Zack Hine•
An Agentic Loop Is More Than Arrows Between Phases
A phase graph can show how work moves. It cannot explain what a loop expects.
- loops
- agent orchestration
- agent control flow
- agent bindings
- portable workflows
- react loop
- agentpm
Blog
Portable building blocks for agent systems
Writing about agent systems, reusable building blocks, and the practical work of making capabilities easier to package, version, and move across runtimes, frameworks, and ecosystems.
Zack Hine•
Portable Agents Need Portable Behavior
A system prompt can express behavior, but it is a weak packaging boundary. Portable agents need portable behavior too.
- instruction profiles
- agent behavior
- prompt engineering
- agent packaging
- agent interoperability
- agent system architecture
- agentpm
Zack Hine•
AI Agent Memory Should Be Portable Before It Is Hosted
Before memory records can move cleanly across agents, apps, runtimes, or teams, their shape has to move first.
- agent memory
- memory blueprints
- agent packaging
- agent interoperability
- durable state
- agent system architecture
- agentpm
Zack Hine•
Retrieval Context Should Be Portable Too
A retrieval corpus that only works inside one app is not portable context. It is preprocessing glue with no package boundary.
- retrieval context
- rag
- knowledge packages
- agent packaging
- agent interoperability
- portable context
- agentpm
Zack Hine•
AI Agent Skills Are Know-How, Not Just Prompt Files
A tool can expose an action. It cannot tell an agent how to perform the work around that action. That missing layer is procedure.
- AI agent skills
- procedural know-how
- AI agent packaging
- agent package manager
- agent interoperability
- agent system architecture
- agentpm
Zack Hine•
Open Source vs. Internal AI Agents: Where the Boundary Actually Falls
The public versus private split in agent systems is not a policy checkbox. It is the point where useful artifacts stop looking generic and start reflecting the systems, rules, and constraints of a real team.
- private agent systems
- open source AI agents
- internal AI tooling
- AI agent packaging
- agent governance
- private namespaces
- agentpm
Zack Hine•
Workflow Templates Are the Missing Onboarding Layer for Agent Systems
The blank page is still one of the biggest adoption bottlenecks in agent systems. Packages solve reuse. Templates solve the first-project problem.
- workflow templates
- agent onboarding
- AI agent packaging
- agent project scaffolding
- agentpm new
- multi-agent workspaces
- agent infrastructure
Zack Hine•
AI Agents Should Be Packages Too
A team builds an agent that works well internally. Another team wants to use it. That is where the packaging gap shows up.
- agents
- AI agent packaging
- agent package manager
- agent lockfile
- reusable AI agents
- agent interoperability
- AI agent infrastructure
Zack Hine•
AI Agent Skills Are Manuals. Package Managers Own Execution.
The fifth tool in an agent system is easy. The fifteenth is noisy. The fiftieth is a design problem.
- AI agent skills
- AI agent tools
- agent tool execution
- agent package manager
- agentpm run
- Claude Skills
- MCP tools
Zack Hine•
Why Agent Systems Need a Packaging Layer
The hard part of agent development is not getting an LLM to call a tool once. The hard part starts when that tool needs to be reused, versioned, installed, trusted, and run somewhere else.
- agents
- AI agent tools
- AI agent packaging
- agent package manager
- AI agent infrastructure
- agent interoperability
- reusable AI agents
Zack Hine•
Seeding AgentPM with Real Building Blocks
Most agent ecosystems have plenty of demos and very few genuinely reusable building blocks. Seeding AgentPM starts with a small set of tools that people should actually want to install.
- agents
- tooling
- portability
- agentpm