Region

System Prompts prompts

Production-grade system prompts for assistants and apps.

9 prompts
Agents & Automation ⚙ AGENT

Customer Support Agent — Production System Prompt

A battle-tested system prompt template for a customer support agent: scope limits, tone, escalation rules, refund policy handling, and prompt-injection defenses.

GPT-4o✓ Claude Sonnet 4.5
★ 156⧉ 1320◌ 0LLM Atlas Team · 2mo ago
Agents & Automation ⚙ AGENT

RAG Assistant System Prompt (Grounded, With Citations)

System prompt for retrieval-augmented assistants that actually stays grounded: strict source discipline, inline citations, and honest "not in the docs" answers.

✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 134⧉ 1105◌ 0LLM Atlas Team · 2mo ago
Agents & Automation ⚙ AGENT

Structured JSON Extraction System Prompt

System prompt for reliable JSON extraction pipelines: strict schema adherence, explicit null semantics, and no chatty preambles ever.

✓ GPT-4oClaude Haiku 4.5
★ 88⧉ 705◌ 0LLM Atlas Team · 2mo ago
Agents & Automation ⚙ AGENT

System Prompt Red-Team Review

Attacks your system prompt before users do: finds instruction/data confusion, conflicting rules, missing refusal paths, and override ambiguities — and ships concrete attack strings to test.

GPT-5Claude Opus 4.5
★ 47⧉ 335◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

LLM-as-Judge — Pairwise Comparison with Bias Controls

A pairwise evaluation judge with the biases engineered out: criterion-by-criterion verdicts, position and length bias countermeasures, and evidence quotes for every judgment.

✓ GPT-5Claude Opus 4.5
★ 44⧉ 318◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

Support Ticket Triage & Draft Reply Engine

Processes inbound support tickets into structured triage JSON plus a grounded draft reply — priority, sentiment, churn and safety flags, and injection-proof handling of ticket content.

Claude Sonnet 4.5✓ Claude Haiku 4.5
★ 40⧉ 289◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

RAG Groundedness Verifier (Claim-by-Claim)

The verification stage of a RAG pipeline: decomposes an answer into atomic claims and labels each SUPPORTED, CONTRADICTED, or NOT_FOUND against the sources — inference is not support.

✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 42⧉ 301◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

LLM-as-Judge — Binary Rubric Scoring

Scores a single output against a rubric of binary pass/fail criteria instead of a mushy 1–10 scale — every verdict backed by a quote, unjudgeable criteria refused.

GPT-5Gemini 2.5 Flash
★ 35⧉ 242◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

RAG Query Rewriter & Decomposer

The retrieval front-end for a RAG pipeline: resolves pronouns from chat history, splits multi-part questions, extracts metadata filters, and never tries to answer.

✓ Claude Haiku 4.5Gemini 2.5 Flash
★ 38⧉ 275◌ 0LLM Atlas Team · 1mo ago
LLM Atlas

A free map of prompts that actually work — tested on real models, starred by real people.

© 2026 LLM AtlasPrompts default to CC0 unless stated.