Alpha MCPAPI reference · v1

The MCP your agents call.

Tritemporal memory that cannot lie about the past, a governed causal graph, knock-on simulation, and a decision ledger — the engine behind every Cascadian answer, at machine speed.

MCPPOSTGRESGOVERNED
Tools / Decisions

record_outcome()

Key

Writes the measured actuals. The expected-vs-actual comparison is computed server-side against the expectation that was frozen at recommendation time — so neither the agent nor the human can quietly move the goalposts after the fact.

record_outcome(decision_id, actuals, measured_at)EXPECTED VS ACTUAL

Callable over MCP as record_outcome(decision_id, actuals, measured_at). REST mirror POST /v1/outcomes Planned — alpha is MCP-only

Why your agent calls it

The loop closes. The agent writes what actually happened; the server computes expected-vs-actual against the frozen expectation. The discount cut came in at −$46k under the revenue estimate but inside the interval — and now that variance is data.

What it returns
FROZENexpected_outcomeMEASUREDrecord_outcomeVARIANCE−$46k · in intervalTHE EXPECTATION IS FROZEN BEFORE THE OUTCOME · NO RETCONS
record_outcome() · Measured actuals against the frozen expectation.ILLUSTRATIVE
Call it from an agent

Over MCP, your agent invokes it on its own when the moment calls for it — just describe the situation. A Python SDK for headless runtimes is planned; this is what the call will look like.

agent · python sdkSDK · PLANNED — ALPHA IS MCP-ONLY
from cascadian import Cascadian cx = Cascadian(api_key=os.environ["CASCADIAN_API_KEY"]) result = cx.record_outcome( decision_id="dec_0142", actuals={"win_rate_pp": -1.7, "gross_margin_pp": 3.1}, measured_at="2026-09-30", )
Parameters
ParamTypeDescription
decision_idREQUIREDstringThe decided decision to score.
actualsREQUIREDobjectThe measured outcome values.
measured_attimestampWhen the actuals were measured.
Example response
record_outcome()JSON · ILLUSTRATIVE
{ "decision_id": "dec_0142", "expected": { "win_rate_pp": -2.1, "gross_margin_pp": 3.4, "revenue_usd": 210000 }, "actual": { "win_rate_pp": -1.7, "gross_margin_pp": 3.1, "revenue_usd": 164000 }, "variance": { "revenue_usd": -46000, "within_interval": true }, "computed": "server-side, against the frozen expectation" }
Related — Decisions