Olympus
BriefPortfolioPipeline
System

System

How Olympus works

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

How it works

Each run, Atlas researches the market across parallel phases — alternative data, institutional flows, macro, asset classes, and sectors — and synthesizes a daily read. Hermes then deliberates: it frames theses, screens candidates, runs per-ticker analysts and PM⇄analyst debates, and sizes risk. 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_diagnosticsCost, tokens, grounding, per-phase outcomes (this page)
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