[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-how-to-prompt-amazon-nova-2-for-moderation-en":3,"article-related-how-to-prompt-amazon-nova-2-for-moderation-en":31,"series-ai-agent-84aa8372-0d76-4040-9bef-3402b952f6d2":76},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":23,"views":27,"created_at":28,"published_at":29,"topic_cluster_id":30},"84aa8372-0d76-4040-9bef-3402b952f6d2","how-to-prompt-amazon-nova-2-for-moderation-en","How to Prompt Amazon Nova 2 for Moderation","\u003Cp data-speakable=\"summary\">Use Amazon Nova 2 Lite on Bedrock to moderate content with structured prompts.\u003C\u002Fp>\u003Cp>This guide is for developers who need a practical moderation workflow without fine-tuning. After following it, you will have a prompt pattern for Amazon Nova 2 Lite, a JSON or XML response format your app can parse, and a simple way to test moderation against your own policy.\u003C\u002Fp>\u003Cp>The approach follows the \u003Ca href=\"\u002Ftag\u002Faws\">AWS\u003C\u002Fa> blog post on \u003Ca href=\"https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fprompting-amazon-nova-2-for-content-moderation\u002F\">Prompting Amazon Nova 2 for content moderation\u003C\u002Fa> and the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Famazon-science\u002FMLCommons-AILuminate\">MLCommons AILuminate repository\u003C\u002Fa>, but you can swap in your own policy categories. It works well when you want to update rules by editing prompts instead of retraining a model.\u003C\u002Fp>\u003Ch2>Before you start\u003C\u002Fh2>\u003Cul>\u003Cli>An \u003Ca href=\"https:\u002F\u002Faws.amazon.com\u002F\">AWS account\u003C\u002Fa>\u003C\u002Fli>\u003Cli>Access to \u003Ca href=\"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002F\">Amazon Bedrock documentation\u003C\u002Fa> and a Bedrock-enabled AWS Region\u003C\u002Fli>\u003Cli>Permission to invoke Amazon Nova 2 Lite in Bedrock\u003C\u002Fli>\u003Cli>AWS CLI v2 installed, if you want to test from the terminal\u003C\u002Fli>\u003Cli>Node.js 20+ or Python 3.11+, if you are building an app integration\u003C\u002Fli>\u003Cli>Your moderation policy text, or the AILuminate v1.1 taxonomy as a starting point\u003C\u002Fli>\u003Cli>An AWS access key and secret access key, if you are not using IAM roles\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Step 1: Define your moderation policy\u003C\u002Fh2>\u003Cp>Goal: create a policy source of truth that the model can follow consistently. Start with the MLCommons AILuminate categories if you want a ready-made taxonomy, or replace them with your own rules for marketplace listings, community posts, or support chats.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779740754913-zutd.png\" alt=\"How to Prompt Amazon Nova 2 for Moderation\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>Write each category in short, explicit language. Include a one-line definition for every label, plus a catch-all no-violation code such as C0. Keep the wording stable so you can reuse the same prompt structure as your policy evolves.\u003C\u002Fp>\u003Cp>Verification: you should see a compact policy list with clear labels, definitions, and a no-violation code that your application can render or store.\u003C\u002Fp>\u003Ch2>Step 2: Assemble a structured prompt\u003C\u002Fh2>\u003Cp>Goal: produce a prompt that forces predictable output for downstream automation. Use XML or JSON when your app needs a parseable response, and place the policy, the content to moderate, and the output contract in separate sections.\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779740767991-3che.png\" alt=\"How to Prompt Amazon Nova 2 for Moderation\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cpre>\u003Ccode>User: You are a text content moderator that detects policy violations and explains the decision.\nReturn ONLY JSON with this shape:\n{\n  \"policy_violation\": \"Yes or No\",\n  \"category_list\": [\"category codes\"],\n  \"explanation\": \"reason\"\n}\nIf there is no violation, use \"C0\".\n[POLICY]\n{{policy definitions}}\n[TEXT]\n{{content to moderate}}\u003C\u002Fcode>\u003C\u002Fpre>\u003Cp>Verification: you should see a response that is valid JSON, contains only the fields you asked for, and uses C0 when the text is safe.\u003C\u002Fp>\u003Ch2>Step 3: Send the prompt to Amazon Nova 2 Lite\u003C\u002Fh2>\u003Cp>Goal: run the moderation prompt against Amazon Nova 2 Lite in Amazon Bedrock. Use the default inference settings from the AWS guidance first, then adjust only after you confirm the output quality for your content type.\u003C\u002Fp>\u003Cp>For throughput-focused systems, start with temperature 0.7 and top-p 0.9, and test reasoning mode off if latency matters more than explanation depth. Keep the request payload small and send only the policy needed for the current moderation decision.\u003C\u002Fp>\u003Cp>Verification: you should see a model response with a violation flag, one or more category codes, and a short explanation that matches the input text.\u003C\u002Fp>\u003Ch2>Step 4: Parse and route the moderation result\u003C\u002Fh2>\u003Cp>Goal: turn the model output into an application decision. Map the response to actions such as allow, flag, remove, or escalate, and make the mapping deterministic in your backend.\u003C\u002Fp>\u003Cp>For example, treat \"Yes\" plus one or more non-C0 categories as a moderation hit, then route the item to review or automatic removal. If the output is \"No\" with C0, allow the content and log the decision for audit and tuning.\u003C\u002Fp>\u003Cp>Verification: you should see your app take the correct action for both safe and unsafe sample inputs, with the decision stored in logs or a moderation queue.\u003C\u002Fp>\u003Ch2>Step 5: Test with your own examples\u003C\u002Fh2>\u003Cp>Goal: validate the prompt against realistic user-generated content before you ship. Build a small test set that includes obvious violations, borderline cases, and clean examples so you can measure false positives and false negatives.\u003C\u002Fp>\u003Cp>Run the same prompt against each sample and compare the model output with your expected label. If you use few-shot examples, add only the examples that improve the specific failure case you observed.\u003C\u002Fp>\u003Cp>Verification: you should see the model classify your test set in a way that matches your policy, with borderline cases reviewed by a human before release.\u003C\u002Fp>\u003Ch2>Common mistakes\u003C\u002Fh2>\u003Cul>\u003Cli>Mixing policy text and content text in one block. Fix: separate them with clear tags or JSON keys so the model can distinguish instructions from the item being moderated.\u003C\u002Fli>\u003Cli>Leaving the output format vague. Fix: specify exact fields, allowed values, and whether the response must be JSON, XML, or free-form text.\u003C\u002Fli>\u003Cli>Using one prompt for every policy change. Fix: version your policy text and update the prompt when rules change, instead of retraining the model for every edit.\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>What's next\u003C\u002Fh2>\u003Cp>Once the basic flow works, extend it with evaluation sets, human review for edge cases, and policy-specific thresholds so you can tune moderation quality over time.\u003C\u002Fp>","Use Amazon Nova 2 Lite on Bedrock to moderate content with structured prompts.","aws.amazon.com","https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fprompting-amazon-nova-2-for-content-moderation\u002F",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779740754913-zutd.png","ai-agent","en","dc3b0a4a-5aa8-45f5-8c8c-076d5ee99950",[17,18,19,20,21,22],"Amazon Nova 2 Lite","Amazon Bedrock","content moderation","prompt engineering","JSON","XML",[24,25,26],"Structured prompts are best when downstream systems need parseable moderation output.","Few-shot examples help Nova 2 Lite learn your policy format and decision style.","You can update moderation rules by editing prompts instead of retraining a model.",5,"2026-05-25T20:25:30.835402+00:00","2026-05-25T20:25:30.828+00:00","a9bee732-b07c-4e5b-a0e6-3048577e32a7",{"tags":32,"relatedLang":35,"relatedPosts":39},[33],{"name":20,"slug":34},"prompt-engineering",{"id":15,"slug":36,"title":37,"language":38},"how-to-prompt-amazon-nova-2-for-moderation-zh","怎麼用 Amazon Nova 2 做審核","zh",[40,46,52,58,64,70],{"id":41,"slug":42,"title":43,"cover_image":44,"image_url":44,"created_at":45,"category":13},"d53bdddf-05eb-4eca-b53b-8439ee35acda","codex-micro-macropad-ai-control-deck-en","Codex Micro turns a macropad into an AI control deck","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1784291596349-nxpa.png","2026-07-17T12:32:45.841021+00:00",{"id":47,"slug":48,"title":49,"cover_image":50,"image_url":50,"created_at":51,"category":13},"ae8b2df7-05be-4377-8fa8-00856625839e","automate-web3-grant-screening-ai-scoring-en","Automate Web3 Grant Screening With AI Scoring","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1784187177735-071f.png","2026-07-16T07:32:24.390132+00:00",{"id":53,"slug":54,"title":55,"cover_image":56,"image_url":56,"created_at":57,"category":13},"5115e111-8a16-41df-a00b-529be3f2c3c9","anthropic-models-build-better-agent-endurance-en","Anthropic Models: Build Better Agent Endurance","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1784102584376-pw9z.png","2026-07-15T08:02:32.41246+00:00",{"id":59,"slug":60,"title":61,"cover_image":62,"image_url":62,"created_at":63,"category":13},"6a959f48-0c84-4717-a858-d02c8bd26fce","googles-gemini-enterprise-agent-platform-cloud-service-en","Google’s Gemini Enterprise Agent Platform makes agents a cloud servic…","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1784059365473-8gbb.png","2026-07-14T20:02:25.392208+00:00",{"id":65,"slug":66,"title":67,"cover_image":68,"image_url":68,"created_at":69,"category":13},"3f5dcc12-bb78-4102-817b-f08f9adbe974","workbuddy-harness-engineering-matters-more-than-model-size-en","WorkBuddy Proves Harness Engineering Matters More Than Model Size","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783987381886-gvmo.png","2026-07-14T00:02:31.980136+00:00",{"id":71,"slug":72,"title":73,"cover_image":74,"image_url":74,"created_at":75,"category":13},"9c82943c-4f7b-4ada-8498-ce42b951a381","perplexity-teammate-coding-agent-strategy-en","Perplexity should build Teammate as a coding agent, not a copilot","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1783589576551-x3my.png","2026-07-09T09:32:26.11108+00:00",[77,82,87,92,97,102,107,112,117,122],{"id":78,"slug":79,"title":80,"created_at":81},"03db8de8-8dc2-4ac1-9cf7-898782efbb1f","anthropic-claude-ai-agent-task-automation-en","Anthropic's Claude AI Agent: A New Era of Task Automation","2026-03-25T16:25:06.513026+00:00",{"id":83,"slug":84,"title":85,"created_at":86},"045d1abc-190d-4594-8c95-91e2a26f0c5a","googles-2026-ai-agent-report-decoded-en","Google’s 2026 AI Agent Report, Decoded","2026-03-26T11:15:23.046616+00:00",{"id":88,"slug":89,"title":90,"created_at":91},"e64aba21-254b-4f93-aa21-837484bb52ec","kimi-k25-review-stronger-still-not-legend-en","Kimi K2.5 review: stronger, still not a legend","2026-03-27T07:15:55.385951+00:00",{"id":93,"slug":94,"title":95,"created_at":96},"30dfb781-a1b2-4add-aebe-b3df40247c37","claude-code-controls-mac-desktop-en","Claude Code now controls your Mac desktop","2026-03-28T03:01:59.384091+00:00",{"id":98,"slug":99,"title":100,"created_at":101},"254405b6-7833-4800-8e13-f5196deefbe6","cloudflare-100x-faster-ai-agent-sandbox-en","Cloudflare’s 100x Faster AI Agent Sandbox","2026-03-28T03:09:44.356437+00:00",{"id":103,"slug":104,"title":105,"created_at":106},"04f29b7f-9b91-4306-89a7-97d725e6e1ba","openai-backs-isara-agent-swarm-bet-en","OpenAI backs Isara’s agent-swarm bet","2026-03-28T03:15:27.849766+00:00",{"id":108,"slug":109,"title":110,"created_at":111},"3b0bf479-e4ae-4703-9666-721a7e0cdb91","openai-plan-automated-ai-researcher-en","OpenAI’s plan for an automated AI researcher","2026-03-28T03:17:42.312819+00:00",{"id":113,"slug":114,"title":115,"created_at":116},"fe91bce0-b85d-4efa-a207-24ae9939c29f","harness-engineering-ai-agent-reliability-2026","Harness Engineering: From Bridle to Operating System, The Missing Link in AI Agent Reliability","2026-03-31T06:36:55.648751+00:00",{"id":118,"slug":119,"title":120,"created_at":121},"7a09007d-820f-43b3-8607-8ad1bfcb94c8","mcp-explained-from-prompts-to-production-en","MCP Explained: From Prompts to Production","2026-04-01T09:24:40.089177+00:00",{"id":123,"slug":124,"title":125,"created_at":126},"116d5ee9-a4f1-4b5a-aac5-5d035dd22bbe","amazon-bedrock-agents-multi-agent-workflows-en","Amazon Bedrock Agents Gets Multi-Agent Workflows","2026-04-01T09:30:30.197685+00:00"]