AI Skill Report Card

Designing AI Architecture

A-83·Sep 13, 2026·Source: Web
14 / 15

Given a request to design an AI system, produce these six artifacts in order:

  1. AI Architecture — high-level system diagram (components, data flow)
  2. Agent Topology — agent roles, hierarchy, communication pattern
  3. Memory Layer — short-term/long-term/episodic memory design
  4. Reasoning Flow — step-by-step decision/inference pipeline
  5. Execution Flow — how requests move from input to action to output
  6. Scaling Plan — how the system grows (more agents, more load, more data)

Every design must state how it satisfies: secure-by-default, auditability, observability, AI governance.

Recommendation
Add a second example covering a different topology (e.g., single-agent or batch pipeline) to show range beyond customer support
14 / 15

Progress:

  • Clarify the use case (single-agent vs multi-agent, sync vs async, real-time vs batch)
  • Define AI Architecture (models, orchestration layer, data stores, APIs)
  • Define Agent Topology (roles, supervisor/worker pattern, handoff rules)
  • Define Memory Layer (what's stored, where, retention, retrieval method)
  • Define Reasoning Flow (prompt chain, tool-use decisions, fallback logic)
  • Define Execution Flow (request → routing → agent(s) → tools → response)
  • Define Scaling Plan (horizontal scaling, cost controls, model swapping)
  • Verify all four priorities are addressed explicitly
  • Present as structured document with clear section headers
Recommendation
Include a template/skeleton for the six artifacts that Claude can fill in directly rather than only a worked example
16 / 20

Example 1: Input: "Design a customer support AI that can answer questions, escalate to humans, and remember past conversations."

Output:

Recommendation
Add explicit guidance on when to scale down complexity (e.g., single-agent sufficiency) to avoid over-engineering simple use cases
  • Orchestrator (LLM router) + 2 specialized agents (FAQ Agent, Escalation Agent)
  • Vector DB (conversation embeddings) + Relational DB (ticket state)
  • Model: primary LLM for reasoning, smaller model for classification/routing
  • Supervisor agent routes intent → FAQ Agent or Escalation Agent
  • FAQ Agent: read-only tool access (knowledge base search)
  • Escalation Agent: write access (create ticket, notify human)
  • Handoff protocol: confidence score < 0.7 triggers escalation
  • Short-term: last 10 turns in session cache (Redis, TTL 1hr)
  • Long-term: customer history in vector DB, retrieved via semantic search
  • Audit log: every memory read/write timestamped and user-attributed
  1. Classify intent (FAQ vs complaint vs unknown)
  2. Retrieve relevant memory + KB context
  3. Generate response with citation to source
  4. Self-check: confidence score, policy compliance check
  5. If low confidence → escalate

Input → Orchestrator → Intent Classification → Agent Selection → Tool Calls (KB search / ticket API) → Response Generation → Safety Filter → Output + Log Entry

  • Stateless agent workers behind load balancer, autoscale on queue depth
  • Cache frequent FAQ answers to reduce LLM calls
  • Model tiering: cheap model for classification, strong model only when needed
  • Secure-by-default: all tool calls require scoped API keys, no raw DB access from LLM
  • Auditability: every decision logged with input, output, model version, confidence
  • Observability: tracing per request (latency, token usage, tool calls) via OpenTelemetry
  • AI Governance: human-in-loop for escalations, periodic bias/quality audits on responses
  • Always separate orchestration logic from agent logic — makes topology changes cheap.
  • Design memory with explicit retention/expiry policy; never store indefinitely by default.
  • Every agent-to-agent handoff must be logged with reason and confidence score.
  • Prefer smaller/cheaper models for routing/classification; reserve large models for final reasoning.
  • Build in a "kill switch" and rate limits at the orchestrator level before scaling agents.
  • Make reasoning steps traceable — log intermediate thoughts/tool calls, not just final output.
  • Don't let agents share unrestricted memory access — scope memory per agent role.
  • Don't skip the observability layer "for now" — retrofitting tracing is expensive.
  • Don't design unbounded agent-to-agent loops without a max iteration/timeout guard.
  • Don't conflate short-term session memory with long-term user profile memory.
  • Don't scale agent count before scaling the orchestrator's routing and monitoring capacity.
0
Grade A-AI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
14/15
Workflow
14/15
Examples
16/20
Completeness
17/20
Format
15/15
Conciseness
13/15