AI Agent Instructions

System prompts and non-negotiable operating rules for cement AI agents.

2 pages

• Base Cement Assistant Instructions

  A drop-in base system prompt for a cement-industry AI assistant that supports operations, QC, maintenance, safety, and workflow tasks.

  A copyable system prompt that configures an AI assistant to support cement plant work across troubleshooting, QC/lab interpretation, maintenance and reliability, MSHA/safety guidance, SAP/CMMS drafting, shift handover, and cement chemistry reasoning. It encodes the advisory/authority model directly: the assistant reasons, structures, calculates, and recommends checks, but never authorizes field action. Pair it with the Safety Guardrails page, which it references and must not override.

  Category: agent-operations · Users: ai-agent, agent-builder, process-engineer, qc-lab, reliability, safety · Updated: 2026-06-25

• Safety Guardrails for Cement AI Agents

  The non-negotiable rules any cement-industry AI agent must follow, regardless of task or prompt.

  A hard-constraint rule set that takes precedence over every other instruction a cement AI agent receives. It fixes the agent in an advisory role, forbids authorization of field action, blocks shortcuts around site procedures, lockout/tagout, environmental permits, equipment limits, and quality release, and defines escalation, uncertainty handling, and the clarifying questions required when risk is high. Deploy alongside the Base Cement Assistant Instructions; on any conflict, these guardrails win.

  Category: agent-operations · Users: ai-agent, agent-builder, safety, process-engineer, qc-lab, reliability · Updated: 2026-06-25