Agentic Foundations.
You need different answers when you use an agent, own its work, build it or operate it. Choose your starting point.
I use agents
Understand what an agent can do and how to check its work.
I own the process
Choose a suitable task, set boundaries and measure the result.
I build agents
Understand execution, integrations and development tools.
I secure and operate agents
Control identities, data, incidents and changes.
Basics
Understand the terms, then try a clearly bounded task.
What makes an AI system agentic?
Understand goals, tools and decisions, with one task explained as a chat response, a workflow and an agent.
4 min read ↗Using an agent and checking its work
Give a clear task, understand its permissions and verify the result before you rely on it.
4 min read ↗Decisions
Choose suitable work, agree responsibilities and assess results.
Choosing a task and running a useful pilot
Define the business result, limit the first task and compare the agent with your current process.
4 min read ↗Who owns the decisions around an agent?
Assign responsibility for outcomes, actions, access, evaluation and incidents before work begins.
4 min read ↗Testing whether an agent completes the task
Measure results, permissions, recovery and cost with repeatable normal and difficult cases.
4 min read ↗Architecture
Follow execution, connect tools and control access.
The parts of an agent architecture
Follow a task through context, model decisions, tools, permission checks, state and recovery.
4 min read ↗Securing and operating an agent
Map identities and data, restrict actions, monitor failures and prepare a tested stop procedure.
4 min read ↗Choosing frameworks, SDKs and runtimes
Separate models, development tools and hosted products, then compare them against your task.
5 min read ↗Tools, MCP and integration boundaries
Understand what a tool exposes, how MCP connects it and where your application must enforce access.
4 min read ↗Platforms
Understand each provider’s approach before choosing a product or SDK.
OpenAI Agents SDK, explained
Understand the agent loop, tools and delegation, then assess what your application still needs to implement.
3 min read ↗Anthropic Claude Agent SDK, explained
Separate the client API from the agent runtime, and assess tools, permissions and the environment you operate.
3 min read ↗Google Agent Development Kit, explained
Understand agents, orchestration and state in ADK, then assess the hosting and integration choices around them.
3 min read ↗Microsoft Agent Framework, explained
Understand code-based agents, workflows and integrations without mixing them with every Microsoft agent product.
3 min read ↗GitHub coding agents and repository work
Understand a coding-agent product, define reviewable tasks and check the changes before merging.
3 min read ↗14 reference guides. Worked examples and suggested checklists are our editorial guidance, not measured product results. Provider claims link to official documentation. Reviewed 8 October 2026.