AI Agent Prompts
Agent Retrieval Strategy Designer
Design how an agent finds, verifies, ranks, and cites external knowledge across structured and unstructured sources.
FreeClaudeChatGPT
Best for
AI teams building agents that must answer or act from current, attributable, and access-controlled organizational knowledge.
Suitable LLM groups
FrontierReasoning
Prompt
You are a retrieval systems architect who specializes in grounding AI agents with reliable, permission-aware evidence.
Inputs:
1. Agent questions and decisions that require knowledge: {{knowledge_tasks}}
2. Available sources and their authority: {{data_sources}}
3. Content volume, formats, languages, and update rates: {{content_profile}}
4. Access controls, citation, freshness, and latency requirements: {{requirements}}
5. Current retrieval problems or baseline results: {{current_problems}}
Do the following:
1. Classify query types and map each to authoritative sources, retrieval methods, metadata filters, and acceptable fallback sources.
2. Design ingestion, parsing, chunking, metadata, indexing, freshness, deletion, and permission-propagation rules for each source type.
3. Define query rewriting, hybrid retrieval, reranking, deduplication, evidence packing, citation validation, and conflict-resolution behavior.
4. Specify when the agent must ask a clarifying question, run another retrieval pass, consult a structured system, or abstain because evidence is insufficient.
5. Deliver a retrieval decision table, ranking formula or rubric, source-conflict policy, evaluation set design, and phased implementation plan with precision, recall, freshness, latency, and citation metrics.How to use
- List sources in authority order, including systems of record.
- Describe query types and expected user decisions.
- State access, freshness, citation, and latency requirements.
- Create evaluation questions from real search failures.
Example input
Knowledge tasks: Answer HR policy questions and guide managers through leave requests. Sources: HRIS fields, approved policy PDFs, country addenda, internal FAQ pages, and archived chat posts. Profile: 6,500 pages in English and German, monthly policy updates, and daily HRIS changes. Requirements: country and role-based access, citations for policy answers, content freshness under 24 hours, and p95 retrieval under 1.5 seconds. Problems: old chat advice outranks policy documents and German compound terms retrieve poorly.
Example output
The strategy routes employee-specific balances to the HRIS, policy interpretation to approved PDFs and country addenda, and uses FAQs only for explanatory support. Archived chat is excluded from authoritative answers. Hybrid BM25 and multilingual embeddings retrieve candidates, followed by a reranker weighted toward authority, jurisdiction, effective date, and exact entitlement type. Conflicting policy versions trigger an effective-date check; unresolved conflicts lead to abstention and HR escalation. Evaluation includes German compounds, permission boundaries, stale documents, and policy-version conflicts.
Customization tips
- — Add jurisdiction and effective-date metadata.
- — Define separate retrieval paths for structured facts and prose.
- — Exclude informal sources from authoritative decisions.
- — Test multilingual and permission-filtered retrieval explicitly.
Tags
#agent-retrieval#rag-design#knowledge-grounding#citation-quality#hybrid-search
FAQ
What is this prompt for?
It creates an end-to-end evidence retrieval strategy for an agent, from ingestion and permissions through ranking, citation, and abstention.
How should I customize it?
Provide source authority, content formats, update schedules, access rules, query examples, latency goals, and known retrieval failures.
Are there any limitations?
The design cannot compensate for missing, contradictory, or poorly governed source content; document owners must resolve authoritative gaps.
How is it different from a basic prompt?
It maps query classes to sources and defines ingestion, hybrid ranking, evidence packing, conflict handling, clarification, and measurable retrieval evaluation.
Related Prompts
All AI Agents prompts →Free
Agent Memory Architecture Planner
Design a practical memory system for an AI agent, including what to retain, how to retrieve it, and when to forget it.
ClaudeChatGPT
#agent-memory#retrieval-design#context-management
Free
Agent Deployment Readiness Reviewer
Run a structured pre-production review across product value, evaluation, security, operations, fallbacks, and rollout controls.
ClaudeChatGPT
#agent-deployment#production-readiness#launch-review
Free
Agent Task Decomposition Planner
Breaks a broad goal into a structured set of sub-tasks an AI agent can execute step by step, with clear success criteria and handoff points for human review.
ClaudeChatGPT
#ai-agents#task-planning#agent-architecture
Related Skills
Agent Systems & LLM WorkflowsFree
RAG Retrieval Quality Engineer
Design and evaluate RAG retrieval with chunking, metadata, hybrid search, reranking, citations, freshness, and failure analysis.
ClaudeChatGPTCursor
#RAG#retrieval quality#vector search
Related Articles
Article · AI Workflows
What is RAG, and do I need it for my AI project?
Retrieval-augmented generation connects AI answers to external documents or knowledge sources. It helps when the model needs current or private information.
Jul 9, 20268 min read
Read What is RAG, and do I need it for my AI project? →