BriefPortfolioPipelineFX Hub
System

System

How Olympus works

Is it running, is it healthy, what does it cost, and how does it work?

How it works

  1. 01

    Atlas

    Research the market

    Each run fans out across parallel phases — alternative data, institutional flows, macro, asset classes, and sectors — and synthesizes a daily read.

  2. 02

    Hermes

    Deliberate the book

    Hermes frames theses, screens candidates, runs per-ticker analysts and PM⇄analyst debates, and sizes risk.

  3. 03

    Portfolio

    Book the decisions

    The result is a booked portfolio with a signed decision behind every position.

See the full graph

What a run persists

Every run is durable — these are the tables it writes, the source of truth the dashboard reads.

WhatWhereNotes
Research segmentsdocumentsOne row per segment (alt-data, macro, sectors, asset classes)
Daily digestdocuments + daily_snapshotsThe read — headline, regime bias, digest markdown
Analyst & deliberation notesdocumentsPer-ticker analyst verdicts and PM⇄analyst debates
Portfolio decisionspositions + decision_logThe booked book and each signed call with its thesis
Run diagnosticsatlas_run_healthRun status, segment counts, timing (public view; cost/tokens operator-only)
Operator controls— for self-hosters running the pipeline

Runs are invoked from the command line. Model routing is automatic — chat phases use the configured reasoning model, web-search phases route to a grounding model.

  • --baselineFull pipeline — every research phase regenerated from scratch
  • --deltaLightweight refresh — only changed segments re-run (~20–30% of baseline cost)
  • --monthlyMonth-end synthesis across the period’s baselines and deltas