web-research
langchain-ai/deepagents
Delegate web research across multiple subagents, synthesize findings, and produce cited reports.
What is web-research?
Breaks down research questions into subtopics, spawns parallel subagents to search the web, and synthesizes their findings into a comprehensive cited report. Use when you need to research a topic online, find current information, compare options, or produce a research report.
- Analyzes research questions and creates structured research plans with 2-5 subtopics
- Delegates web searches to parallel subagents with clear, specific instructions
- Organizes all research files in a dedicated folder structure for easy access
- Reads and synthesizes findings from multiple sources into a cohesive response
- Produces final research reports with source citations and URLs
- Limits searches to 3-5 per subtopic to maintain efficiency
How to install web-research
npx skills add https://github.com/langchain-ai/deepagents --skill web-research- Access to web search capability via subagents
- Ability to create and manage local file directories
- write_file and read_file tools for organizing research outputs
How to use web-research
- 1.Create a research folder using mkdir research_[topic_name]
- 2.Write a research_plan.md file breaking down the question into 2-5 distinct subtopics
- 3.Use the task tool to spawn subagents for each subtopic with clear instructions and file output paths
- 4.Run up to 3 subagents in parallel for efficiency
- 5.Use list_files to verify all findings files were created
- 6.Read the findings files using read_file with local file paths
- 7.Synthesize the information into a comprehensive response with source citations
- 8.Optionally write a final research_report.md file
Use cases
- Compare features and pricing across competing products or services
- Investigate current trends, news, or developments in a specific industry
- Research background and context for a complex topic before making decisions
- Gather pros and cons for evaluating different options or approaches
- Create a comprehensive report on a subject with cited sources
- Researchers and analysts gathering information on complex topics
- Decision-makers comparing options or evaluating alternatives
- Content creators and writers needing sourced background information
- Business professionals conducting market or competitive research
- Anyone needing current information beyond their training data
web-research FAQ
Run up to 3 subagents in parallel for efficient research. This balances speed with manageability.
Limit each subagent to 3-5 web searches maximum. This prevents over-research and keeps the process focused.
Always instruct subagents to use write_file to save findings to research_[topic_name]/findings_[subtopic].md. Use read_file to access local files, not URLs.
Break them into 3-5 non-overlapping subtopics in your research plan. Each subtopic becomes a separate subagent task.
Yes, use the fetch_url tool to retrieve additional information from specific URLs if needed during synthesis.
Full instructions (SKILL.md)
Source of truth, from langchain-ai/deepagents.
name: web-research description: Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.
Web Research Skill
Research Process
Step 1: Create and Save Research Plan
Before delegating to subagents, you MUST:
-
Create a research folder - Organize all research files in a dedicated folder relative to the current working directory:
mkdir research_[topic_name]This keeps files organized and prevents clutter in the working directory.
-
Analyze the research question - Break it down into distinct, non-overlapping subtopics
-
Write a research plan file - Use the
write_filetool to createresearch_[topic_name]/research_plan.mdcontaining:- The main research question
- 2-5 specific subtopics to investigate
- Expected information from each subtopic
- How results will be synthesized
Planning Guidelines:
- Simple fact-finding: 1-2 subtopics
- Comparative analysis: 1 subtopic per comparison element (max 3)
- Complex investigations: 3-5 subtopics
Step 2: Delegate to Research Subagents
For each subtopic in your plan:
-
Use the
tasktool to spawn a research subagent with:- Clear, specific research question (no acronyms)
- Instructions to write findings to a file:
research_[topic_name]/findings_[subtopic].md - Budget: 3-5 web searches maximum
-
Run up to 3 subagents in parallel for efficient research
Subagent Instructions Template:
Research [SPECIFIC TOPIC]. Use the web_search tool to gather information.
After completing your research, use write_file to save your findings to research_[topic_name]/findings_[subtopic].md.
Include key facts, relevant quotes, and source URLs.
Use 3-5 web searches maximum.
Step 3: Synthesize Findings
After all subagents complete:
-
Review the findings files that were saved locally:
- First run
list_files research_[topic_name]to see what files were created - Then use
read_filewith the file paths (e.g.,research_[topic_name]/findings_*.md) - Important: Use
read_filefor LOCAL files only, not URLs
- First run
-
Synthesize the information - Create a comprehensive response that:
- Directly answers the original question
- Integrates insights from all subtopics
- Cites specific sources with URLs (from the findings files)
- Identifies any gaps or limitations
-
Write final report (optional) - Use
write_fileto createresearch_[topic_name]/research_report.mdif requested
Note: If you need to fetch additional information from URLs, use the fetch_url tool, not read_file.
Best Practices
- Plan before delegating - Always write research_plan.md first
- Clear subtopics - Ensure each subagent has distinct, non-overlapping scope
- File-based communication - Have subagents save findings to files, not return them directly
- Systematic synthesis - Read all findings files before creating final response
- Stop appropriately - Don't over-research; 3-5 searches per subtopic is usually sufficient
Related skills
More from langchain-ai/deepagents and the wider catalog.
langgraph-docs
Access LangGraph Python documentation to build stateful agents and multi-agent workflows.
social-media
Draft engaging social media posts with research-backed content and generated images for LinkedIn, Twitter/X, and other platforms.
arxiv-search
Search arXiv for preprints and academic papers by topic with abstracts.
blog-post
Write and structure long-form blog posts with SEO optimization and auto-generated cover images.
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\".
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.