Agentic Trader Docs

Agent Pipeline

How context becomes specialist analysis, manager output, and guarded execution without hidden leaps.

Why the pipeline matters

The repo is not asking a single chat prompt to improvise a trade. It is assembling typed context, routing it through specialist stages, and applying a deterministic guard before anything reaches execution.

High-level flow

  1. Market and provider context is assembled.
  2. Specialist agents interpret their slice of the problem.
  3. A manager synthesizes the specialist outputs.
  4. Guard logic decides whether action is allowed.
  5. Execution intent and outcome are persisted as explicit records.

Inputs the pipeline should prefer

  • canonical provider snapshots
  • typed feature bundles
  • freshness and source attribution
  • missing-data visibility
  • runtime mode and operator intent

Inputs the pipeline should avoid pretending to have

  • fabricated fundamental confidence
  • hidden provider truth when a provider is missing
  • unstated fallbacks that change semantics
  • web-only local state not reflected in runtime contracts

Fallback rule

Fallbacks are sometimes necessary, but they must be honest.

That means:

  • explicit reasons when provider evidence is missing
  • different behavior between permissive training paths and strict operational paths
  • zero or degraded confidence when supporting evidence is absent
  • no silent substitution that looks like primary truth

Where to debug pipeline issues

When a result feels suspicious, inspect:

  • normalized provider snapshots
  • decision feature bundles
  • specialist outputs
  • manager summaries
  • guard decisions
  • persisted review or trace artifacts

The right fix is usually found there before touching prompts blindly.

Docs rule for this area

If the pipeline contract changes, update:

  • architecture docs
  • data and intelligence docs
  • runtime docs if operator-visible behavior changed
  • .ai/current-state.md
  • .ai/decisions.md
How was this page?
This GitHub Pages build prepares a browser-local feedback draft and a prefilled GitHub issue. Node-hosted local docs can still wire feedback into runtime logs later.

Stores a draft in this browser and gives you a GitHub issue link to submit when ready.

On this page