Back to guides
4
3 min

Research Agent

Search, Summarize, Cite

Why Research Is the Killer Feature

Email and calendar management save time. Research assistance saves *thinking*. An AI assistant that can search your saved knowledge, synthesize findings, and cite sources transforms how you make decisions.

Search: Finding What Matters

Your bookmarks are a personal knowledge base — articles, documentation, tools, and references you've saved. The search tool needs to be smarter than exact string matching.

A good bookmark search checks:

  • Title — the primary label
  • Tags — categorical labels you assigned
  • Notes — your annotations and key takeaways
  • URL — sometimes the domain reveals relevance
  • Fuzzy matching (case-insensitive, partial matches) makes the search useful for natural language queries like "that article about API rate limiting" even if the bookmark title is "Anthropic API Best Practices."

    Summarization with Citations

    Every claim your assistant makes should trace back to a source. This isn't just good practice — it's what makes AI output trustworthy.

    The pattern:

  • Search returns matching bookmarks with their notes
  • Claude reads the notes and synthesizes key themes
  • Each finding includes a reference: [Source: bookmark title]
  • Example output:

    > Rate limiting best practices suggest using exponential backoff starting at 1 second [Source: Anthropic API Best Practices]. For high-throughput applications, implement request queuing with a token bucket algorithm [Source: Building Resilient API Clients].

    Research Brief Format

    A structured research brief is more useful than freeform prose:

    SectionPurpose
    Topic Overview2-3 sentence summary of what was found
    Key FindingsBulleted list of facts, each with a citation
    Source ListAll bookmarks referenced, with URLs
    Knowledge GapsWhat the available data doesn't cover
    Recommended ActionsSuggested next steps based on findings

    This format works because it's scannable, actionable, and honest about limitations.

    Cross-Referencing Research with Tasks

    Your task list often contains items that need research:

  • "Evaluate CI/CD options for the new service"
  • "Compare pricing for cloud GPU providers"
  • "Research compliance requirements for EU expansion"
  • By connecting the research agent to the task list, Claude can answer: "What research do I need for the infrastructure migration project?" It searches tasks for research-related items, then checks bookmarks for existing material on those topics.

    Building Trust Through Transparency

    PracticeImpact
    Always cite sourcesUser can verify claims
    Flag knowledge gapsUser knows what's missing
    Distinguish facts from inferenceUser knows what Claude concluded vs. what was stated
    Show search resultsUser sees what data Claude used

    An assistant that says "I found 3 bookmarks on this topic, but none of them cover pricing" is more useful than one that guesses at pricing.

    Key Takeaways

  • Fuzzy search across titles, tags, and notes makes natural language queries work.
  • Every claim needs a citation — this is what makes AI-assisted research trustworthy.
  • Structured research briefs (overview, findings, gaps, actions) are more useful than freeform answers.
  • Cross-referencing bookmarks with tasks connects research to real work.
  • This is chapter 4 of Build Your AI Assistant with Claude.

    Get the full hands-on course — free during early access. Build the complete system. Your projects become your portfolio.

    View course details