AgentX overview

A simpler way to launch investing agents.

Building an investing agent from scratch with AI tools is complex: prompts, data, ranking, backtesting, validation, portfolio setup, and ongoing management all need to work together. AgentX packages that into a guided product: clients can choose an agent from the Store or create one through a controlled workflow.

Client journey
Pick or describeStart from a Store agent or write a strategy idea in plain language.
AgentX structures it ->
Review the agentSee objective, universe, risk, evidence, warnings, and expected behavior.
Launch with controls ->
Connect portfolioThe agent operates inside approved market, risk, and execution boundaries.
Monitor and improve ->
Managed lifecycleSignals, drift, risk, decisions, and health are tracked after launch.
Client View Technical Architecture

What AgentX Is

A client-facing explanation for investors, relationship managers, and product teams.

Plain English

AgentX turns investment ideas into managed agents.

Instead of asking a client or advisor to assemble their own AI stack, data pipeline, strategy logic, trading rules, and monitoring layer, AgentX provides a guided path from idea to launched agent. The client experience is simple: browse, choose, customize, review, launch, and monitor.

For clientsA simpler way to access personalized investing agents without building from scratch.
For client-facing teamsA repeatable story: Store for ready-made agents, Creator for new ideas, management loop after launch.
For the platformEvery agent is structured, validated, measured, and connected to the same operating system.

The Client Path

AgentX gives two entry points: select a proven strategy from the Store or create a new one through a guided mechanism.

01

Start

Choose a Store agent or describe a new investing idea in normal language.

02

Structure

AgentX turns the idea into objective, universe, risk, rebalance style, and rules.

03

Validate

The system checks whether the idea can be mapped to tradable instruments and reviewed evidence.

04

Launch

The selected or created agent becomes a managed portfolio workflow with clear controls.

05

Monitor

Clients and teams can track behavior, performance, risk, drift, and decision history.

Agent Store

The Store is the simple path for clients who want to start from curated agent templates instead of creating a strategy from zero.

Browse agents

Clients can compare agents by theme, goal, risk, asset class, rebalance cadence, and performance evidence.

Understand fit

Each Store agent should explain what it tries to do, what market universe it uses, and what risks or limits apply.

Launch faster

The client starts from a reviewed strategy object, not a blank AI prompt or a custom engineering project.

Creation Mechanism

Creator Studio is the guided path for new agents: it makes AI creation structured, reviewable, and operational.

What the client does

  • Describe the investing thesis, goal, market, risk level, and optional tickers.
  • Review the proposed universe, benchmark, holdings, and warnings.
  • Decide whether to save, test, publish, or launch the agent.

What AgentX handles

  • Turns the idea into a structured strategy contract instead of a loose prompt.
  • Maps themes and concepts to tradable instruments and data-backed rankings.
  • Carries validation, backtest evidence, risk settings, and lifecycle monitoring forward.

Why This Is Simpler

The message: AI can help build agents, but production-grade investing agents need more than a chat prompt.

Building alone means stitching together prompts, market data, rules, testing, execution, monitoring, and client reporting.
AgentX offers the packaged route: Store agents for speed, Creator for personalization, and an operating loop after launch.

What You Can Do With It

A practical client-facing summary of the product surface.

Personalize a portfolio

Turn a theme like dividend income, AI infrastructure, value, defense, macro, or quality growth into a governed agent.

Subscribe to strategies

Use the Store to launch agents built from approved strategy templates and tracked performance artifacts.

Explain every step

Client-facing people can show what the agent is trying to do, why it holds positions, and where the controls are.

Manage after launch

AgentX monitors signals, risk, drift, portfolio state, and health instead of stopping at creation.

Scale creator ideas

Successful ideas can become Store strategies so more clients can discover and launch them.

Keep a review trail

Strategy versions, validation reports, run logs, and decision records make agents easier to audit and improve.

Technical Architecture

The existing engineering overview remains below for teams that need the data, validation, and runtime details.

7QuantDB schemas surfaced through the data API
146tables and materialized views in the live schema explorer
2.8M+visible rows across live schema metadata
93foreign-key relationships from the schema endpoint

The Three Pillars

AgentX is built on three core systems that work together: a unified data operating system, semantic strategy creation, and managed agent lifecycle. Each is detailed in its own section below.

Data operating system

QuantDB centralizes market data, factors, signals, portfolio data, app state, and DCC taxonomy behind one API and one schema explorer.

Semantic strategy creation

User prompts become structured strategy intent, taxonomy concepts, risk profile, benchmark, and eToro-tradable ticker universes.

Managed agent lifecycle

Agents continue after launch: signal generation, regime detection, conviction checks, LLM context, drift monitoring, risk controls, and execution routing.

Interactive Architecture Diagrams

These four diagrams show how the three pillars fit together. Pan, zoom, and drag to explore.

Creator Workflow

The creator flow is designed to prevent vague prompts, unreviewed universes, unsafe requests, and untraceable backtests.

Prompt to Strategy Preview

Step-by-step request flow from creator prompt to QuantDB validation and back.

Step
Creator UI
AgentX API
LLM Layer
Semantic Layer
QuantDB / Gates
1. Submit
Goal, market, risk, optional tickers
/api/strategy-preview receives payload
2. Interpret
Builds intent prompt + guardrails
Returns strict JSON intent or rejection
3. Resolve
Calls universe resolver
Concepts, aliases, sectors, geo, factors, seed universe
Reads taxonomy and instrument data
4. Gate
Normalizes StrategySpec preview
Checks semantic match quality
eToro tradability, portfolio quality, fallback policy
5. Return
Preview, holdings, warnings, preview hash
Public-safe response
Bias/PIT status carried forward

QuantDB And Semantic Layers

AgentX reads from QuantDB directly for low-latency internal queries and through data.quantclaw.org for stable service contracts.

LayerPurposeImportant surfacesHow AgentX uses it
rawProvider landing zoneSource-specific raw snapshotsAuditability and provider lineage before normalization.
dataCanonical market datainstruments, price_history, factor_scores, consensus_snapshots, taxonomy_mappingRanking, semantic universe resolution, PIT-aware backtest inputs, profiles, and live data.
signalsSignal and derived analyticssignals, derived_indicators, external_signals, signal_backtests, feature snapshotsSignal history, model outputs, evaluation, and research feedback loops.
portfolioPortfolio analyticsholdings, trade_blotter, monthly_scores, backtestsModel portfolio analytics and performance reporting.
appApplication statevault_agent_portfolios, subscriptions, conversations, validation resultsAuth-linked portfolio state, user workflow state, and operational metadata.
agentxAgentX app schema in QuantDBstrategies, strategy_creators, strategy_versions, subscriptions, run logs, target weightsReviewed from AgentX migrations and code: Creator Store, StrategySpec persistence, validation history, and target portfolio snapshots.
Guardrail: backtest claims must remain explicit about point-in-time status. Store cache runs currently mark bias status as unknown or unverified unless the run proves PIT inputs, dataset versions, validation gates, transaction costs, and structured run logs.

Data Lineage: Provider Data → Agent Decision

Strategy Store Apparatus

The Store is both a product surface and a contract boundary between creator workflows, validation, performance evidence, and subscriptions.

Marketplace state

  • agentx.strategies stores published and system strategies.
  • agentx.strategy_creators joins creator identity and display metadata.
  • agentx.strategy_versions preserves published snapshots for review and rollback.
  • agentx.strategy_subscriptions connects Store strategies to launched user agents.
  • Rows carry status, subscriber count, validation score, validation report, factor config, and backtest result payloads.
  • AgentX maps DB rows back into UI-compatible strategy templates.

Backtest cache and honesty layer

  • Daily cache refresh runs engine results into runtime/backtest-cache/store.
  • Each run writes a structured log under strategies/run_logs.
  • latest-good.json protects the Store UI from failed refreshes.
  • The API exposes freshness, cache status, bias status, coverage, and failure metadata.

Schema / Domain Relationships

Managed Agent Lifecycle

After creation, AgentX manages agents in repeated cycles. The loop is designed to degrade gracefully when data is missing and to separate paper, shadow, and live execution modes.

Swimlane: Creator Publish & Store Lifecycle

1. Market filter

Batch route loads active agents, filters archived/test/guest shells, checks market hours, and narrows each universe to open-market tickers.

2. Regime layer

Regime detector produces growth, reflation, slowdown, or stress context with cash target, size multiplier, threshold adjustment, and factor overrides.

3. Signal layer

Signal generator, conviction buffer, portfolio manager, and risk manager produce buy/sell/wait decisions with bounded failure isolation.

4. LLM layer

LLM context activates only for anomalies, rule conflicts, earnings, macro events, or corporate actions. It can confirm, pause, adjust score, flag human, or no-op.

5. Drift layer

Drift monitor compares live/eToro reconciled positions to target weights and proposes trims, fills, or missing-position buys.

6. Execution layer

Execution bridge supports paper, shadow, and live modes, with live requiring authenticated agent-portfolio state and safety approvals.

7. Monitor layer

Startup instrumentation validates schema, starts the portfolio poller, and drains DB/Redis cleanly on shutdown. Order monitoring uses private-feed events with HTTP fallback.

8. Run ledger

Each batch stores run status, signals, trades, live fills, errors, and human-readable decision summaries for admin review.

Runtime Management Loop

Operational Visibility

The platform has multiple health surfaces so product and engineering can separate data staleness, app health, execution health, and strategy behavior.

Agent health

/api/agent/health checks QuantDB Platinum data, regime state, schema health, portfolio risk state, and per-agent conviction backlog.

Admin dashboard

/api/admin/dashboard aggregates Store cache freshness, live portfolio monitor events, active PM status, data health, and pipeline alerts.

Pipeline health

/api/v1/pipeline/health checks staleness across price history, derived indicators, factors, GuruFocus rankings, PIT fundamentals, revisions, consensus, and daily signals.

Code Map

Primary files and endpoints reviewed for this overview. These are the best entry points for R&D, product, and technology teams.

AreaFiles / endpointsRole
Data APIquantdb-api/src/index.ts
/schema, /architecture, /docs, /v2/smart-portfolio/*
Unified data gateway, API docs, schema explorer, and public-safe technical pages.
Schema explorerquantdb-api/src/routes/schema.tsRead-only introspection of schemas, columns, row counts, sizes, indexes, and relationships.
Semantic universeagentx-current/src/lib/semantic-universe.ts
agentx-current/src/lib/strategy-universe-resolver.ts
Prompt-to-taxonomy matching, alias seeds, QuantDB taxonomy lookup, and eToro instrument validation.
LLM intentagentx-current/src/lib/strategy-intent-interpreter.tsProvider-backed classification, safe rejection reasons, normalized objective, factors, geography, and risk.
Strategy contractagentx-current/src/lib/strategy-spec.ts
agentx-current/schemas/strategy-spec/*
Canonical type system used by builder, rank API, backtest, DB persistence, and validation.
Creator APIs/api/strategy-preview
/api/creator/rank
/api/backtest
Preview contract, QuantDB rank proxy, and backtest invocation with structured run logging.
Store APIs/api/store/strategies
/api/store/backtests
agentx-current/src/lib/strategy-store.ts
Marketplace listing, strategy CRUD, Store cache, validation reports, creator attribution, and subscribers.
Agent loopagentx-current/src/lib/agent-loop.ts
/api/agents/loop/batch
Batch orchestration for regime, signals, LLM context, risk, drift, execution, and ledgers.
Ongoing managementagentx-current/src/instrumentation.ts
agentx-current/src/lib/portfolio-poller.ts
agentx-current/src/lib/order-monitor.ts
agentx-current/src/lib/drift-monitor.ts
agentx-current/src/lib/etoro-execution-bridge.ts
Startup checks, portfolio polling, order lifecycle monitoring, drift detection, eToro reconciliation, paper/shadow/live phases, and go-live controls.

Demo Talk Track

Use this sequence to explain the depth of the platform to R&D, technology, and product teams.

Product lens

AgentX lets a user describe an investing thesis, turns it into a structured agent, shows evidence, and makes it subscribable in the Store.

Technology lens

The system has strict contracts: StrategySpec, preview hash, QuantDB APIs, schema introspection, PIT semantics, cache status, and run logs.

R&D lens

The agent loop combines quantitative scores, market regime, conviction thresholds, LLM anomaly checks, drift monitoring, and execution modes.

Reviewed Sources

This page is based on local code and live read-only service metadata, not hand-waved architecture.

/home/quantdev/apps/quantdb-api
/home/quantdev/apps/agentx-current
/home/quantdev/apps/agentx
/home/quantdev/apps/price-feed
data.quantclaw.org /api/v1/schema
AgentX docs/backtest-store-cache.md
AgentX docs/data-contracts/PIT_SEMANTICS.md
AgentX docs/ACTIVE_PM_RUNBOOK.md
PM2 service map: quantdb-api, agentx, agentx-staging