I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations.
I hooked it up to web search, wikipedia, weather, todoist and home assistant.
Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!
I hooked it up to web search, wikipedia, weather, todoist and home assistant.
Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!
Sep 17, 2026 · 7:16 PM UTC
55
66
1,191
115,690
Watch the full explainer: youtube.com/watch?v=QbYBRj…
2
2
51
11,957
@CodingGarden How does it handle an ambiguous request between two tools? A quick clarification before changing a Home Assistant device seems more useful than forcing a route. Curious whether you use a confidence threshold or a separate “ask” outcome.
1
0
3
2,698
@ScottShapiroUXDion to jev for home assistant "no device or room is mentioned at all" - this then asks for a follow up that extracts and matches the name to a device in the home.
We can do a similar thing for ambiguous tool calls. Provide jev an option "More than one tool call can satisfy this a follow up prompt to choose, OR detect high match percent in multiple tools and automatically give a follow up to the user before executing.
We can do a similar thing for ambiguous tool calls. Provide jev an option "More than one tool call can satisfy this a follow up prompt to choose, OR detect high match percent in multiple tools and automatically give a follow up to the user before executing.
1
0
10
2,440
@CodingGarden What happens if you say something like "turn the light to green then after 5 seconds turn it to red"?
1
0
0
1,351
@LightningK0alaate a new "timer" tool and make it available to jev but definitely doable! Jev would just respond with which action to time delay, and how long. Then we pass that off to a background queue that invokes it when necessary.
Compound requests are a bit tricky though. The smart home example from typesafe AI actually detects a compound request, passes to an llm to de-compose into individual commands. Then passes each command to jev.
Compound requests are a bit tricky though. The smart home example from typesafe AI actually detects a compound request, passes to an llm to de-compose into individual commands. Then passes each command to jev.
1
0
5
1,180
@CodingGarden no LLM on the chat path is the claim. when wikipedia comes back messy, does Jev still pick the next tool, or do you fall through to a language model for the sentence?
1
0
1
1,438
@ethereaglehq The answer is directly from the article right now.
It detects a wikipedia lookup. Gets the article. Then does a second request that includes the full article where each sentence is an option for jev to choose.
See their guide here: docs.typesafe.ai/cookbooks/sema…
It detects a wikipedia lookup. Gets the article. Then does a second request that includes the full article where each sentence is an option for jev to choose.
See their guide here: docs.typesafe.ai/cookbooks/sema…
1
0
8
1,238
@CodingGarden curious how jev picks the tool and the args without an LLM in the loop. keyword rules or a tiny classifier. i tried ollama for local routing before and the arg parsing falls apart the second the prompt gets vague. whats your fallback when it cant decide which tool to fire
2
0
2
3,215
@49agents"choice" to jev - "Which tool would fulfil the user's latest request (taking the conversation into account)?" and the options are a dynamic list of every available tool.
For arg extraction / matching on the user prompt there is a seperate question for every single available tool like: "For a weather request: which city or place does the user want the weather for? If they don't name one, pick the place from the earlier request." and the options provided are extracted from the user prompt as a list of options. Could be the prompt split on spaces, could be smarter word pairs.
For arg extraction / matching on the user prompt there is a seperate question for every single available tool like: "For a weather request: which city or place does the user want the weather for? If they don't name one, pick the place from the earlier request." and the options provided are extracted from the user prompt as a list of options. Could be the prompt split on spaces, could be smarter word pairs.
1
0
10
2,872
@CodingGarden One of the tool call is a LLM? for explanations?
1
0
0
1,005
@LifeOfPhat Nope! That's just a wikipedia lookup. Jev extracts the topic the user is asking about, queries wikipedia, then a follow up is sent to jev with the content of the wikipedia article asking which line from the article answers the user's prompt.
0
0
6
973
@CodingGardenen building a similar website helper with ProgramAsWeights. It combines small neural functions for routing and answering with ordinary code controlling the flow.
The functions are compiled from English descriptions and can run locally on CPU, without external model API calls.
Code: github.com/programasweigh…
Demo: programasweights.com/#ask
The functions are compiled from English descriptions and can run locally on CPU, without external model API calls.
Code: github.com/programasweigh…
Demo: programasweights.com/#ask
0
0
2
234
@CodingGarden TypeSafe: Jev is not a chatbot and cannot chat
People: *immediately turn it into a chatbot*
People: *immediately turn it into a chatbot*
0
1
7
372
@CodingGarden I was thinking exactly the same thing about using Jev as a routing mechanism. It fits the scenario extremely well!
0
0
1
226
@CodingGarden github.com/AboveColin/HA-… I made an Home Assistant integration for the ones interested! You are able to create sensors out of the jev classifier, automations or integrate it into your home assistant conversational assistant!
2
0
1
152
@CodingGarden and I gave it access to a whole falcon-9 class rocket and it was about to launch and land!
x.com/uttkarsh_42/st…
x.com/uttkarsh_42/st…
so I gave jev full control of the falcon-9 class rocket
full launch to landing
no autopilot, no scripted trajectories, no safety veto in the code
every decision was made by jev ( you can see decisions at the bottom of the video)
and yeah it was able to land the booster
245 calls and and $0.04 in API calls
for sim I used mujoco
and the configurations were 42m booster, 425 tonnes, 9 engines, real atmosphere, mach dependent drag, wind and propellent depletion
the vehicle was going ubstable every .8 secs, and jev's decesion making takes place at ~1Hz and output in ~0.4 sec
so I gave jev these controls
> launch or hold
>engine count for every burn( it chose 5 for landing by itself !)
> when to light that burn
>ascent cutoff, coast, entry, legs, touchdown
so after giving all these controls to jev the experiments begun
and after 12 runs and tweaking multiple things it managed to land by itself
I will write a full article about it
and what I did with experiments and whet I tweaks I made
but for some final thoughts
people are saying it's just a classifier
yes, but it's a very good and effective classifier, and its speed and decision making, open up a whole new work for real life tasks and implementationa
I will also open source the whole repo for this after cleaning up the clutter in my code
so this is the short demo
I hope you like it
0
0
2
513
@CodingGarden Seems like a backward step since all the responses have to be pre-coded. Like Apple Siri, it can tell you the weather in Denver, but not much else
0
0
1
62
@CodingGarden Do you guys think that JEV could replace machine learning algorithms?
For example to predict how many customers a grocery store will have in this specific date.
For example to predict how many customers a grocery store will have in this specific date.
0
0
0
54
@CodingGarden If jev is used for user entry parsing, why not use the simple !weather !wikipedia etc. command parsing?
You would never have it guess wrong and we are back at where chat bots have started.
You would never have it guess wrong and we are back at where chat bots have started.
0
0
0
77
@CodingGarden LLM을 쓰지 않고 도구 선택과 인수만 Jev가 맡는 구조라면 역할 분리가 선명하다. 출처까지 붙는 즉답형 비서가 얼마나 안정적인지 궁금해짐
0
0
1
311
@CodingGarden I also played with Jev based text generation.
I did the thing you're not supposed to do and tried text generation with typesafe...
1
0
0
106
@CodingGarden Impressive demo! Thanks for sharing it.
0
0
1
475
@CodingGarden I wonder how it performs when the answer needs to be the result of thinking and deduction. Jev didn’t have thinking right?
0
0
0
157
@CodingGarden Is this open source? GitHub somewhere? Would love to see
0
0
0
50
@CodingGarden Nice work! Quite innovative use of Jev. Getting so many ideas from this!
0
0
1
248