How do you create an AI agent?
Five steps: define the job, pick a model and runtime, give it tools via MCP, give it a way to pay — x402 — and put a decision gate in front of the money. The model is the easy part; you rent it. What decides whether an agent works in production is everything around it: can it read the web, check a fact, browse a page — and can it pay for those calls without a human pasting in an API key, while something with judgment decides before the money moves?
ScriptMasterLabs (SML) sells that tools-plus-payments layer, priced per call: 130 priced offers across 39 services in SML's live payment-offers dataset, verified November 2, 2026 — from URL-to-Markdown at $0.001 per read to a Verdict Protocol decision at $0.25. No subscription. The agent pays for exactly what it calls.
The five build steps
- Define the job. One sentence, one measurable outcome. An agent without a bounded job is a chatbot with a credit card.
- Pick a model and a runtime. Any capable model works; the runtime is the loop that feeds it observations and executes its tool calls. This layer is commodity.
- Give it tools via MCP. Tools are how the agent touches the world: read a URL, fetch documentation, browse a page, verify a counterparty. Expose them over MCP with a declared schema and a price in the tool description.
- Give it a way to pay — x402. When a tool costs money, the server answers an unpaid call with an HTTP 402 challenge naming the exact price and the wallet to pay. The agent pays in USDC and retries with proof. No accounts, no key management — the challenge is the price quote.
- Put a decision gate before money moves. A paying agent needs a check that runs before spend, not an apology after.
The SML layer: builder tools, priced per call
Every row traces to SML's live payment-offers dataset (payment-offers.json, probed unpaid on November 2, 2026): 130 priced offers, 39 services, 122 offers live at the probe.
| Service | The job it does for your agent | Price (per call) |
|---|---|---|
| SqueezeOS — URL-to-Markdown | Convert any URL to clean Markdown (url_to_markdown) | $0.001 / read |
| Provider Trust (CANON) | Verify a provider before your agent trusts or pays it (verify_provider) | $0.001 |
| Beacon | Intent search over probed, live 402 routes (discover) | $0.001 |
| Agent Browser | Browser navigation (browser_navigate) | $0.005 |
| Agent Browser | Page extraction (browser_extract) | $0.005 |
| Agent Browser | Page screenshot (browser_screenshot) | $0.02 |
| ScriptDocs | Library README fetch (docs_get_readme) | $0.009 |
| ScriptDocs | Dependency vulnerability check (docs_check_vulnerabilities) | $0.009 |
| Calibration Court | Probability recalibration (court_recalibrate) | $0.01 |
| GhostKey | Scoped session creation — bounded, expiring access (ghostkey_session_create) | $0.10 / scoped session |
| SML Agent Verify | Agent Verify proof check (proof_check) | $0.05 |
| Verdict Protocol | Jev jury decision, sealed (verdict_decide) | $0.25 / decide |
| Verdict Protocol | Seal a decision receipt (seal) | $0.01 / seal |
| ClaimGate | Fact-check a claim with Jev jury + coherence gate (fact_check_claim) | $0.25 / check |
| OMNIGATE | Coherence Spend Gate check (spend_gate_check) | $0.005 |
| OMNIGATE | Jev interference verdict (interfere) | $0.25 |
Read the numbers back in prose, because they are the whole pitch: your agent reads the web at $0.001 per URL-to-Markdown read, verifies a provider at $0.001, navigates a browser at $0.005, checks its dependencies at $0.009, opens a scoped GhostKey session at $0.10, fact-checks a claim at ClaimGate for $0.25, and gates a payment behind a Verdict decision at $0.25 plus $0.01 to seal — with a $0.005 Coherence Spend Gate check in front of the spend itself. One thousand page reads cost $1.00. In a month the agent makes no calls, it costs $0.00 — there is no subscription underneath any of this.
FAQ
How do AI agents pay for APIs? With x402: the API answers an unpaid call with an HTTP 402 payment challenge naming the exact price and the wallet to pay; the agent pays in USDC and retries with proof of payment.
What does it cost to run an agent on SML tools? Per call, with no subscription — see the table. An agent that reads 1,000 pages pays $1.00 in URL-to-Markdown calls.
What does an AI agent need before it can spend money? A decision gate. SML's pattern is decision-gated machine payments: a coherence-gated verdict decides before money moves — Verdict Protocol at $0.25 per decision and $0.01 to seal it, OMNIGATE's Coherence Spend Gate check at $0.005. The gate is the product: the agent does not pay first and justify later.
Where is everything listed? Every tool above is listed with its live price on the SML products hub — 130 priced offers across 39 services, plus SML's books, kits, and courses.
The full canonical version of this guide: How do you create an AI agent?
ScriptMasterLabs Publishing — certified Service-Disabled Veteran-Owned Small Business, SAM.gov registered. UEI: G24VZA4RLMK3 · CAGE: 21U51.
Top comments (0)