Models that plan, call tools, and act in a loop — plus the SDKs that make it tractable.
Sign in to track your progress across sections.
13 articles
Listed inWhat are AI Agents?AI Agentson
Anthropic on the difference between workflows and agents, five composable patterns, and why most teams should start with the simplest thing that works.
Listed inMulti-Agent SystemsAI Agentson
Lilian Weng's survey of planning, memory, and tool use — still the clearest map of the agent design space.
Listed inGoogle ADKAI Agentson
Google's ADK: agent definitions, tools, sessions, and the built-in evaluation harness.
Listed inClaude Agent SDKAI Agentson
Writing the agent loop is straightforward; the harness supplies what surrounds it. Context management, sessions, permissions, and the file and shell tools an agent needs are what adopting the SDK gives you.
Listed inManual ImplementationAI Agentson
The agent loop in forty lines, why a failing tool returns its error as a result, and what a framework is doing on top.
Listed inTools & Function CallingAI Agentson
The model chooses a tool from its description alone, and every declaration is billed on every request whether or not it is called. Assume any tool with a side effect will be invoked twice.
Listed inWhat are AI Agents?AI Agentson
Systems where the model decides the next action instead of following a fixed script.
Listed inGoogle ADKAI Agentson
Google's Agent Development Kit for building and evaluating agents.
Listed inOpenAI AgentKit & Agents SDKAI Agentson
OpenAI's hosted agent runtime, handoffs, and guardrails.
Listed inMulti-Agent SystemsAI Agentson
Splitting work across specialised agents, and the coordination cost that follows.
Listed inAgent Use CasesAI Agentson
Where a loop beats a pipeline, and where it just adds variance.
Listed inVertex AI Agent BuilderAI Agentson
Managed agents on Google Cloud with grounding and enterprise controls.