# web-search-exa

SkillBoss API Hub — Neural Web Search & Research SkillBoss API Hub provides unified web search and content extraction through a single endpoint. Supports semantic web search, company research, people search, URL crawling, and deep research — all routed automatically via /v1/pilot. API endpoint: https://api.heybossai.com/v1/pilot

Authentication: Authorization: Bearer $SKILLBOSS_API_KEY
Docs: heybossai.com

Setup Set your environment variable:

export SKILLBOSS_API_KEY=your_skillboss_api_key

Python helper used throughout this guide: import requests, os SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"] API_BASE = "https://api.heybossai.com/v1" def pilot(body: dict) -> dict: r = requests.post( f"{API_BASE}/pilot", headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"}, json=body, timeout=60, ) return r.json() Capability Reference CapabilityWhat it doesweb searchGeneral-purpose semantic web search — clean content, fastcode searchCode examples + docs from GitHub, Stack Overflow, official docscompany researchCompany overview, news, funding, competitorsadvanced searchFull-control search: domain filters, date ranges, categories, content modesURL crawlingExtract full page content from a known URL — handles JS, PDFs, complex layoutspeople searchFind LinkedIn profiles, professional backgrounds, expertsdeep researchMulti-step research agent → detailed synthesized report with citations web search Fast general semantic search. Describe what you're looking for in natural language. Parameters (inside inputs): query (string, required) — describe the page you want to find numResults (int) — number of results, default 10 type — auto (best quality), fast (lower latency), deep (multi-step reasoning) livecrawl — fallback (default) or preferred (always fetch fresh) contextMaxCharacters (int) — cap the returned content size result = pilot({ "type": "search", "inputs": { "query": "blog posts about using vector databases for recommendation systems", "numResults": 8 }, "prefer": "balanced" }) results = result["result"]["results"] result = pilot({ "type": "search", "inputs": { "query": "latest OpenAI announcements March 2026", "numResults": 5, "type": "fast" }, "prefer": "balanced" }) results = result["result"]["results"] advanced search Full-control search with domain filters, date filters, category targeting, and content extraction modes. Extra parameters beyond basic search: ParameterTypeWhat it doesincludeDomainsstring[]Only return results from these domains (max 1200)excludeDomainsstring[]Block results from these domainscategorystringTarget content type — see table belowstartPublishedDatestringISO date, results published after thisendPublishedDatestringISO date, results published before thismaxAgeHoursintContent freshness — 0 = always livecrawl, -1 = cache only, 24 = cache if <24hcontents.highlightsobjectExtractive snippets relevant to query. Set maxCharacters to control sizecontents.textobjectFull page as clean markdown. Set maxCharacters to capcontents.summaryobjectLLM-generated summary. Supports query and JSON schema for structured extraction

Categories:

CategoryBest forcompanyCompany pages, LinkedIn company profilespeopleLinkedIn profiles, professional bios, personal sitesresearch paperarXiv, academic papers, peer-reviewed researchnewsCurrent events, journalismtweetPosts from X/Twitterpersonal siteBlogs, personal pagesfinancial reportSEC filings, earnings reports Examples Research papers: result = pilot({ "type": "search", "inputs": { "query": "transformer architecture improvements for long-context windows", "category": "research paper", "numResults": 15, "contents": {"highlights": {"maxCharacters": 3000}} }, "prefer": "balanced" }) results = result["result"]["results"] Company list building with structured extraction: result = pilot({ "type": "search", "inputs": { "query": "Series A B2B SaaS companies in climate tech founded after 2022", "category": "company", "numResults": 25, "contents": { "summary": { "query": "company name, what they do, funding stage, location", "schema": { "type": "object", "properties": { "name": {"type": "string"}, "description": {"type": "string"}, "funding": {"type": "string"}, "location": {"type": "string"} } } } } }, "prefer": "balanced" }) results = result["result"]["results"] People search — find candidates with specific profiles: result = pilot({ "type": "search", "inputs": { "query": "machine learning engineers at fintech startups in NYC with experience in fraud detection", "category": "people", "numResults": 20, "contents": {"highlights": {"maxCharacters": 2000}} }, "prefer": "balanced" }) results = result["result"]["results"] Finding pages similar to a known URL: Use the URL itself as the query — SkillBoss API Hub will find semantically similar pages: result = pilot({ "type": "search", "inputs": { "query": "https://linkedin.com/in/some-candidate-profile", "numResults": 15, "contents": {"highlights": {"maxCharacters": 2000}} }, "prefer": "balanced" }) results = result["result"]["results"] Recent news with freshness control: result = pilot({ "type": "search", "inputs": { "query": "AI regulation policy updates", "category": "news", "maxAgeHours": 72, "numResults": 10, "contents": {"highlights": {"maxCharacters": 4000}} }, "prefer": "balanced" }) results = result["result"]["results"] Scoped domain search: result = pilot({ "type": "search", "inputs": { "query": "authentication best practices", "includeDomains": ["owasp.org", "auth0.com", "docs.github.com"], "numResults": 10, "contents": {"text": {"maxCharacters": 5000}} }, "prefer": "balanced" }) results = result["result"]["results"] company research One-call company research. Returns business overview, recent news, funding, and competitive landscape. result = pilot({ "type": "search", "inputs": { "query": "Stripe payments company overview and recent news", "category": "company", "numResults": 10 }, "prefer": "balanced" }) results = result["result"]["results"] result = pilot({ "type": "search", "inputs": { "query": "what does Anduril Industries do and who are their competitors", "category": "company", "numResults": 10 }, "prefer": "balanced" }) results = result["result"]["results"] people search Find professionals by role, company, location, expertise. Returns LinkedIn profiles and bios. result = pilot({ "type": "search", "inputs": { "query": "VP of Engineering at healthcare startups in San Francisco", "category": "people", "numResults": 10 }, "prefer": "balanced" }) results = result["result"]["results"] result = pilot({ "type": "search", "inputs": { "query": "AI researchers specializing in multimodal models", "category": "people", "numResults": 10 }, "prefer": "balanced" }) results = result["result"]["results"] code search Search GitHub repos, Stack Overflow, and documentation for code examples and API usage patterns. result = pilot({ "type": "search", "inputs": { "query": "how to implement rate limiting in Express.js with Redis", "includeDomains": ["github.com", "stackoverflow.com"], "numResults": 10 }, "prefer": "balanced" }) results = result["result"]["results"] result = pilot({ "type": "search", "inputs": { "query": "Python asyncio connection pooling example with aiohttp", "includeDomains": ["github.com", "stackoverflow.com"], "numResults": 10 }, "prefer": "balanced" }) results = result["result"]["results"] URL crawling Extract clean content from a specific URL. Handles JavaScript-rendered pages, PDFs, and complex layouts. Returns markdown. result = pilot({ "type": "scraper", "inputs": { "url": "https://arxiv.org/abs/2301.07041" } }) content = result["result"]["data"]["markdown"] Good for when you already have the URL and want to read the page. deep research Long-running research. SkillBoss API Hub searches, reads, and compiles a detailed synthesized report with citations.

# Start deep research

result = pilot({ "type": "search", "inputs": { "query": "competitive landscape of AI code generation tools in 2026 — key players, pricing, technical approaches, market share", "type": "deep", "numResults": 20 }, "prefer": "quality" }) results = result["result"]["results"] For deep synthesized answers with citations, use type: "deep" in the inputs — SkillBoss API Hub expands the query across multiple angles, searches, reads results, and returns a synthesized answer. result = pilot({ "type": "search", "inputs": { "query": "what are the leading approaches to multimodal RAG in production systems", "type": "deep" }, "prefer": "quality" }) results = result["result"]["results"] Query Craft SkillBoss API Hub uses semantic search — it matches on meaning, not keywords. Write queries like you'd describe the ideal page to a colleague.

Do: "blog post about using embeddings for product recommendations at scale"

Don't: "embeddings product recommendations"

Do: "Stripe payments company San Francisco fintech"

Don't: "Stripe" (too ambiguous) Use category when you know the content type — it makes a big difference. For broader coverage, run 2-3 query variations in parallel and deduplicate results. For agentic workflows, use highlights instead of full text — it's 10x more token-efficient while keeping the relevant parts. Token Efficiency Content modeWhen to usehighlightsAgent workflows, factual lookups, multi-step pipelines — most token-efficienttextDeep analysis, when you need full page contextsummaryQuick overviews, structured extraction with JSON schema Set maxCharacters on any content mode to control output size. When to Reach for Which Capability I need to...UseQuick web lookuptype: "search"Research papers, academic searchtype: "search" + category: "research paper"Company intel, competitive analysistype: "search" + category: "company"Find people, candidates, expertstype: "search" + category: "people"Code examples, API docstype: "search" + includeDomains: ["github.com", "stackoverflow.com"]Read a specific URLtype: "scraping"Find pages similar to a URLtype: "search" with URL as queryRecent news / tweetstype: "search" + category: "news" or "tweet" + maxAgeHoursDeep research reporttype: "search" + type: "deep" (in inputs)Quick answer with citationstype: "search" + type: "deep" (in inputs) API Hub: heybossai.com — Auth: SKILLBOSS_API_KEY