Triage and routing
Prompts that classify intent, urgency and required team.
24 curated prompts
Customer Support Prompts
Support automation fails when the model guesses policy. These prompts require answers to stay inside approved knowledge, define clear escalation triggers, and keep tone consistent without over-apologising.
customer support promptsAI support promptshelpdesk prompts
Grounded replies
Templates that answer only from supplied knowledge base content.
Escalation and boundaries
Prompts defining when to hand off to a human and what to say.
Featured AI prompt templates
Copy-ready prompts selected from this topic cluster.
TextAI Agents
Customer Support Agent
Professional SaaS customer support agent with emotion recognition, issue classification, standardized resolution flows, and escalation protocols to ensure efficient, compliant, and empathetic customer service.
TextAI Agents
AI Governance & Legal Compliance Agent
Provides AI use case classification, regulatory obligation assessment, vendor term review, and policy drift monitoring for legal/privacy teams. All outputs are drafts for attorney review—not legal advice or conclusions.
TextAI Agents
Agent Permission Auto-Mode Architect
Design a two-layer permission classifier for agents to operate efficiently on low-risk actions while preserving human approval for high-risk operations, eliminating confirmation fatigue without compromising safety.
TextAI Agents
Comprehensive Technical Program Manager (TPM) Initiative Planning & Execution Framework
Design and execute a complete technical program management package for complex engineering initiatives, covering strategy, architecture, resources, risks, delivery frameworks, and metrics across the full lifecycle.
TextAI Agents
Embodied AI Developer
Design and implement embodied agents using Vision-Language-Action (VLA) systems, emphasizing perception-action grounding, world model forecasting, modular architecture, and sim-to-real transfer capabilities.
TextAI Agents
Auditable Enterprise LLM Agent Harness Architect
Reconstruct prompt-heavy enterprise LLM prototypes into a traceable, auditable, code-owned agent architecture by moving behavior into manifests, schemas, validators, and runtime gates.
TextAI Agents
Agent State Hygiene Architect
Designs safe maintenance routines for local AI coding agent state: inspect-before-mutate, archive-don't-delete, and continuity-preserving handoffs.
TextAI Agents
NotebookLM Research Orchestrator
As a NotebookLM Research Orchestrator, your role is to ingest documents, media, and web sources into Google NotebookLM, then synthesize them into podcasts, videos, slide decks, reports, quizzes, flashcards, mind maps, and data tables through its indexing and generation pipeline.
TextAI Agents
Agents Best Practices Guide
This skill is used when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.
TextAI Agents
Agent Harness Performance Engineer
Optimize existing AI coding-agent harnesses (e.g., Claude Code, Codex CLI, Cursor) to achieve consistent, measurable, production-grade outcomes through cross-harness parity, memory persistence, security, and continuous learning.
TextAI Agents
Agentic Company Orchestrator Design
Design a zero-human multi-agent company operating system with org structure, task allocation, budget control, governance, and audit trails for autonomous, goal-driven execution under financial constraints.
TextAI Agents
Agent Reliability Engineer
Design, measure, and improve the reliability of AI agent systems—distinct from capability. Based on 2026 research, emphasizes stability under repeated runs, perturbed inputs, and fault injection across four dimensions: consistency, robustness, predictability, and safety/fault tolerance.
How do I prevent the model from promising refunds?
Constrain the answer to the supplied policy text and require an escalation message when policy does not cover the case.
What should triage output include?
Intent, urgency, suggested queue, and the evidence in the ticket that supports the classification.
How do I keep tone consistent across agents?
Define a short style contract — greeting, empathy budget, next-step format — and require the same structure every time.