Better prompts.
Useful results.

Act as an AI agent gateway architect. Design a least-privilege Model Context Protocol gateway for [tool inventory] across [cloud providers]. Use [identity provider] and [policy engine]. Keep production tools read-only and route human and agent access through [gateway]. Return policy examples for [principal] and tool groups.

Act as a security architect. Design a zero trust AI agent authentication plan using X.509 PKI and MCP. Replace placeholders: [AGENT_NAME], [MCP_SERVER], [TRUSTED_CA], [TOKEN_AUDIENCE], [OCSP_RESPONDER], [KEYCLOAK_VERSION]. Include user auth, agent to agent, and MCP auth layers. Add signed envelopes, delegation assertions, RFC 8693 audience scoped tokens, and OCSP checks. Flag prerequisites and verification steps.

Investigate the recent performance incident on {database_name} occurring around {timestamp}. Provide: (1) current blocking chains and wait types, (2) likely root cause with prioritized remediation steps, (3) a ready‑to‑use Jira ticket summary and description assigned to the on‑call engineer for {team}.

Explain the key differences between Claude Haiku 5.5 and previous Haiku versions, describe the primary use cases for software developers and cloud engineers, detail how Haiku 5.5 integrates with AWS services (IAM, CloudWatch, Bedrock Guardrails), and compare its pricing advantage over Haiku 4.5. Focus on practical implementation guidance for high-volume, cost-sensitive workflows.

You are a [PROFESSION] working on [PROBLEM AREA]. Using Amazon Bedrock for foundation models, Strands Agents SDK for multi‑agent orchestration, and AWS Lambda for deployment, outline a three‑agent prototype that solves [SPECIFIC USE CASE]. Include agent responsibilities, data sources (e.g., Amazon DynamoDB), and a brief flow description.

To deploy the automated remediation stack for your environment, clone the GitHub repository and configure your AWS credentials using the AWS CLI with profile [AWS_PROFILE]. Navigate to the directory and run `cdk bootstrap` followed by `cdk deploy` to provision the EventBridge rules, Lambda functions, and IAM permissions. Once deployed, invoke the test `devops-agent-timeout` function to trigger an incident, start an investigation in the DevOps Agent console, and approve the pending remediation callback in the Lambda console by sending `{'approved': true}`.

You are a [PROFESSION] working on a WordPress site. Using the newly released [FEATURE] (e.g., Abilities API Composer package, Accordion block, theme.json form styling, PHP AI Client), describe a step‑by‑step approach to [GOAL] (e.g., add role‑based capabilities, build an accessible FAQ, style a contact form, prototype an AI chatbot). Include any required tools, verification steps, and a short code snippet placeholder.

You are Qlik Answers, an enterprise AI assistant built on Amazon Bedrock. When a user asks a natural-language question, first route it through our entry layer, then determine the optimal path: if it's a simple factual lookup, use the fast path; if it requires deep analysis, engage a specialist agent. Pull relevant context from our knowledge base, analytics apps, glossaries, and documents. Generate a response that cites its sources and passes through our grounding-validation check. Ensure compliance with data sovereignty rules across regions. If a requested model isn't available in the target region, fall back to Amazon SageMaker AI and later migrate back to Bedrock.

Act as a business analyst. Draft a business case for agentic automation for {workflow_name}. Baseline data: {baseline_volume} transactions, {baseline_hours} hours per task, and {loaded_rate} loaded hourly rate. Size four value pools: released capacity, exception handling, decision quality, and maintenance resilience. Apply a realization factor of {realization_factor} to each pool. Assign owners {owner_roles}. Explicitly separate redeployed value from cash cost reduction to avoid double counting. Output a value pool table and a net annual value formula.

As a {profession}, I want to {task} using the {feature} introduced in WordPress 6.9. Provide step-by-step instructions with code examples.

I am a [profession] seeking guidance on WordPress 7.0 Beta 1. Please provide step-by-step instructions for:
1. Testing the always-iframed post editor with different block API versions
2. Setting up viewport-based block visibility controls
3. Applying per-block custom CSS using the Advanced → Additional CSS sidebar
4. Using WordPress Studio CLI v1.7.0 for automated development tasks
5. Exploring AI Experiments plugin features (excerpt generation, content summarization, image generation)
6. Updating my theme to support new textAlign and aspect ratio features
7. Configuring WordPress Playground for local development with Docker
Provide concrete examples and best practices for each task.

Please use the {{ability_name}} tool on my WordPress site to {{action_description}}. If needed, provide input parameters as JSON: {{input_json}}.