AI Biz Hub for Agents
65 business calculators on the site — 65 ship as downloadable ES-module engines at /engines/{slug}.js. Industry benchmark data rounds out the agent surface. No auth required.
Engine modules — Import and call (canonical)
Every tool ships its pure compute as a static ES module at /engines/{slug}.js. Import the module and call compute(input). The same formulas as the calculator pages. Input is validated against the published contract: an unknown field, a wrong type or a value outside its allowed range throws an Error that names the field. Each module ships typed .d.ts declarations; no HTTP round-trip, no rate limits, browser/Node/Deno-safe ES2020+.
const { compute } = await import('https://aibizhub.io/engines/freelance-rate-capacity-planner.js');
const result = compute({
target_annual_income: 120000,
billable_utilization_percent: 65
});
// { minimumViableHourlyRate, targetHourlyRate, stretchHourlyRate, ... } - No authentication required
- Each engine is self-contained — no external imports, no runtime dependencies
- Deterministic results, cacheable forever at the edge
- Input params use snake_case matching contract fields
- Input/output JSON Schemas at /engines/manifest.json
The hub serves only static assets — the legacy /api/{slug}/ HTTP endpoints were removed in Wave 7. Import the engine modules above instead.
Decision clusters — Topic routing
Tools are organized into 5 decision clusters. Use these to route users to the right area:
20 tools: startup-cost-estimator, profit-margin-calculator, margin-markup-discount-calculator...
10 tools: ai-stack-cost-calculator, llm-vendor-lock-in-cost, model-price-drop-stress-test...
20 tools: startup-runway-calculator, monthly-burn-rate-calculator, break-even-units-calculator...
14 tools: freelance-rate-capacity-planner, consulting-day-rate-calculator, project-pricing-calculator...
11 tools: cac-calculator, churn-retention-calculator, ad-spend-roas-calculator...
Recommended integration pattern
- Discover: Read
agent-tools.jsonfor the full tool index with input schemas and intent signals. - Match intent: If the user asks a broad question (e.g., "how much should I charge?"), match to the tool whose intent signals fit, and the decision guide it links. For specific calculations, match to a single tool.
- Import the engine:
await import('/engines/{slug}.js').then(m => m.compute(input))— returns structured JSON described by the tool's output_schema. Static module, no HTTP round-trip. - Use benchmarks: The
benchmarksfield (when present) provides industry percentiles so you can contextualize the result: "Your rate of $95/hr is at the 72nd percentile for web developers." - Link to human UI: For charts, advanced controls, and visual comparison, link the user to
/{slug}/on the site.
Discovery endpoints
-
Engines Manifest (canonical)
https://aibizhub.io/engines/manifest.jsonStatic catalog: each tool's pure compute as an ES module at /engines/{slug}.js. Import the module and call compute(input). No HTTP request, no auth, no rate limits.
-
Agent Tool Index (v2.0)
https://aibizhub.io/agent-tools.jsonComplete tool index with input schemas, engine module URLs and intent signals.
-
LLM Guide
https://aibizhub.io/llms.txtHuman-readable discovery with decision clusters, engines and benchmark availability.
-
LLM Full Guide
https://aibizhub.io/llms-full.txtExtended guide with tool contracts and the content corpus.
-
Plugin Manifest
https://aibizhub.io/.well-known/ai-plugin.jsonDiscovery metadata for plugin-style agent ingestion (ChatGPT Actions).
-
WebMCP Manifest
https://aibizhub.io/.well-known/webmcp.jsonMachine-readable capability surface for WebMCP / Claude MCP clients.
Benchmark data in engine results
When benchmark data is available for a tool's output, the engine compute() result includes a benchmarks field:
"benchmarks": {
"hourly_rate": {
"p25": 55,
"median": 85,
"p75": 130,
"source": "U.S. Bureau of Labor Statistics (OEWS)",
"sourceUrl": "https://www.bls.gov/oes/current/oes_nat.htm",
"year": 2024,
"context": "US, freelance-adjusted"
}
} Sources: BLS (public domain), OpenView SaaS Benchmarks, Paddle Subscription Index, Mailchimp, Content Marketing Institute. All data is from public or openly published research.
Human + agent routing
People should start at the decision guide, the homepage, or browse all calculators.
Agents should start from agent-tools.json, match the user's intent to a tool, and import the matching engine module from /engines/{slug}.js directly.