FutureSearch Logofuturesearch
  • Pricing
  • Research
  • Docs
  • Evals
  • Markets
  • Blog
  • Company
  • Try it for free
FutureSearch Logo

General inquiry? You can reach us at hello@futuresearch.ai.

Company

TeamCareersPressPrivacy PolicyTerms of Service

Developers

SDK DocsAPI ReferenceCase StudiesGitHubSupport

Integrations

Claude CodeCursorChatGPT CodexClaude.ai

Track Record

Trading ResultsAccuracy EvalsTournament Standings

Follow Us

X (Twitter)@dschwarz26LinkedIn
FutureSearchdocs
Frontier forecasting
Installation
  • All install methods
  • Claude.ai
  • Claude Code
  • Web App
  • Python SDK
  • Skill
Reference
  • API Key
  • forecast
  • decision
  • multi_agent
  • agent_map
  • World Modeling
  • Published Forecasts
  • MCP Server
  • Progress Monitoring
Guides
  • Turn Claude into an Accurate Forecaster
  • Forecast Outcomes for a List of Entities
  • Forecast Conditional Scenarios
  • Forecast Categorical and Threshold Questions
  • Find Profitable Prediction Market Trades
  • Research a Question with a Team of Agents
  • Add a Column via Web Research
  • Error Handling in FutureSearch: Failed Rows and Partial Results
Case Studies
  • Forecast a Decision: Grant Funding at Three Levels
  • Forecast a Decision: Which CEO Replacement Maximizes Share Price
  • Forecast a Binary Question End to End
  • Forecast a Date, Then Grade It
  • Forecast Categorical Outcomes for Two Stealth Labs
  • Forecast Conditional Scenarios for OpenAI's IPO
  • Forecast Anthropic and OpenAI IPOs: Dates and Valuations
  • Forecast a Sum-of-the-Parts SpaceX IPO Valuation
  • Forecast Founder Seed Valuations for AI Researchers
  • Find Startups Selling to Frontier AI Labs
  • Run 10,000 LLM Web Research Agents
FutureSearchby futuresearch
by futuresearch

Forecast a Binary Question End to End

Binary mode returns a calibrated probability from 0 to 100 that a yes/no question resolves YES, plus a rationale with citations. One question, one row, one call.

The question

FieldValue
QuestionWill AWS, Azure, Google Cloud, or Oracle announce a deployment of Intel's Crescent Island GPU by December 31, 2027?
Outcome typebinary
ResolvesA public announcement from any of the four clouds naming a Crescent Island deployment, on or before December 31, 2027

Crescent Island is Intel's inference GPU built on LPDDR5X rather than HBM.

Run it

import asyncio

from pandas import DataFrame
from futuresearch.ops import forecast


async def main():
    result = await forecast(
        input=DataFrame([
            {
                "question": (
                    "Will AWS, Azure, Google Cloud, or Oracle announce a deployment "
                    "of Intel's Crescent Island GPU by December 31, 2027?"
                ),
                "resolution_criteria": (
                    "Resolves YES on a public announcement from any of AWS, Azure, "
                    "Google Cloud, or Oracle naming a Crescent Island deployment, on "
                    "or before December 31, 2027."
                ),
                "background": (
                    "Crescent Island is Intel's LPDDR5X-based inference GPU. Intel's "
                    "two prior Gaudi generations won no top-four cloud deployments."
                ),
            },
        ]),
        forecast_type="binary",
        effort_level="HIGH",
    )
    print(result.data[["question", "probability", "rationale"]])


asyncio.run(main())

probability is clamped to the range 3 to 97, so near-certain outcomes keep some residual uncertainty.

Results

QuestionProbability
A top-four cloud announces a Crescent Island deployment by December 31, 202713%

The anchor in the rationale is the base rate: zero top-four wins across two Gaudi generations.

What would move the number up:

  • Oracle building a budget inference tier on a non-Nvidia accelerator, which it has done for price-sensitive workloads before
  • A deep co-engineering partnership announced at re:Invent or the OCP Summit, bypassing the slow validation pipeline
  • Independent testing showing unprecedented cost-per-token efficiency
  • Intel disclosing strong, independently verified inference economics in late 2026
  • Any named cloud co-engineering commitment

Going deeper

  • Long-form analysis: Intel Crescent Island: Why No Major Cloud Will Deploy It by 2027
  • Published output: the full forecast and its sources
  • Guide: Turn Claude into an accurate forecaster

Ready to try it yourself? Run it in the app →