Financial News Sentiment Breaker
Noul circuit-breaker + Choice impact-scope pattern for market news headlines.
Architecture overview
Monitors wire headlines to produce a halt/continue signal and impact breadth classification. Designed for risk gates — not trade advice.
Generative LLMs can take seconds, missing short risk windows.
Typed answers support deterministic halt logic; latency claims should cite TypeSafe’s published 70–500ms range, not fabricated site timings.
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.
| Field | Type | Range | Notes |
|---|---|---|---|
| state | string | object | array | Plain text or structured JSON | Content to evaluate. Shared across all questions in one request. |
| model | string | e.g. "jev-latest" | Optional; defaults to TypeSafe flagship alias when omitted in SDKs. |
| questions.<id>.type | "choice" | "score" | "noul" | Exactly one of three primitives | Question ID is chosen by you; answers return under the same keys. |
| questions.<id>.instructions | string | Natural-language judgment | The actual question sent for inference (IDs are not sent to the model). |
| questions.<id>.criteria (choice) | Record<option, string | null> | 1–255 options | Map of option key → rubric description. |
| questions.<id>.criteria (score) | string[] | ≥ 2 ordered levels | Ordered level descriptions; score is a weighted position along them. |
| questions.<id>.criteria (noul) | { true?: string; false?: string } | Optional | Optional 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 levels | legend 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 integers | Token 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.
Headline: "Reuters: Major semiconductor manufacturer CEO resigns following formal accounting probe."
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":{"headline":"HEADLINE"},"model":"jev-latest","questions":{"circuit_break":{"type":"noul","instructions":"Halt positions immediately?"},"impact":{"type":"choice","instructions":"Market impact breadth","criteria":{"single_ticker":"Single","industry_sector":"Sector","systemic_macro":"Macro","noise":"Noise"}}}}'TypeScript
import { choice, noul, TypeSafeClient } from "@typesafe-ai/sdk";
const client = new TypeSafeClient();
const newsRisk = await client.systemOne({
state: { headline: wireHeadline },
model: "jev-latest",
questions: {
circuit_break: noul("Halt positions immediately?"),
impact: choice("Market impact breadth", {
single_ticker: "Single name only",
industry_sector: "Entire industry sector",
systemic_macro: "Systemic macro risk",
noise: "Noise / irrelevant",
}),
},
});Python
from typesafe_sdk import Choice, Noul, TypeSafeClient
with TypeSafeClient() as client:
news_risk = client.system_one(
state={"headline": wire_headline},
model="jev-latest",
questions={
"circuit_break": Noul(instructions="Halt positions immediately?"),
"impact": Choice(
instructions="Market impact breadth",
criteria={
"single_ticker": "Single name only",
"industry_sector": "Entire industry sector",
"systemic_macro": "Systemic macro risk",
"noise": "Noise / irrelevant",
},
),
},
)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: ~74ms (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
- Pre-trade risk gates with human override
- Headline triage into analyst queues
- Noise filtering before expensive research agents
Not suitable for
- Automated trade execution without compliance controls
- Price forecasting or portfolio construction
- Interpreting charts or filings as state without extraction
Common failure modes
- Headline-only state missing body / ticker mapping
- Overfitting thresholds on a few dramatic examples
- Confusing vendor latency claims with exchange co-location reality
Other Jev AI Tools
This site is an independent third-party directory and is not affiliated with, endorsed by, or operated by TypeSafe AI.