Explore Prompts

Design a UI: inline citations, hover previews, source quality badges, and ‘expand to passage’. Include keyboard flows and accessibility specs (WCAG). Output wireframes and event schema.

Specify constrained modes with scope limits, consent prompts, guideline links, and mandatory citation density. Provide refusal templates and domain-specific disclaimers.

Create a cross-lingual flow: detect language, translate queries, use multilingual embeddings, and cite in user language while preserving original quotes. Provide locale heuristics and typography rules.

Draft defenses for tool-using agents: content sanitization, domain allowlists, URL reputation, and read-only sandboxes. Provide red-team prompts and pass/fail gates.

Design a time-decay model that boosts fresh, authoritative sources. Include publisher priors, sitemap/news bias, and re-crawl triggers. Output evaluation with time-split test sets.

Create a compression stage with map-reduce summaries, selective citation carry-through, and entropy-based token pruning. Provide metrics (coverage, faithfulness) and an ablation plan.

Specify a KG-augmented RAG: entity/link extraction → KG lookup → vector recall → late fusion ranking. Provide ranking features (entity overlap, path length), and a sample Gremlin/SPARQL query pack.

Design a debate pattern: one agent argues a thesis, another refutes with sources, a judge agent scores evidence and drafts a balanced synthesis. Provide rubric, tie-breaker rules, and output template.

Build a verifier that detects agreement/contradiction between sources. Define stance labels, entailment thresholds, and escalation rules to human review. Output a confusion matrix target and fallback messaging.

Create an algorithm that decomposes complex prompts into sub-questions, selects tools per hop, and merges evidence. Provide pseudocode, scoring for hop-utility, and examples for science, law, and finance queries.

Design a retrieval pipeline that enforces source-anchored answers. Include chunking policy, hybrid retrieval (BM25+embeddings), quote extraction with line/section anchors, and footnote rendering. Output a reference implementation outline and QA checklist.

Act as a principal architect. Specify a next-gen chat research system with roles (Planner, Retriever, Synthesizer, Verifier), message schemas, tool contracts, and failure handling. Deliver a C4 diagram, sequence charts for 1/3/5-hop queries, and a minimal API spec for each role.