a canvas

Jev brought us closer to JARVIS it instantly does things like launch agents on a canvas - without awkawardly waiting for slowGPT LLM loop @clonkapp is now the fastest agent orchestrator on the planet

Runs on demand
Added
X post ↗
Agent tooling

SEO and GEO fixes, 90% cheaper

Jev dropped the price of SEO/GEO fixes by 90% Agents that audit and fix a client's SEO/GEO used to cost us ~$250 Here's where the savings come from: 1/ 30x faster reads of Search Console and PostHog/Mixpanel data 2/ 30x faster checks of what ChatGPT searches on Bing 3/ 30x faster modeling of what users ask Gemini and…

Runs on demand
Added
X post ↗
Agent tooling

Abide coding-agent rules

best coding agent use case for Jev: enforcing rules a linter can't coding agents tend to break rules and some rules can't be codified Jev can now score every turn against such rules and tell the agent what to fix asap open-source:

Runs on demand
Added
X post ↗GitHub ↗
★ 211
Agent tooling

AgentRun reusable workflows

Today I’m excited to show you our new harness called AgentRun, built with @pidotdev and @typesafeai's Jev. It’s built for an agent to learn how to do a job, code itself a general solution, and then get out of the way.

Runs on demand
Added
X post ↗
Agent tooling · Experiments

A draft quality gate

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 silence was safer and stopped sending me anything at all. took a second agent to unstick it. your checker needs a branch for the moment it goes quiet: > let it…

Runs on demand
Added
X post ↗
Agent tooling · Creative

Coaching and writing checks

Alright playing with Jev through Vercel. 1. quick coaching support during a session rather than running through my gateway. 2. Anti-slop detector and fixer.

Runs on demand
Added
X post ↗
Agent tooling

A prompt box that fills itself in

thanks to @typesafeai jev I no longer have fill out all of those fields on prompt boxes. It picks the agent / model / computer / folder for me. - For a major rewrite it uses Fable + Claude Code. - Changes to an ios app run on one of my macs

Runs on demand
Added
X post ↗
Workflows · Agent tooling

Incident triage in Box

🆕@typesafeai dropped Jev this week, a new frontier model optimized for decisions. We put it to work on an incident triage workflow in Box. Jev doesn't generate text. You send it state plus typed questions and it returns booleans with probabilities, enums, and scores in a single pass, so there's no output to parse and…

Runs on demand
Added
See how it works →X post ↗
Agent tooling

A Slack agent, twice as fast

Jev made our Slack agent 2x faster ⚡️ Our agent can be quite slow because it needs to read skills and figure out which tools to call. We used @typesafeai's new model to speed this up by first passing it the prompt and classifying the best skill, tool and params to use before handing it to the agent

Runs on demand
Added
See how it works →X post ↗
Experiments · Agent tooling

Voice intent to tool calls

Played around with @typesafeai Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence. So far, we've used different LLM combinations…

Runs on demand
Added
X post ↗
Agent tooling · Workflows

Corent model routing

Corent’s brain uses @typesafeai Jev now. Not to generate the output, to make the decision before the output gets generated. When a request comes into Corent, you don’t need to tell us which model to use. You send the prompt, the workload and the quality level. Then Jev helps us decide what that request actually needs…

Runs on demand
Added
See how it works →X post ↗
Agent tooling · Workflows

Starchild prompt routing

Starchild just became the first professional-grade app to integrate Jev from @typesafeai We use Jev to help route to LLMs which gave a 20x decrease in cost and 6x increase in speed for prompt classification Here it is classifying prompts in real-time (avg time was 140ms)

Runs in realtime
Added
See how it works →X post ↗
Agent tooling · Data & analysis

Measuring progress in agent traces

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, what it returned but never whether the agent is actually getting anywhere. An agent editing, testing and reverting the same file six times looks perfectly…

Runs on demand
Added
See how it works →X post ↗
Agent tooling

Shipper Website-to-App with Jev

Shipper presents a Jev-assisted workflow for turning website URLs into mobile applications; the full build path is not independently reproduced.

Runs on demand
Added
X post ↗
Workflows · Agent tooling

Orus trade-strategy review

As promised, Jev is now integrated into Orus agents. What is Jev, and how can it help our agents? Jev is a model from TypeSafe AI, built to answer precise questions with structured answers. In Orus, it reviews the trades your strategy proposes, before they happen. It approves the entry, refuses it, or waits for one…

Runs on demand
Added
See how it works →X post ↗
Agent tooling

Skill Router for Claude Code

Just hacked a fun little project - Skill Router (Open source) using Claude and Jev @typesafeai Why? I have ~ 90 Claude Code skills installed and use maybe five. The rest are fine, I just forgot they existed, and Claude won't reach for a skill on its own unless you call it. So I built myself a little personal…

Runs on demand
Added
X post ↗
Experiments · Agent tooling

Intent-aware search in Replicas

small experiment where I used jev to power the global search in replicas. the possibilities of improving UX with models like jev are endless. we can now have things like: - search that understands what users mean - actions that change based on what you're trying to do - routing tasks to the right agent/model…

Runs on demand
Added
X post ↗
yoshi preview
Agent tooling

yoshi

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy.

Runs on demand
Added
See how it works →GitHub ↗
★ 22
Experiments · Agent tooling

Jev and ChatGPT Task Race

i made a @typesafeai jev+chatgpt instance race against a purely chatgpt instance on two super simple tasks to see the difference, 2-3x faster! :o on first-time tasks chatgpt will write a question set for jev on the fly, and then subsequent tasks get super fast https://t.co/gMBtV3ou3c

Runs on demand
Added
X post ↗
Agent tooling

A chief of staff for bots

got @typesafeai's new model Jev as a chief of staff for bots Jev reads the task, wakes the right teammates off the bench and gives each one the right model It is possible on OpenMausBot as it supports all the LLMs from your existing subscriptions Jev as a decision engine is great

Runs on demand
Added
See how it works →X post ↗
Hard-coded rules moved to Jev preview
Agent tooling

Hard-coded rules moved to Jev

Now using @typesafeai Jev in etc AI ends up vibe coding so much AI regex slop if you don't read the code, so I can finally move all this hard-coding to Jev and it's insanely fast! Also for regular LLM calls, it is around 10x faster, 50% cheaper

Runs on demand
Added
X post ↗Website ↗