exa-research
Exa Research provides Q&A capabilities with source attribution, combining the Answer API for cited responses with deep search for query expansion and summaries. Use it to build research automation, fact verification, and long-form reports with streaming support.
Exa Research implements Q&A systems with verified sources and citations through its Answer API and deep search features.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-25
Exa Research implements Q&A systems with verified sources and citations through its Answer API and deep search features. Exa Research provides Q&A capabilities with source attribution, combining the Answer API for cited responses with deep search for query expansion and summaries. Use it to build research automation, fact verification, and long-form reports with streaming support.
Use it when
- Exa Research combines deep neural search with citation extraction to provide comprehensive research results.
- Yes, Exa Research supports streaming answer generation with full source attribution.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
ejirocodes/agent-skills/exa-research
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I use exa answer endpoint to get citations?
Exa Research's answer endpoint delivers Q&A responses with verified source citations built in. The Answer API processes your query, searches authoritative sources, and returns grounded responses that attribute claims directly to their origins. This enables you to build fact-checked systems where every answer includes traceable source links, making it ideal for research automation and knowledge verification workflows.
What is exa deep search with citations and how does it work?
Exa Research combines deep neural search with citation extraction to provide comprehensive research results. When you submit a query, the system expands it intelligently, retrieves relevant content from authoritative sources, and summarizes findings while preserving source attribution. This approach powers research automation by automating the discovery, verification, and summarization of information across multiple sources simultaneously.
Can exa research provide streaming answers with source attribution?
Yes, Exa Research supports streaming answer generation with full source attribution. You can build applications that deliver real-time responses to users while maintaining citations throughout the stream. The Python integration enables async processing, allowing you to handle research tasks asynchronously and generate long-form reports without blocking, perfect for building responsive research tools.
How does exa research handle fact verification and query expansion?
Exa Research extracts and verifies facts through smart query expansion and deep neural search. The system automatically expands your initial query to capture related concepts, searches across verified sources, and returns grounded results with citations. This enables automated fact-checking workflows where claims are validated against authoritative sources, reducing manual verification overhead in research automation pipelines.
What are the main use cases for building research automation with exa?
Exa Research powers multiple research automation scenarios: Q&A systems with verified citations, automated fact verification, long-form report generation with async processing, and knowledge extraction pipelines. The combination of the Answer API for cited responses, deep search for query expansion, and streaming support makes it suitable for research platforms, content verification tools, and knowledge management systems.
Is Exa Research open source and what license does it use?
Exa Research is released under the MIT license, making it freely available for commercial and private use. The MIT license permits modification, distribution, and private use with minimal restrictions, enabling developers to integrate Exa Research into their own projects and build custom research automation solutions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Exa Research & Answer API
Quick Reference
| Topic | When to Use | Reference |
|---|---|---|
| Answer API | Q&A with citations, grounded responses | answer-api.md |
| Deep Search | Smart query expansion, high-quality summaries | deep-search.md |
| Citations | Source attribution, verification | citations.md |
Essential Patterns
Answer API (Python)
```python from exa_py import Exa
exa = Exa()
response = exa.answer( "What are the key features of Python 3.12?", text=True )
print(response.answer) for citation
(truncated - see the full file via the links below)
File tree — 4 files
exa/skills/exa-research/SKILL.md
exa/skills/exa-research/references/answer-api.md
exa/skills/exa-research/references/citations.md
exa/skills/exa-research/references/deep-search.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Implement Q&A system with verified sources and citations”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Exa RAG enables you to construct retrieval-augmented generation systems that pull live web data into your AI applications. Integrate with LangChain, LlamaIndex, Vercel AI SDK, or Claude MCP to add grounded search capabilities, citations, and fact-checking to your agents.
This skill provides patterns for integrating Exa.ai's search API into applications using Python (exa_py) or TypeScript (exa-js). It covers search modes—auto, neural, and keyword—along with domain and date filtering, text extraction, summaries, and highlights to help you retrieve and process web content effectively.
exa-entities integrates Exa.ai's search capabilities to locate companies and people across the web for sales prospecting, market research, and recruiting. Query by industry, location, or role to surface relevant profiles and company information, or use Websets to monitor and collect data continuously.
Exa Research performs neural web search that understands meaning rather than keywords, offering four distinct actions: find relevant URLs by topic, get cited answers to factual questions, fetch full text from web pages, and discover similar sites. Each call costs $0.012, with content retrieval billed per URL.
web-search-exa provides neural search powered by embeddings to discover relevant web content, extract full page text, and synthesize findings. Query the web intelligently across multiple search modes, filter by domain or date, and get LLM-generated answers informed by live search results.
Exa Search integrates Exa's Search API to conduct web research with fine-grained control over results. Choose your search mode, apply domain and date filters, and request only the content you need—highlights for efficiency or full text for deep reading. Built-in workflows handle news lookups, source verification, and citation management.