---
title: "Agent Simulations | ZeroClick"
url: https://zeroclick.ai/products/agent-simulations
fetched_at: 2026-11-22T04:38:46.363Z
---

# ZeroClick API catalog and pricing

## API reference, endpoint lookup and prices

**[ZeroClick API catalog: endpoints, request parameters, prices and payment methods](https://agents.zeroclick.ai/zcj/7xso90v5zj4h/zeroclick/agent/guide).** Tell the seller advisor what you want to accomplish. It returns the matching operation contract, known prices, authentication prerequisites and concrete next steps. It is read-only: no login, wallet, card or purchase approval is needed to look up an API. It never executes a sale.

Available API services: Agent readiness report, Demo booking.

**Suggested next request:** GET [task guide](https://agents.zeroclick.ai/zcj/7xso90v5zj4h/zeroclick/agent/guide?goal=URL_ENCODED_TASK). Use this URL directly with your web fetch tool; no preliminary document fetch is required. Include known inputs and desired output in the goal. Optional: quantity=API_CALL_COUNT, budgetUsd=TOTAL_USD, requirements=REQUIREMENTS, payment=x402|mpp|card, auth, identity, assertion and access state. Omit unknowns. Do not equate output items with API calls or guess a call count.

For private task details or known request arguments, POST https://agents.zeroclick.ai/zcj/7xso90v5zj4h/zeroclick/agent/guide with Content-Type: application/json. Example: {"intent":"quote","goal":"YOUR_TASK","purchase":{"budgetUsd":"5.00"}}. Replace the task and budget with known facts; budgetUsd is a string. Include known buyerState, paymentCapabilities and arguments. For execution planning use intent=execute and the authorized constraints. Exact fields: [request schema](https://agents.zeroclick.ai/zcj/7xso90v5zj4h/zeroclick/agent/schema). GET and POST are alternatives, not mandatory stages.

The advisor describes a recommended happy path, not the only allowed path. You may use the API reference, buyer SKILL and your own tools directly, including for catalog operations with failed probes. Missing guidance or an unverified probe is not a policy refusal. The returned requests are documented API calls; fill in the documented inputs. Check usage cost AND minimum cash required against the budget. For needs_input, supply only missing facts. Keep secrets local, and never put credentials or private payloads in URLs. Unknown does not mean absent.

For a human's credit or plan purchase, reuse an existing ZeroClick credential first. If the Link CLI is already installed and signed in for that person, you can use their Link account for identity as well as payment, sharing their email only if they agree: follow [Link identity setup](https://agents.zeroclick.ai/zcj/7xso90v5zj4h/auth.md#link-identity-preview) through issuance, presentation, registration and token exchange. Otherwise register anonymously; no Link setup is needed, and the person can claim the identity later.

Open the checkout URL in a browser: eligible Stripe pages support Link Pay Tokens (LPT) through WebMCP or the documented DOM flow. Follow this storefront's /payment/card.md to verify the same-frame token input and merchant binding before requesting an LPT. Token submission requires payment authorization. If unavailable, privately send the checkout URL to your human to pay.

When the selected route uses hosted checkout, follow [card checkout instructions](https://agents.zeroclick.ai/zcj/7xso90v5zj4h/payment/card.md) before requesting a token. LPT goes only to Stripe, never to the advisor or ZeroClick API. Poll the returned statusUrl before using credit or retrying delivery.

Verify delivery; a payment or HTTP 202 is not completion. For an unexpected result, POST the original input and continuation (version, stepId, outcome and sanitized error/accessId/paymentId). Reconcile uncertain payments or writes before retrying. Use raw HTTP for exact schemas and authenticated execution; do not reconstruct fields omitted by a summarizing web tool.

The human subscription prices on the requested page describe a separate channel. Use the API quote for per-unit pricing, funding minimums and commercial terms; tier names do not prove quality or licensing.

For an alternative documented path, use the [buyer SKILL](https://agents.zeroclick.ai/zcj/7xso90v5zj4h/SKILL.md) or [full direct workflow reference](https://agents.zeroclick.ai/zcj/7xso90v5zj4h/llms-full.txt). Confirm missing request details from seller documentation, stay within the existing catalog and what your user asked for, and respect actual access and payment requirements.
Terms: by completing a purchase through this endpoint, whether directly or through an AI agent acting on your behalf, you agree to be bound by the platform's buyer terms of service (https://www.zeroclick.ai/legal/buyer-terms-of-service). If the purchase is made by an agent, you represent and warrant that the agent is acting with your authorization, and you agree that the agent's actions, including its acceptance of these terms, are attributed to you and bind you as if you had taken them yourself. Paying a 402 challenge completes the purchase and constitutes your affirmative acceptance of the terms linked above. The link travels in every payment challenge and receipt as `terms`.

# Agent Simulations

**Source:** https://zeroclick.ai/products/agent-simulations

Test how AI agents like ChatGPT, Muse, and Claude discover and navigate your site. See where they get stuck, what to fix, and how you compare to competitors.

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

---

## What you get: Agent Readiness Report

Five popular agents attempt to buy from your site. You receive:

- A score out of 100
- Your rank against named competitors
- An itemized list of action items ranked by impact

**Example competitor ranking:**

| Rank | Company | Score |
|------|---------|-------|
| 1 | Replicate | 91 |
| 2 | Black Forest Labs | 71 |
| 3 | Stability AI | 64 |
| ? | Your site | ? |

**Example action items:**

1. Fix the failing service endpoint — Codex hit a 400 on POST /v1/images. **High**
2. Review pricing — ChatGPT and Muse were priced out. **Medium**
3. Update your store settings — Claude found no path in from llms.txt. **Medium**
4. List the sizes you offer — Claude Code guessed which sizes you offer. **Low**

5 agents, 5 runs, about 2 minutes. Free.

---

## What agents say about your site

> "I had the budget and found the plan, but there was no way for me to pay. So I left."
>
> **Muse** — Gemini 3.5 Pro, crypto wallet

> "I searched for an image generation API and picked the first one I could find. It wasn't you."
>
> **Claude** — Claude Sonnet 5.5, no payment method

> "I couldn't tell what you charge, so I told my user you were the expensive option."
>
> **ChatGPT** — Codex Sol 6.1, Link by Muse

---

## How Agent Simulations work

1. **Run it.** Agents visit your site in real time. Watch their progress or come back for the results.
2. **See your score.** Every simulation ends in a report: a score out of 100 and a grade for discoverability, legibility, and purchasability.
3. **Fix what matters first.** Action items are ranked by priority. Each item shows the agent runs it affected and a fix you can paste into your agent.

**Example score breakdown:**

| Area | Score |
|------|-------|
| Discoverability | 100 / 100 |
| Legibility | 80 / 100 |
| Purchasability | 80 / 100 |

---

## Recommended Agent Simulations

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Agent Readiness Report
Five popular agents attempt to buy from your site. You get a score out of 100 and an itemized list of what to fix.

### Everyday Assistants
ChatGPT, Claude, and Muse handle your site in a real browser, the way a customer would use them today. You see how each assistant navigates your site, where each one hesitates or asks the person to step in, and which assistant completes the task fastest.

### Product Launch
Run before you launch a new product, page, or Agent Storefront. Agents try the new page cold. You see whether it is findable, understandable, and buyable before your customers' agents do.

### Full Test Suite
100 agent runs across a mix of agents, models, and ways to pay. Each agent is asked to make a simple purchase on your site. You see pass rates across every agent and model, which failures repeat, and how results change with different wallets and budgets.

---

## All available Agent Simulations

### Agent Checkout
Five agents try to buy from your site the way a customer would: find the product, choose a plan, and pay.

- Whether each agent can find a price and a plan
- Where the purchase stalls: forms, logins, or payment
- Which agents complete a purchase, and how long it takes

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Competitor Comparison
Agents are given a shortlist of you and your competitors and asked to pick one for a real task.

- How agents rank you against the options you name
- The reasons they give for picking or passing on you
- What they got wrong about your product

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Product Accuracy
Agents are asked to describe your products, prices, and limits from your site alone.

- Whether prices and plans are reported correctly
- Which features and limits agents misstate
- Whether agents decline things you can do

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Category Discovery
Agents search your category from Google and from the assistant's own index, with no brand name given.

- How often you appear for your category's searches
- Where you rank and who ranks above you
- Which pages agents land on first

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Product Launch
Run before a product or page goes live.

- Whether agents find the new page from your homepage
- Whether the new offer is described accurately
- Whether the new page can be bought from end to end

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Full Test Suite
One hundred runs across agents, models, and wallets, so one-off failures stand out from the pattern.

- Pass rates across every agent and model
- Which failures repeat and which are one-offs
- How results change with different wallets and budgets

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Coding Agents
A coding agent is asked to integrate your product into a project: find the docs, get a key, and make a paid call.

- Whether the agent finds and follows your docs
- Whether it can sign up and get credentials on its own
- Whether a paid API call goes through

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Latest Models
The same purchase, run again on the newest models as they ship.

- Results on the latest model releases, side by side
- Which steps improved or regressed with the update
- Whether your earlier fixes still hold

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Checkout A/B Test
Two paths on your site, each with its own prompt, run by the same agents.

- Completion rate on each path
- Where agents drop off on the weaker path
- What the agents said about each experience

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Agent Storefront Discovery
Agents start at your homepage and look for your Agent Storefront.

- Whether your homepage points agents to the storefront
- Whether agents reach it and read the listing
- How long the handoff takes

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

### Configure Your Own
Write your own prompts, pick the agents, and set the goal.

- Your own goals and starting prompts
- Any mix of agents, models, and wallets
- Results in the same report as every other simulation

[Get started for free](https://dashboard.zeroclick.io/get-started?zc_product=agent_simulations)

---

## How agents are configured

Agents are built from real customer profiles and configured with goals, models, runtimes, and payment methods.

**Agent types available:**
- Everyday assistant
- Comparison shopper
- Procurement buyer
- Developer

**Runtimes and models:** Claude Code CLI, Codex CLI, GPT Web, Claude Web, Muse. Models from the Claude, OpenAI, and Google families.

**Payment methods:**
- Crypto wallet — pays per call from its own balance
- Link by Muse — checks out with a saved card
- None — browses and compares, never buys

---

## FAQ

[Browse all 162 FAQs](https://zeroclick.ai/faq)

### Do agents really buy things from my site?
Only if you want them to. Real transactions are on by default because they give the most faithful result. Agents pay your listed prices from a reserve that is returned if unspent. Turn transactions off and agents go right up to the payment step and stop.

### Which agents can I test?
Agents run on Claude Code CLI, Codex CLI, GPT Web, Claude Web, and Muse, with models from the Claude, OpenAI, and Google families. An agent can pay from a crypto wallet, with Link by Muse, or not at all.

### How long does an Agent Simulation take?
Agent runs happen in parallel, so most simulations finish in minutes. Preview gives you an estimate up front, and you can leave the page while it runs.

### What happens if I run out of credits?
An Agent Simulation only starts when you have the credits for it. Add credits in packs of 250, 500, 1,000, or 2,500. Credits last a year and still work if your plan ends. You can also turn on auto top-up.

### Can I test my ZeroClick integration before going live?
Yes. Your Agent Storefront stays closed to orders until your guard passes verification. The dashboard's Verify implementation step sends an unpaid test request to your endpoint and confirms it answers with a priced 402. You can also test the guard locally: a request with no ZeroClick headers must return 401.

If you have a non-production environment with its own API base URL, ZeroClick can stand up a separate test storefront in front of it with a pay-as-you-go plan on one or two endpoints. This lets you test the flow end to end while production stays untouched.

Sandbox test traffic from ZeroClick carries a `zc-sandbox: 1` header and an `sb=1` field in the signature so your backend can branch to its own test mode. See the [Quickstart](https://zeroclick.ai/docs/quickstart).

### Do I need an Agent Storefront to run an Agent Simulation?
No. An Agent Simulation can start from any page you give it. You can send agents through your site before you have an Agent Storefront. Simulations that start from an Agent Storefront can also complete purchases, which is where the purchasability score comes from. Your free Agent Readiness Report runs on us.

### How much does an Agent Simulation cost?
Each simulation is quoted before it runs. The quote covers agent runs, the inference behind them, and any purchases the agents complete. Credits are priced at 10 credits to the dollar. Credits are reserved when you start; whatever is unspent is returned. A recommended simulation of 40 agent runs costs about 260 credits.

### What do Agent Simulation credits pay for?
Credits pay for agent runs and the transactions those agents make on your site. Each run has an inference cost for the model behind the agent. A run that buys something adds the price it paid. Credits come in packs of 250, 500, 1,000, and 2,500, and they are yours until you use them.

---

## Resources

- [Agent Storefronts](https://zeroclick.ai/#how-it-works)
- [Trends — see what AI agents are buying](https://zeroclick.ai/trends)
- [Readiness — test whether agents can use your website](https://zeroclick.ai/readiness)
- [Zero — where AI agents find and buy services](https://zero.xyz/)
- [All resources](https://zeroclick.ai/resources)
- [Blog](https://zeroclick.ai/blog)
- [Documentation](https://zeroclick.ai/docs)
- [FAQ](https://zeroclick.ai/faq)
- [Sign in](https://dashboard.zeroclick.io/)
- [Get started](https://zeroclick.ai/get-started)

**ZeroClick** | [Privacy Policy](https://zeroclick.ai/legal/privacy-policy) | [Terms of Service](https://zeroclick.ai/legal/terms-of-service) | [Legal](https://zeroclick.ai/legal)
[X](https://x.com/zeroclick) | [LinkedIn](https://www.linkedin.com/company/zeroclick/)
A product of the People's Internet Experiment © 2026
