Memory hook: One responsibility, one boundary, one exit.
Must remember
- Decompose goals into deterministic workflow steps, agent decisions and tool actions. Use an agent only where flexible reasoning/interaction adds value; fixed business rules can stay in ordinary code.
- Define each agent’s role, allowed tools, data scope, autonomy, outputs and termination criteria. Human-AI experience design includes understandable approvals, correction, escalation and user control.
- Sequential, parallel, hub-and-spoke, peer-to-peer and orchestrator/subagent patterns have different failure and coordination costs. Match dependencies and ownership rather than adding agents for appearance.
- Select model families and compute from task quality, latency, concurrency, state and cost. Foundry, Azure Functions, Container Apps/other supported compute, data stores and integration components must fit the execution lifetime.
- Design session, shared-team and long-term memory separately with tenant boundaries and retention. Zero Trust requires per-agent identities and constrained lateral access.
- Specify trace correlation, replayable observable events, health metrics and quality checks during design. Use reproducible dev containers, dependencies, CLI/editor tooling and reviewed AI instruction files for the development workflow.
Choose under exam pressure
| Requirement | Choice and reason |
|---|---|
| An approval must always precede a payment | A deterministic authorization gate around the agent’s proposed action. |
| Several independent analyses feed one decision | Bounded parallel workers with a coordinator that validates and reconciles results. |
Traps
- A multi-agent design can increase latency, cost and failure modes.
- A persona written in a prompt is not an enforceable permission boundary.
Active recall
1. What belongs in an agent contract?
Responsibility, inputs, outputs, tools, permissions, completion criteria and failure behavior.
2. Why separate shared and personal memory?
Their ownership, privacy and lifecycle requirements differ.
3. When prefer a simple workflow?
When steps and rules are known and do not need flexible agent decisions.
4. What should be traceable?
Observable model/tool/workflow events and decisions, without requiring hidden internal reasoning.
5. Why define autonomy levels?
To clarify which actions may execute directly and which require approval or escalation.