Ground Truth InterviewsRU Sign in

All courses › Agents

Agents

Build AI agents that stop when they should and do what they are allowed to

01The agent loop

One step of an agent loop Practice: one step of the loop The loop in code Practice: the loop in code Stopping and retrying Practice: stopping and retrying What only code can decide Practice: what code decides

02Reliability in production

Timeout and idempotency key Practice: timeout and idempotency key Says done, but nothing happenedDeep dive Practice: false successDeep dive Durable agent: checkpoints and resumeDeep dive Practice: durable agentDeep dive

03Agent designs

Workflow or agent Practice: workflow or agent ReAct and plan-and-execute Practice: ReAct and plan-and-execute Plan-and-SolveDeep dive Practice: Plan-and-SolveDeep dive ReflexionDeep dive Practice: ReflexionDeep dive One agent or a swarm Practice: one agent or a swarm

04Context and cost

Why the agent bill grows Practice: tokens and cache Context engineering Practice: managing the window Agent memory Practice: what the agent keeps

05Tools and protocols

MCP Practice: MCP Tool descriptions and injectionDeep dive Practice: tool descriptions and injectionDeep dive Code instead of a toolsetDeep dive Practice: code instead of a toolsetDeep dive Agent skills and A2ADeep dive Practice: agent skills and A2ADeep dive

06Frameworks

LangGraph or the raw loopDeep dive Practice: LangGraph or the raw loopDeep dive Agent SDKs: what you are buyingDeep dive Practice: agent SDKsDeep dive

07Coding agents

Driving a coding agent from a specDeep dive Practice: driving a coding agent from a specDeep dive