Appendix A: Best practice reference

This appendix provides a complete reference of all best practices defined in the Agentic AI Lens, organized by pillar and focus area.

Operational excellence

AGENTOPS01: How do you establish operational practices for agentic AI systems?

AGENTOPS02: How do you manage prompt and configuration lifecycle?

AGENTOPS03: How do you manage agent lifecycle and deployment processes?

AGENTOPS04: How do you establish tool integration and management practices?

AGENTOPS05: How do you implement comprehensive observability and monitoring for agentic systems?

AGENTOPS06: How do you implement testing, evaluation, and validation frameworks?

AGENTOPS07: How do you establish operational recovery and consumption monitoring?

Security

AGENTSEC01: How do you secure agentic memory and securely manage state between agents?

AGENTSEC02: How do you control and secure agent tool usage?

AGENTSEC03: How do you manage agent identities, permissions, and prevent privilege escalation?

AGENTSEC04: How do you support agent goal alignment and prevent manipulation?

AGENTSEC05: How do you implement observability and prevent repudiation?

AGENTSEC06: How do you secure multi-agent orchestration and coordination?

AGENTSEC07: How do you protect human oversight from manipulation and detect rogue agents?

AGENTSEC08: How do you validate and secure agent inputs and outputs?

AGENTSEC09: How do you perform vulnerability scanning and penetration testing for agentic AI systems?

Reliability

AGENTREL01: How do I develop reliable agentic systems?

AGENTREL02: How do you develop agentic systems that reliably execute tasks with predictable outcomes?

AGENTREL03: How do you support agent memory and state remaining reliably accessible throughout the agent lifecycle?

AGENTREL04: How do you orchestrate multi-agent systems to reliably execute tasks?

AGENTREL05: How do you implement reliable agent cognition that accesses the right data at the right time?

AGENTREL06: How do agents integrate effectively with existing systems without impacting the reliability of established processes?

AGENTREL07: How do fault tolerant agent systems recover?

AGENTREL08: How do agents determine when and where graceful degradation is appropriate?

Performance efficiency

AGENTPERF01: How do you plan strategically for agent performance and establish measurement practices?

AGENTPERF02: How do you optimize core agent processing and cognitive pipelines?

AGENTPERF03: How do you optimize memory management, context windows, and retrieval-augmented generation?

AGENTPERF04: How do you achieve efficient communication and protocol usage across agent interactions?

AGENTPERF05: How do you optimize workflow orchestration and multi-agent collaboration for performance?

AGENTPERF06: How do you optimize tool integrations and framework usage for agent performance?

AGENTPERF07: How do you manage multitenant performance isolation and optimize resource utilization?

Cost optimization

AGENTCOST01: How do you optimize agent reasoning and execution costs?

AGENTCOST02: How do you optimize agent model invocation and token consumption costs?

AGENTCOST03: How do you manage agent memory and state costs efficiently?

AGENTCOST04: How do you optimize agent tool invocation?

AGENTCOST05: How do you implement cost attribution?

AGENTCOST06: How do you optimize agent discovery registry and deployment costs?

AGENTCOST07: How do you establish agent cost governance and continuous optimization?

Sustainability

AGENTSUS01: How do you build sustainable and repeatable frameworks for managing compute, memory, and other shareable agent resources?

AGENTSUS02: How do I establish sustainable frameworks for agent dependencies?

AGENTSUS03: How do I establish durable patterns for agent interactions with users and business processes?

Summary