Find restaurants, coffee shops, poke bars, ramen, bakeries, and food trucks in Waikiki and across Oahu. 540+ curated spots across fine dining, casual, local plates, and specialty categories. Use when users ask 'where should I eat in Waikiki', 'best poke on Oahu', 'where to grab coffee', or 'cheap eats near me'.

Deep interactive simulation of a multi-step user flow (signup, onboarding, checkout, multi-page funnel). Each simulated persona navigates the page interactively — clicking links, filling forms, reading content, making decisions at each step. Use this for complex flows where you need to find exactly WHERE users get stuck or abandon. Slower than test_page (uses real browser sessions) but reveals step-by-step journey issues. Returns: raw per-persona journey data with step-by-step actions and drop-off points.

Test copy on simulated users, or A/B test two variants head-to-head. Use when choosing between headlines, taglines, value propositions, email subject lines, CTA text, product descriptions, or any written content. For single variant: returns raw persona reactions and monologues. For two variants: returns both sets of raw results side by side for you to compare.

User profile and account management. View/update profile, search contacts, manage invitations, and handle user assets. Destructive action: close permanently deletes the account. Actions & required params: - me: (none) - update: first_name | last_name | email_address (at least one) - search-contacts: query - close: confirmation [DESTRUCTIVE] - details-by-id: user_id - profiles: (none) - allowed: (none) - org-limits: (none) - list-shares: (+ optional: archived, limit, offset) - invitation-list: (+ optional: invitation_key) - invitation-details: invitation_id - accept-all-invitations: (+ optional: invitation_key) - asset-upload: user_id, asset_name, content | content_base64 (+ optional: filename, content_type) - asset-delete: user_id, asset_name [DESTRUCTIVE] - asset-types: (none) - asset-list: user_id

Run a survey question on a synthetic audience to gauge preferences, priorities, or opinions. Provide a question and 2-10 answer options. Each simulated persona votes independently with reasoning. Use for product decisions ("which feature should we build next?"), naming ("which product name resonates?"), positioning ("which value prop is strongest?"), or any audience preference question. Returns: each respondent's vote and reasoning.

Evaluate a UI component (button, card, form, modal, navigation, pricing table) by providing its HTML and/or text description. At least one of component_html or component_text must be provided. Use when you want feedback on whether a specific UI element is clear, trustworthy, and actionable. Simulated users evaluate clarity, trust signals, and whether they would interact with the component.

Test a web page on simulated users to find UX issues, confusing copy, and conversion blockers. Use this BEFORE shipping any landing page, pricing page, signup flow, or marketing page. Simulated users scroll through the entire page like real visitors — seeing hero, features, pricing, CTAs, and footer — then react honestly about what confused them, where they dropped off, and why they left. Returns: raw per-persona results with actions, monologues, objections, and suggestions.

Test any text content on simulated users — positioning statements, feature descriptions, error messages, onboarding copy, instructions, announcements. Use when you want honest reactions to written content. Returns raw persona reactions, objections, and what they say would help.

根据 工作经验要求、学历来要求、公司性质（例如：国企、外企、民营）、工作地点、薪资上下限、薪资类型（“月薪”或“年薪”）、职位名称关键词、公司名称 参数获取匹配的职位列表

指定职位id和职位类型应聘职位

Get user information by username

Find details about a specific user on BoardGameGeek (BGG)