research-article

Research Article

Given a topic, discovers what the state of the art is by searching broadly, triaging sources, deep-reading the strongest ones, and synthesizing the field. The output is a research brief that becomes the input to /create-article, so the writing step can focus on craft rather than discovery.

Prerequisites

• Topic: The subject to investigate (e.g., "vector databases", "test-time compute in LLMs", "CRDTs for collaborative editing")
• Scope (optional but recommended): The specific angle or question, time bounds (e.g., "last 2 years"), and what "state of the art" means here (best accuracy, fastest, most adopted, most recent breakthrough)
• Intended audience (optional): Helps calibrate which sources and framing are relevant
• Seed sources (optional): Any URLs, papers, or files the user already knows matter

Steps

1. Clarify the topic and scope. State the specific research question in one sentence. Define what "state of the art" means for this topic (top benchmark score, dominant method, industry standard, latest breakthrough). Note any time bounds or constraints.
2. Search broadly. Search multiple source types (see Search Strategy below). Start with surveys, review papers, and benchmark leaderboards to map the field quickly before going deep.
3. Build a candidate source list. For each result, capture title, URL, type, year, and a one-line relevance note. Prioritize primary sources (papers, official docs, benchmarks) over secondary commentary, but keep influential blog posts and talks that shape practice.
4. Triage. Rank candidates by relevance, credibility, and recency. Score credibility from concrete authority signals, not impressions:
   • Papers: a peer-reviewed venue and citations beat an uncited preprint; note the sample size.
   • Reports and standards: the publishing organization and its methodology (for example NBER, DORA, OpenTelemetry).
   • Repositories: stars, forks, and recent activity, and flag a small or obscure repo even when it states a useful number.
   • Vendor content: a company with a product in the category is self-interested; keep it, but label it and never present it as independent.
   • Blogs: a named author and no sales pitch; a services-company SEO post with no author is Weak. Record an authority signal and a credibility rating (Strong, Moderate, or Weak, with a qualifier such as "Strong (small n)") for every source you keep. Keep the strongest 8-15 to deep-read. Drop outdated or low-quality sources, but record why so the exclusion is deliberate.
5. Deep-read the top sources. Fetch and read each one. Extract: the problem it addresses, its approach, its key results and numbers, and how it compares to prior work. Verify claims against the source rather than paraphrasing from memory or a summary.
6. Map the field. Group the sources into the main approaches. Identify what currently defines the state of the art (top scores, dominant technique, widely adopted standard). Note where the field agrees and where it actively disagrees.
7. Surface gaps and open questions. What is unsolved, contested, or just emerging? These tensions are what make an article worth reading.
8. Synthesize. Write the state-of-the-art summary. Recommend an angle for the article: the single core insight or argument the research best supports.
9. Produce the research brief using the output format below.