Explore Prompts

Design an extractor for structured data: schema.org/JSON-LD, OpenGraph, and meta tags. Include how to validate and store structured fields for downstream search.

Plan how to use sitemaps and RSS/Atom feeds to discover content efficiently. Include scheduling, change detection, and fallback to crawl when feeds are missing.

Design a URL frontier with ranking signals: relevance to query, freshness, link context, domain trust, and duplication risk. Include pseudocode-level description and metrics.

Design a politeness policy: per-domain rate limiting, crawl-delay handling, time windows, and exponential backoff. Include instrumentation to prove compliance.

Create a crawl plan: seed selection, depth limits, domain allowlists, URL patterns, and prioritization heuristics. Include a method to estimate crawl cost and coverage.

Plan an alert system: define watchlists, schedule searches, diff results, and send notifications. Include dedupe, false positive controls, and ‘significance’ scoring.

Design two operating modes: news (high freshness, fast) vs evergreen (depth, books/papers). Include different source scoring, caching, and output formats.

Design cross-language research: translate queries, search in multiple languages, normalize entities, and merge evidence. Include how to detect mistranslations and preserve proper nouns.

Design an entity extraction + graph pipeline: NER, entity resolution, relationship extraction, and graph storage. Include queries to answer “who is connected to what.”

Create a method to cluster collected sources into themes: embeddings, hierarchical clustering, and label generation. Include how to keep clusters stable across updates.

Design an evidence table format (CSV/JSON): each claim mapped to sources, snippets, dates, and reliability scores. Include how to generate it automatically from the pipeline.

Create a standard research brief template: executive summary, key findings, evidence table, open questions, and citations. Include options for analyst vs layperson formats.