Sustainable Finance Partners, LLC

Phronesis.
Practical wisdom for the energy transition.

A verified-correctness forecasting substrate. API-forward by design. Agents are first-class customers; humans are welcome too.

Phronesis is the flagship platform of Sustainable Finance Partners, LLC — a Colorado limited liability company operating from Denver.

For Agents

Start at /spec

Markdown-first contract docs. OpenAPI 3.1. MCP server endpoint. Idempotency-key required. Sub-cent meter-event precision. AP2 mandate compatible.

Open the contract surface For Humans

Keep scrolling

Five forecasting verticals operating on production today. Cost-attestation per forecast in dollars and cents. Calibration scorecard public from day one.

See the substrate
What is Phronesis

A forecasting platform that capital allocators can audit and agents can call directly.

Phronesis mints probabilistic forecasts across eight verticals — energy, computing, healthcare, climate physical risk, regulatory, supply-chain, space, and robotics. Every forecast is primary-source-cited, time-stamped, persisted to a canonical ledger, and rendered publicly on a calibration scorecard from the moment it issues. Humans get a methodologically defensible forecasting service. Agents get a contract surface designed for them, not retrofitted to them.

Production state

Five verticals operating on production today

Every forecast is timestamped, primary-source-cited, persisted to the canonical Mnemosyne ledger, and rendered publicly on the calibration scorecard at issue.

Verticals live
5 of 8
V#1 Energy, V#2 Computing + AI Infrastructure, V#3 Healthcare, V#7 Space, V#8 Robotics — all minting forecasts on production at substrate-OPERATIONAL-VALIDATION depth.
Cost per forecast
$0.0084 – $0.0151
Real Anthropic Haiku-4-5 inference cost per minted forecast, attested per call. Vertical-specific template depth drives the curve.
API uptime
24/7
Hermes contract surface running continuously on dedicated production runtime. MCP and REST co-equal at every endpoint.
Vertical axis

Eight verticals. One substrate.

Phronesis is an AI-native forecasting substrate instantiated for energy-transition first. Roughly seventy percent of the architecture is vertical-agnostic; the per-vertical layer specializes the prompt library and the data plane.

  • V#1Energy TransitionLive
  • V#2Computing + AI InfrastructureLive
  • V#3Healthcare (HIPAA Safe Harbor)Live
  • V#4Climate Physical RiskPre-launch
  • V#5RegulatoryPre-launch
  • V#6Supply-ChainPre-launch
  • V#7Space + Space EconomyLive
  • V#8RoboticsLive
How it works

Verified correctness is a substrate property.

Four architectural commitments, enforced at the code layer.

01 Primary-source citation always

Every forecast traces to a primary source: FERC filings, EDGAR, USPTO, state PUC dockets, DOE grant awards, peer-reviewed research. No second-hand citations of secondary citations.

02 Timestamp discipline

Every forecast carries an issue date and an evaluation window. The forecast ledger is the canonical record of what was known when. Calibration accrues publicly over time.

03 API and MCP co-equal

Every endpoint that exists for human-driven REST clients exists at parity for autonomous-agent MCP clients. Idempotency keys are required, not optional. Errors are structured and machine-recoverable.

04 Agentic-commerce native

Stripe Agentic Commerce Suite integration: Shared Payment Tokens, AP2 mandate verification at the contract surface, sub-cent meter-event precision. Three-layer trust stack from authorization to settlement.

Engage

Forecasts you can audit.
Decisions you can defend.

If you are an agent acting on behalf of a capital allocator, start at the contract surface. If you are a human, the calibration scorecard is the most useful place to begin.

View API spec Open calibration scorecard