Pat MulleeAI Product & Platform Leadership
Skip to primary interaction
Finance

Economic Indicators & Evidence Briefs

Interactive simulation · Fictional data · Runs in your browser

Explore prewritten economic briefs, inspect fictional observations, and distinguish cited statements from inference.

  • Inspect the evidence linked to sample statements
  • Distinguish cited statements from labelled inference
  • Explore a review pattern without treating citation coverage as accuracy
Inspect a cited macro briefCheck grounding

CPI, all urban consumers

  • Reached 315.6 in Jan 2025 CPIAUCSL 2025-01
  • Index rose from 310.4 to 315.6 in the sample CPIAUCSL 2024-08

Primary interaction

Interactive simulation · Fictional observations and prewritten briefs. No live economic data or AI generation. Citation coverage measures linked bullets, not factual accuracy.

How the cited brief is structured

Operating model

From a series to a cited brief

Explore prewritten briefs linked to fictional observations. Uncited conclusions are labelled as inference; citations still require review.

01

Select

Pick a macro series to brief.

02

Generate

Draft structured investor bullets.

03

Cite

Bind each bullet to an observation.

04

Check

Inspect citations and labelled inference.

CPI, all urban consumers315.6▲ 5.2 since 2024-08

Synthetic observations

  • 2025-01315.6latest in sample
  • 2024-12314.2
  • 2024-11313.1
  • 2024-10312
  • 2024-09311.2
  • 2024-08310.4
  • Headline CPI reached 315.6 in January 2025, up from 314.2 the prior month.
  • The sample index rose from 310.4 in August 2024 to 315.6 in January 2025, an increase of 5.2 index points. The monthly increase rose from 0.8 points in September to 1.4 points in January.
  • These six sample observations do not establish year-over-year inflation or support a forecast of future policy decisions.inference, not grounded
67%citation coverage6 of 9 bullets cite a source
6citations issuedacross 3 series
3flagged inferencesshown as inference, not fact

Cited sources

  • CPIAUCSL 2025-01 · CPI, all urban consumers
  • CPIAUCSL 2024-08 · CPI, all urban consumers
  • FEDFUNDS 2025-01 · Effective federal funds rate
  • FEDFUNDS 2024-08 · Effective federal funds rate
  • T10Y2Y 2025-01 · 10-year minus 2-year Treasury spread
  • T10Y2Y 2024-11 · 10-year minus 2-year Treasury spread

Citation coverage counts bullets with a source link. It does not verify whether the source supports the statement. Uncited bullets are labelled as inference.

Observations stay observable; inference stays labelled.

67%citation coverage
3macro series
6cited bullets
Under the hood

Capability proof

Capability proof

Cited macro briefing

Service model

An analyst-facing brief generator over macro series.

Intelligence layer

Turns a series into structured bullets, each bound to an observation.

Operational state

Holds the series, observations, generated brief, and citations together.

Human control

Analysts open every citation and see inferred bullets flagged before using them.

Business value

Cuts time to a trustworthy macro read while keeping every claim traceable.

Architecture

The studio runs client-side over a precomputed synthetic dataset. In a real deployment, observations would come from a FRED client, the model would draft bullets constrained to cite retrieved values, and an offline eval would score grounding before any change shipped. Here the structure is the point: every grounded bullet binds to a dated observation, and inferred conclusions are marked rather than blended in.

What this demo is, and isn't

  • The series and observations are fictional and labeled synthetic. No real FRED data is used.
  • Briefs are precomputed for the demo, not generated live, so the focus is the citation pattern.
  • Grounding and the inference flag are illustrative of the eval surface a regulated deployment would need.