Explore Prompts

Design a bias-control policy: require diverse sources (geography, institution, viewpoint), detect monocultures, and add “missing perspective” prompts. Include reporting in outputs.

Create a workflow for conflicting sources: identify disagreements, categorize (definition vs data vs interpretation), and present balanced conclusions with confidence levels.

Design a claim extraction step: identify factual assertions, attach supporting evidence, and flag unsupported claims. Include scoring for evidence strength and contradictions.

Design a citation system: store supporting snippets, anchor to URL + section/page, and enforce quote-length limits. Include how to generate citations in final responses automatically.

Draft a policy for paywalled/restricted content: detect paywalls, avoid bypass, rely on accessible sources, and suggest user-provided excerpts when needed. Include user messaging guidelines.

Create a plan for handling PDFs: downloading, parsing text, capturing page numbers, and generating citations. Include limitations and a quality checklist for extraction accuracy.

Design a content extraction module: boilerplate removal, main-content detection, metadata extraction (title/author/date), and language detection. Include fallback strategies for messy pages.

Plan a resilient fetching layer: retries, exponential backoff, timeouts, caching, and content-type handling. Include how to avoid hammering sites and manage 429/503 responses.

Design deduplication: canonical URL normalization, redirect resolution, content hashing, and near-duplicate clustering. Include evaluation metrics for dedupe accuracy.

Design a freshness strategy for research: recency-aware search, change detection, and update alerts. Include how to present “as of” dates and avoid outdated claims.

Create a source scoring rubric: domain trust, author expertise, citations, recency, and conflicts of interest. Output a weighted scoring model and how to tune it per domain.

Design a query planning module that expands a user question into search operators, sub-queries, and entity lists. Include multilingual support and query diversification strategies.