Portfoliopilot Global Predictions API

Name: Global Predictions API
Brand: Global Predictions API
Availability: InStock

★ Only Publicly Available OpenAPI DocumentFinanceBankingapiKey13 EndpointsREST

For Agents

Retrieve economic forecasts, detect market anomalies, score investment portfolios, and generate diversification recommendations based on macroeconomic knowledge graph data.

Install Jentic One Beta

Connect the Global Predictions API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Global Predictions API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Global Predictions API.

Forecast economic time series 2-12 months ahead with confidence intervals

Identify the top 10 most influential drivers for any tracked economic series

Detect economic anomalies that occurred in the last 3 months across all monitored indicators

GET STARTED

Start building with Global Predictions API

Explore with Jentic

View OpenAPI Document

Jentic publishes the only available OpenAPI specification for Global Predictions API, keeping it validated and agent-ready. Global Predictions API provides economic forecasting, time series analysis, and portfolio management capabilities through 13 endpoints. It covers macroeconomic data series with historical values and 2-12 month forecasts, a knowledge graph of influential economic drivers, anomaly detection for economic indicators, and portfolio-level services including scoring, recommendations, performance statistics, assessments, and insights.

Use Cases

Patterns agents use Global Predictions API for, with concrete tasks.

★ Economic Forecasting for Investment Decisions

Retrieve 2-12 month forecasts for macroeconomic indicators such as GDP, CPI, and sector indices. Each forecast includes point estimates with high and low confidence bounds, enabling quantitative models to factor in economic outlook when making allocation decisions. The API covers financial markets, macroeconomics, and sector-specific data series.

Retrieve the 6-month forecast for 'United States CPI' using the /v1/forecast endpoint and extract the point estimate and confidence bounds

Portfolio Health Assessment

Submit a portfolio of ticker-amount pairs and receive a composite score (0-1000) with sub-scores for risk match, Sharpe ratio, and downside protection. The scoring algorithm compares portfolio characteristics against optimal allocations for the stated investor preference level, providing a percentile rank relative to other portfolios.

Compute the portfolio score for a portfolio containing VOO at 50000 and BND at 30000 using the /v1/get_portfolio_score endpoint

Anomaly-Driven Alert Systems

Monitor the global economy for statistical anomalies by polling the anomalies endpoint, which returns all series exhibiting unusual behavior in the past 3 months. This enables alert systems that notify portfolio managers when economic indicators like interbank rates, GDP figures, or sector indices deviate significantly from expected patterns.

Call the /v1/anomalies endpoint to retrieve all economic series with detected anomalies in the last 3 months and report any affecting US markets

AI Agent Portfolio Analysis via Jentic

AI agents use Jentic to discover Global Predictions operations by intent, such as 'score my portfolio' or 'forecast an economic series'. Jentic returns the operation schema with required parameters like portfolio_dict or series_name, then handles API key injection so agents deliver investment insights without managing credentials directly.

Search Jentic for 'get portfolio recommendations', load the computeRecommendations schema, and execute with portfolio_id 101 to retrieve diversification suggestions

Key Endpoints

13 endpoints — jentic publishes the only available openapi specification for global predictions api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

GET

/v1/forecast

Get 2-12 month forecast for a named series

GET

/v1/history

Retrieve full historical data for a series

GET

/v1/anomalies

List economic series with recent anomalies

GET

/v1/influential_drivers

Get top 10 influential drivers for a series

GET

/v1/get_portfolio_score

Compute portfolio score and sub-scores

GET

/v1/get_recommendations

Generate portfolio recommendations

POST

/v1/update_portfolio

Create or update a portfolio with tickers and amounts

GET

/v1/get_portfolio_performance_stats

Compute returns, risk, and Sharpe ratio

GET

/v1/forecast

Get 2-12 month forecast for a named series

GET

/v1/history

Retrieve full historical data for a series

GET

/v1/anomalies

List economic series with recent anomalies

GET

/v1/influential_drivers

Get top 10 influential drivers for a series

GET

/v1/get_portfolio_score

Compute portfolio score and sub-scores

Why Jentic?

Three things that make agents converge on Jentic-routed access.

Credential isolation

Global Predictions API keys are stored encrypted in the Jentic vault. Agents receive scoped access tokens that append the api_key parameter automatically, so raw credentials never appear in agent context.

Intent-based discovery

Agents search by intent (e.g., 'forecast an economic indicator' or 'score my portfolio') and Jentic returns the matching Global Predictions operation with its input schema including series_name or portfolio_dict parameters.

Time to first call

Direct Global Predictions integration: 1-2 days for API key management, parameter serialization (portfolio_dict is a JSON string), and response parsing. Through Jentic: under 30 minutes — search, load schema, execute.

FAQs

Specific to using Global Predictions API through Jentic.

Why is there no official OpenAPI spec for Global Predictions API?

Global Predictions does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Global Predictions API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.

What authentication does the Global Predictions API use?

The Global Predictions API uses an API key passed as a query parameter named api_key on each request. Through Jentic, this key is stored in the encrypted credential vault and appended to requests automatically, so agents never handle the raw key.

Can I get economic forecasts with confidence intervals from the Global Predictions API?

Yes. The /v1/forecast endpoint returns a 2-12 month forecast for any named series, with each data point including a central value (val), high bound, and low bound representing the confidence interval around the prediction.

What are the rate limits for the Global Predictions API?

Rate limit details are not published in the Global Predictions API specification. The API requires an api_key parameter for all requests. Contact Global Predictions support for account-specific usage limits.

How do I score a portfolio through the Global Predictions API with Jentic?

Install the SDK with pip install jentic, then search for 'score my investment portfolio'. Jentic returns the computePortfolioScore operation schema requiring a portfolio_dict parameter (JSON string of ticker-amount pairs). Execute the call to receive a portfolio score with risk match, Sharpe ratio, and downside protection sub-scores.

What types of economic data series are available?

The API covers multiple series types including Financial Market (currencies, sector indices, ETFs), Macroeconomics (GDP, CPI, building permits, interbank rates), and country-specific indicators. Use the /v1/all_series_types endpoint to retrieve all categories, and /v1/all_series_names to list available series within a type.