Tech Study Guide
Advanced Agents
Advanced agent engineering with ReAct, planning, reflection, tool routing, multi-agent systems, durable execution, memory, sandboxing, approval workflows, trajectory evaluation, and failure recovery.
Advanced Agents
Advanced agents are workflow engines with probabilistic planning. The model may choose the next action, but deterministic systems must own state, permissions, execution, retries, and rollback.
Agent Patterns
| Pattern | Use | Risk |
|---|---|---|
| ReAct | Interleave reasoning and actions. | Hidden bad intermediate actions. |
| Planner/executor | Separate decomposition from execution. | Planner creates impossible tasks. |
| Reflection | Review output or trajectory before finalizing. | Extra tokens without better correctness. |
| Tool router | Choose among specialized tools. | Wrong tool or missing auth boundary. |
| Multi-agent | Split roles or debate. | Coordination overhead and inconsistent state. |
| Durable execution | Persist state across failures. | Resume bugs and duplicated side effects. |
State Machine Boundary
flowchart LR
Requested --> Planned
Planned --> Approved
Approved --> Executing
Executing --> Completed
Executing --> Failed
Failed --> Retrying
Failed --> Compensating
Retrying --> Executing
Compensating --> Reviewed
Sandbox and Approval Controls
| Control | Purpose |
|---|---|
| Read-only tools | Allow exploration without side effects. |
| Approval gates | Pause before irreversible or expensive actions. |
| Sandboxes | Limit file, network, process, and secret access. |
| Idempotency keys | Prevent duplicate writes on retry. |
| Audit replay | Reconstruct prompts, tools, observations, and state. |
Practical Lab: Trajectory Review
trajectory_case:
goal:
tool_calls:
observations:
final_answer:
invalid_tool_calls:
unnecessary_steps:
policy_violations:
recovery_quality:
Study Cards
Why do advanced agent evals need trajectories?
The final answer can hide unsafe tool choices, duplicate side effects, or bad recovery behavior.
What does durable execution add to agents?
Persisted workflow state so an agent can resume or recover after failures.
Why are approval gates important?
They prevent irreversible or high-impact actions from being executed solely by model judgment.