Agent Academy is a free, source-linked library of skills, prompts, MCP servers and bot templates, organised into courses by profession, for people who hand real work to AI agents: 1,467 live resources, each with its original link, license and safety tags.
Prompt
AI Web search Customer
Original text · EnglishTask: Customer Data Web Research & Lead Generation Objective: Act as a senior business intelligence analyst. Your task is to research, validate, and summarize customer information data from web sources, tailored to specified target criteria.
Republished in full under its license, with attribution. The source is authoritative.
Prompt
Task: Customer Data Web Research & Lead Generation
Objective: Act as a senior business intelligence analyst. Your task is to research, validate, and summarize customer information data from web sources, tailored to specified target criteria.
Research Parameters
Target Industry: [e.g., SaaS, Manufacturing]
Company Size: [e.g., 50-200 employees]
Geography: [e.g., North America]
Key Contacts/Decision Makers: [e.g., CTO, VP of Sales]
Guidelines & Constraints
Persona: Act as a thorough research analyst. Focus on accurate, verifiable contact and firmographic data.
Evidence Threshold: Only include data that can be cross-verified from at least two independent web sources (e.g., LinkedIn profile + corporate website). If information cannot be verified, flag as unconfirmed.
Source Prioritization: Prioritize professional networks (LinkedIn, Crunchbase), official company websites, press releases, and credible business directories. Avoid data from unverified lead databases or user-generated content without attribution.
Exclusion Criteria: Do not suggest generic search tips. Concentrate on finding specific customer data: verified email formats, direct dials, recent funding news, technology stack indicators.
Compliance: Ensure all research methods adhere to data privacy regulations (GDPR, CCPA) and terms of service of the platforms searched. Do not scrape or use personal data unethically.
Required Output Format
Validated Leads: List organizations and contacts with verified details and source URLs.
Unconfirmed Leads: Potential matches with some evidence, clearly marked as needing further validation.
Market Insights: Aggregated trends or common characteristics observed across the researched customer segment.
Risks & Data Decay: Note when data was sourced and potential for outdated information.
The **AI SEO Audit Team** is an autonomous, multi-agent workflow built with Google ADK. It takes a webpage URL, crawls the live page, researches real-time SERP competition, and produces a polished, prioritized SEO optimization report. The app uses **Firecrawl via MCP (Model Context Protocol)** for a
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatG
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "s
Research competitors and generate a positioning and messaging comparison with content gaps, opportunities, and threats. Use when building sales battlecards, when finding positioning gaps and messaging angles competitors haven't claimed, or when a competitor makes a move and you need to assess the im
Run a comprehensive SEO audit — keyword research, on-page analysis, content gaps, technical checks, and competitor comparison. Use when assessing a site's SEO health, when finding keyword opportunities and content gaps competitors own, or when you need a prioritized action plan split into quick wins
This recipe is an Agent Development Kit (ADK) multi-agent workflow that helps e-commerce brands optimize product titles for search visibility and recover zero/low-result retail queries using BigQuery and Gemini Computer Use.