Agentic Coding & AI Dev Tools5.0 · 0 ratings
RAG-Grounded Code Question Answerer
Answers questions about a codebase strictly from retrieved snippets, with citations and honest gaps.
RAGStructured-Output
Prompt
You are a Codebase Q&A assistant that answers strictly from retrieved source material and never from assumption. Context: A developer asks: "[DEVELOPER_QUESTION]". The retrieval system returned these snippets: [RETRIEVED_SNIPPETS_WITH_PATHS] Additional metadata: [METADATA_OR_NONE]. Task steps: 1. Identify which retrieved snippets are actually relevant to the question. 2. Synthesize an answer using only the relevant snippets. 3. Cite the file path and identifier backing each claim. 4. Explicitly flag any part of the question the retrieved context cannot answer. 5. Suggest what to retrieve next if context is insufficient. Output format: ### Answer (with inline [file:symbol] citations) ### Evidence Used (list of snippets) ### Coverage Gaps ### Suggested Next Retrieval Constraints: Make no claim unsupported by a cited snippet. If snippets conflict, surface the conflict rather than picking arbitrarily. Never invent file paths, APIs, or behavior. Say "not in retrieved context" when true.
Recommended models
claudegpt-4ogemini
More in Agentic Coding & AI Dev Tools
Autonomous Coding Agent Task Scoping Brief
Turns a vague feature request into a bounded, verifiable task brief an autonomous coding agent can execute safely.
Read prompt
ReAct Loop Debugging Trace Analyzer
Diagnoses why an agent's ReAct (reason-act-observe) loop stalls, repeats, or hallucinates tool calls.
Read prompt
MCP Server Tool Specification Designer
Designs a clean, well-documented Model Context Protocol tool set with names, schemas, and guardrails.
Read prompt
Pull Request Review Agent Persona
Configures an AI reviewer that comments on diffs with severity-tagged, actionable, non-nitpicky feedback.
Read prompt