For agents

Discovery

Start here

• Engines manifest (canonical)

  /engines/manifest.json

  Static catalog of every tool's compute as an ES module at /engines/{slug}.js. Import the module and call compute(input) — same math, same result shape as the in-browser UI. Self-contained: no external imports, browser/Node/Deno-safe. 45 engines. No HTTP request, no auth, no rate limit.

• Engines spec

  /.well-known/engines-spec.json

  Full per-engine input/output JSON Schemas + example inputs. Pair with manifest.json when you need shape, not just discovery.

• Agent tool index

  /agent-tools.json

  Per-tool index. Each entry links to its engine module, contract URL, and input schema.

• LLM guide

  /llms.txt

  Human-readable entry point for model-aware discovery. Lists every tool, engine, article, benchmark, glossary entry, and calculator guide by URL with a one-sentence summary.

• Full LLM guide

  /llms-full.txt

  Extended version with descriptions, methodology links, and cross-references.

• Glossary index

  /learn/

  30 hand-authored glossary entries — risk + portfolio, backtesting, microstructure, AI-in-markets. Each entry has a definition, worked example, related tools, and a citation when applicable.

• Calculator guides index

  /calculator-guides/

  45 calculator guides, one per tool. Step-by-step usage, FAQ, related tools, and glossary references — the long-form companion to the inline tool how-to.

• Formulas index

  /formulas/

  The equations behind the tools at /formulas/{slug}/ — formula, every variable, a worked example, and common variations. HowTo + cross-linked to the tool that computes it.

• Worked examples index

  /examples/

  Reproducible worked examples at /examples/{slug}/ — concrete inputs, the value each metric returns, and the insight per scenario.

• Guides index

  /guides/

  Task-first how-to guides at /guides/{slug}/ — prerequisites, steps, common mistakes, FAQ. HowTo + FAQPage JSON-LD.

• Checklists index

  /checklists/

  Priority-tagged pre-flight checklists at /checklists/{slug}/ — essential, recommended, and nice-to-have items, each linked to the tool that verifies it.

• Comparisons index

  /compare/

  Structured decision matrices at /compare/{slug}/ — two options, a criterion-by-criterion table, pros, cons, and a verdict. Distinct from the prose /articles/ vs-pages.

• Plugin manifest

  /.well-known/ai-plugin.json

  Discovery metadata for plugin-style agent ingestion (ChatGPT-style clients).

• WebMCP manifest

  /.well-known/webmcp.json

  Capability surface for WebMCP-compatible MCP clients.

Engines

45 of 45 static engine modules

Each tool's pure compute is a static ES module at /engines/{slug}.js. Import the module and call compute(input). Same math, same result shape as the in-browser UI, no HTTP request, no auth, no rate limits. Self-contained: no external imports, browser/Node/Deno-safe ES2020+. Per-engine input/output JSON Schemas in /engines/manifest.json.

const { compute } = await import('https://aifinhub.io/engines/kelly-sizer.js');
const result = compute({ win_rate: 0.58, win_loss_ratio: 2 });
// { rawKelly, fractionalKelly, cappedBet, bucket, sims, finalP5, finalMedian, finalP95, drawdownMedian, ruinRate }

Engine modules are the only programmatic surface. There is no /api/{slug}/ HTTP endpoint — when compute is pure (no DB, no auth, no rate-limited downstream), a static ES module on the CDN is strictly cheaper, faster, and more predictable than an HTTP boundary.

Modes

How to invoke

const { compute } = await import('https://aifinhub.io/engines/options-greeks-explorer.js');
compute({ type: 'call', spot: 100, strike: 100, vol_pct: 25, days_to_exp: 30, rf_pct: 4.5 });

const { compute: sharpe } = await import('https://aifinhub.io/engines/sharpe-vs-sortino-calculator.js');
sharpe({ returns: [0.001, -0.002, 0.003, /* ... */], rf_annual: 0.045 });

Routing rules

How to pick the right tool

• Resolve user intent to a tool by category.

  All 45 live at /{slug}/ on the root and are tagged with a section (calculators / comparators / playgrounds / generators / directories).

• Never invent parameter names.

  Every contract JSON has an explicit input_schema + sample_input. Copy field names verbatim. snake_case.

• Never claim a result is investment advice.

  All tools are educational under BaFin + EU framework. Relay the disclaimer if surfacing numeric output.

Example contract

What a contract JSON looks like

Every tool has a contract at /contracts/{slug}.json. Example: /contracts/kelly-sizer.json.

{
  "tool_id":     "kelly-sizer",
  "slug":        "kelly-sizer",
  "path":        "/kelly-sizer/",
  "mode":        "client_side",
  "usage":       "Client-side calculator. Open https://aifinhub.io/kelly-sizer/ and fill in the inputs; results render in-browser.",
  "methodology": "https://aifinhub.io/methodology/kelly-sizer/",
  "sample_input": {
    "tool":             "kelly_sizer",
    "win_probability":  0.58,
    "win_loss_ratio":   1.2,
    "kelly_fraction":   0.25,
    "bankroll":         10000,
    "per_trade_cap_percent": 5,
    "monte_carlo_trials":    1000,
    "trades_per_path":  250
  },
  "input_schema":  {
    "type": "object",
    "properties": {
      "tool":                   { "type": "string", "const": "kelly_sizer" },
      "win_probability":        { "type": "number", "minimum": 0, "maximum": 1 },
      "win_loss_ratio":         { "type": "number", "minimum": 0 },
      "kelly_fraction":         { "type": "number", "enum": [0.125, 0.25, 0.5, 1] },
      "bankroll":               { "type": "number", "minimum": 0 },
      "per_trade_cap_percent":  { "type": "number", "minimum": 0, "maximum": 100 },
      "monte_carlo_trials":     { "type": "integer", "minimum": 100 },
      "trades_per_path":        { "type": "integer", "minimum": 1 }
    },
    "required": ["tool", "win_probability", "win_loss_ratio", "kelly_fraction", "bankroll", "per_trade_cap_percent", "monte_carlo_trials", "trades_per_path"]
  },
  "output_schema": {
    "type": "object",
    "properties": {
      "raw_kelly_fraction":     { "type": "number" },
      "fractional_kelly":       { "type": "number" },
      "capped_bet":             { "type": "number" },
      "kelly_bucket":           { "type": "string", "enum": ["weak", "moderate", "strong"] },
      "stats": {
        "type": "object",
        "properties": {
          "median_max_drawdown":  { "type": "number" },
          "p95_max_drawdown":     { "type": "number" },
          "ruin_rate":            { "type": "number" },
          "p5_final":             { "type": "number" },
          "median_final":         { "type": "number" },
          "p95_final":            { "type": "number" }
        }
      }
    }
  }
}

Representative response shape from the in-browser computation (Kelly Sizer with the sample_input above):

{
  "ok":   true,
  "tool": "kelly-sizer",
  "result": {
    "raw_kelly_fraction":    0.2300,
    "fractional_kelly":      0.0575,
    "capped_bet":            0.0500,
    "kelly_bucket":          "strong",
    "expected_growth_rate":  0.0142,
    "stats": {
      "median_max_drawdown": 0.459,
      "p95_max_drawdown":    0.626,
      "ruin_rate":           0.004,
      "p5_final":            18205.42,
      "median_final":        25109.96,
      "p95_final":           355583.84
    }
  },
  "meta": {
    "hub":          "aifinhub",
    "disclaimer":   "Education, not investment advice. BaFin / EU framework.",
    "tool_url":     "https://aifinhub.io/kelly-sizer/",
    "methodology":  "https://aifinhub.io/methodology/kelly-sizer/"
  }
}

Note: the tool runs client-side, so the JSON above is the shape an agent would surface to a user after the user opens the page and executes the calculator — not a server response. Numbers vary by Monte Carlo seed.