realtime-uiActive Specification

Dynamic UI Component Dispatcher

Enum-constrained component selection for dashboards using Choice + Noul anomaly flags.

Architecture overview

Selects a UI widget from a closed set (chart, table, alert, summary) based on data characteristics. Constrained Choice output avoids misspelled component tags that crash React trees.

Traditional LLM limitation

LLM-generated JSON often invents component identifiers, causing render crashes.

Jev AI tools advantage

Choice is limited to your criteria keys, so the dispatcher can map directly onto a typed component registry.

Official API schema (field names from docs.typesafe.ai)

Source: TypeSafe HTTP API reference. Question IDs below this table are directory example compositions — you choose them.

FieldTypeRangeNotes
statestring | object | arrayPlain text or structured JSONContent to evaluate. Shared across all questions in one request.
modelstringe.g. "jev-latest"Optional; defaults to TypeSafe flagship alias when omitted in SDKs.
questions.<id>.type"choice" | "score" | "noul"Exactly one of three primitivesQuestion ID is chosen by you; answers return under the same keys.
questions.<id>.instructionsstringNatural-language judgmentThe actual question sent for inference (IDs are not sent to the model).
questions.<id>.criteria (choice)Record<option, string | null>1–255 optionsMap of option key → rubric description.
questions.<id>.criteria (score)string[]≥ 2 ordered levelsOrdered level descriptions; score is a weighted position along them.
questions.<id>.criteria (noul){ true?: string; false?: string }OptionalOptional clarification of yes/no meanings. Answer field is noul ∈ [0, 1].
answers.<id> (choice){ type, choice, probabilities, confidence }choice ∈ criteria keys; confidence ∈ [0, 1]Probabilities sum to 1 across options.
answers.<id> (score){ type, score, legend, probabilities, confidence }score may fall between levelslegend maps level index → description.
answers.<id> (noul){ type, noul }noul ∈ [0, 1]Probability that the answer is yes. No separate confidence field.
usage{ input_tokens, output_tokens }Non-negative integersToken accounting for the request.

Example composition for this Jev AI tools workflow

Sample state and question keys are illustrative compositions for this directory page — not a separate official product API. Primitives remain Choice / Score / Noul.

Dataset Payload: 12-week user retention metrics array with an unexpected 34% drop in week 11.
Choice
best_component: Optimal visual representation component
Options: [line_chart, data_table, anomaly_alert, summary_text]
Noul
highlight_anomaly: Does the dataset contain a significant outlier needing an anomaly badge?

Runnable call examples

Endpoint: https://api.typesafe.ai/v1/systemone (official). Requires your own TYPESAFE_API_KEY.

curl

curl -X POST https://api.typesafe.ai/v1/systemone \
  -H "Authorization: Bearer $TYPESAFE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"state":{"metrics":{}},"model":"jev-latest","questions":{"best_component":{"type":"choice","instructions":"Optimal visual representation","criteria":{"line_chart":"Chart","data_table":"Table","anomaly_alert":"Alert","summary_text":"Summary"}},"highlight_anomaly":{"type":"noul","instructions":"Significant outlier present?"}}}'

TypeScript

import { choice, noul, TypeSafeClient } from "@typesafe-ai/sdk";

const client = new TypeSafeClient();
const ui = await client.systemOne({
  state: { metrics },
  model: "jev-latest",
  questions: {
    best_component: choice("Optimal visual representation", {
      line_chart: "Time series chart",
      data_table: "Tabular view",
      anomaly_alert: "Alert banner",
      summary_text: "Short summary card",
    }),
    highlight_anomaly: noul("Significant outlier present?"),
  },
});

Python

from typesafe_sdk import Choice, Noul, TypeSafeClient

with TypeSafeClient() as client:
    ui = client.system_one(
        state={"metrics": metrics},
        model="jev-latest",
        questions={
            "best_component": Choice(
                instructions="Optimal visual representation",
                criteria={
                    "line_chart": "Time series chart",
                    "data_table": "Tabular view",
                    "anomaly_alert": "Alert banner",
                    "summary_text": "Short summary card",
                },
            ),
            "highlight_anomaly": Noul(instructions="Significant outlier present?"),
        },
    )

Latency & cost (source attribution)

Official end-to-end latency range: ~70–500ms; many calls land near ~100ms from US West Coast (source: typesafe.ai / TypeSafe public materials, 2026-09). Official list price: $0.042 / 1M input tokens; output tokens free (source: typesafe.ai, as of 2026-09). Card latency figures are illustrative compositions within that published range — not independent lab measurements by this directory.

  • Card illustration on this page: ~75ms (illustrative, within official range — not a lab run by jevaitools.com).
  • Official list price: $0.042 / 1M input tokens; output tokens free (source: typesafe.ai, as of 2026-09).

This directory has not published an independent measurement script for this page. To measure yourself: call the official endpoint with your key, record wall-clock p50/p95 andusage.input_tokens, and keep the date of the run.

Comparison with generative LLMs on the same decision task

TypeSafe publishes workflow evaluations where Jev is compared with frontier LLMs on accuracy, cost, and latency (company materials, 2026). Those multipliers are vendor-reported ceilings, not results measured by this directory. Run the same questions through an LLM structured-output adapter on your labeled set before choosing a stack.

Suitable for

  • Closed widget registries with stable keys
  • Client or BFF dispatch before render
  • Anomaly badges driven by Noul thresholds

Not suitable for

  • Generating novel UI layouts or CSS
  • Accessibility copywriting
  • Choosing among unbounded third-party embed URLs

Common failure modes

  • Registry keys drift from Choice criteria keys
  • Passing raw multi-MB payloads as state instead of summaries
  • Treating Noul 0.5 as “medium anomaly” instead of uncertainty

Other Jev AI Tools

This site is an independent third-party directory and is not affiliated with, endorsed by, or operated by TypeSafe AI.