Support-triage workbench

First-party playground: paste or edit state and typed questions, then Run live. Answers come back as choice, score, and noul through this site's /api/decide. Independent community site · not an official Convai product. When live inference is unavailable, use the labeled Offline demo further down. Python, cURL, and the notebook call Router from the upstream package.

What this System-1 decision model does

Laya AI is an open-source System-1 decision model from Convai Innovations / NandhaKishorM. One forward pass returns typed answers over text. It does not generate a paragraph you have to parse. You define the questions. The checkpoint fills choice, score, and noul. Run it live on the playground or locally with python -m pip install laya. Independent community site · not an official Convai product.

choice: One label, a probability per option, and a confidence. Routing, intent, topic.
score: Expected level on an ordered rubric. Urgency, frustration, severity.
noul: P(true) from 0 to 1. Phishing, churn, “does this statement hold?”.

Laya vs Jev, from the README

These cells are the upstream README’s routed comparison. This site did not remeasure them. The 0.766 cell is laya-typed-decisions after fine-tuning. On the same 2,000 decisions the English base is 0.362 and the multilingual base is 0.352, under a 0.461 majority baseline. pip install laya does not apply that fine-tune. The full split, including third-party cards, is on Laya vs Jev.

Source: NandhaKishorM/laya README, “Laya (with routing) vs Jev”. Jev latency citations in that README: AbdelStark/jev-benchmarks and nibzard/decision-model-benchmark.
	Jev 1.13.0	Laya (routed)
typed-decisions, 2,000 decisions	0.727	0.766
AG News, 4 labels	0.910	0.950
DAIR Emotion, 6 labels	0.480	0.595
Banking77 (72 vs 77 labels)	0.870	0.425
ECE, lower better, post-temperature	0.246	0.081
p50 latency, 1 question	236–276 ms	32.8 ms

Run locally

Python 3.10 or newer, then python -m pip install laya. The README does not publish a minimum VRAM. After preload, one multilingual question is 32.8 ms on a Tesla T4 and 193–464 ms on CPU. max_loaded=1 reloads on a language switch (7.4 s median on CPU, 10.3 s on a T4). Details: run locally.

Laya AI is not LayaAir

LayaAir is the Layabox game engine. This page is about the Apache-2.0 decision checkpoint in NandhaKishorM/laya. The site is an unofficial community project and is not affiliated with Convai Innovations. The 中文页面 repeats that distinction.

Live playground

Live. Hosted inference through this site's API. Independent community site · not an official Convai product. Checking whether live inference is configured…

Tasks

Routing

Route a ticket, score urgency, and flag churn.

State JSONQuestions JSON

Run live calls POST /api/decide on this site. Hosted inference through this site's API. Independent community site · not an official Convai product. Offline demo is a labeled keyword heuristic with the Router().predict shape. The README says act_probability is not a usable gate.

Offline demo. Local weights are not loaded. This pass is a keyword heuristic with the same JSON shape as Router().predict. Use it when live inference is unavailable.

Checks

These probabilities are the keyword demo, not convaiinnovations/laya. Python, cURL, and the notebook call the package on your machine.

Run live for model answers, or Offline demo for the labeled heuristic. Schema checks appear below either path.

Export the same ticket

Python, cURL, and the notebook match the editors and call the real package. They do not call /api/decide or /api/demo. Router(preload=True) downloads checkpoints on first use. cURL expects laya-serve already listening on 127.0.0.1:8000.

pip

python -m pip install laya

Python

from laya import Router

router = Router(preload=True)

state = {
    "from": "user@acme.com",
    "subject": "Duplicate charge on invoice #4411",
    "body": "Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan."
}

questions = {
    "department": {
        "type": "choice",
        "instructions": "Which department should handle this request?",
        "criteria": {
            "billing": "invoices, payments, refunds",
            "technical": "bugs, outages, system errors",
            "sales": "pricing, new contracts",
            "other": "everything else"
        }
    },
    "urgency": {
        "type": "score",
        "instructions": "How urgent is this request?",
        "criteria": [
            "not urgent",
            "soon",
            "critical deadline or blocking issue"
        ]
    },
    "churn_risk": {
        "type": "noul",
        "instructions": "Does the user threaten to cancel or leave?"
    },
    "refund_requested": {
        "type": "noul",
        "instructions": "Does the user explicitly request a refund?"
    }
}

result = router.predict(state, questions)
print(result["answers"])
print(result["routing"]["model"])

cURL · local laya-serve

# Local laya-serve only. Start it first, then send this body.
#   pip install "laya[serve]" && laya-serve
# Docker: see docs/docker.md (POST /v1/systemone). This URL is not the site demo.
curl -sS http://127.0.0.1:8000/v1/systemone \
  -H 'content-type: application/json' \
  -d '{"state":{"from":"user@acme.com","subject":"Duplicate charge on invoice #4411","body":"Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan."},"questions":{"department":{"type":"choice","instructions":"Which department should handle this request?","criteria":{"billing":"invoices, payments, refunds","technical":"bugs, outages, system errors","sales":"pricing, new contracts","other":"everything else"}},"urgency":{"type":"score","instructions":"How urgent is this request?","criteria":["not urgent","soon","critical deadline or blocking issue"]},"churn_risk":{"type":"noul","instructions":"Does the user threaten to cancel or leave?"},"refund_requested":{"type":"noul","instructions":"Does the user explicitly request a refund?"}}}'

The .ipynb is an unofficial export: %pip install laya, then the same Router script. It is not a Convai notebook.

Open the official Colab notebook. Model card: convaiinnovations/laya. Docker is on Serve with Docker. Preload pitfalls are on Get started.