Agents
Agent memory, budgets & guardrails
Give agents bounded memory, cost budgets and guardrails.
Target proficiency: Applied
Course outcomes
- AIN 401 CO3
Design an AI-native system architecture — retrieval, agents, tools, memory and guardrails — through an AI-DLC gated workflow from Inception to Construction.
- AIN 401 CO5
Assess security, privacy and responsible-AI risks using the OWASP LLM and Agentic Top 10, NIST AI 600-1 and EU AI Act risk tiers, and implement proportionate mitigations.
- MST 502 CO3
Demonstrate Orchestration & Integration competence: complete the Day 31–45 builds, explain the underlying theory, and defend the phase artefact under live questioning.
- MST 502 CO5
Demonstrate Production, Security & Governance competence: complete the Day 61–75 builds, explain the underlying theory, and defend the phase artefact under live questioning.
- MST 508 CO2
Demonstrate Core LLM Engineering competence: complete the Day 16–30 builds, explain the underlying theory, and defend the phase artefact under live questioning.
- MST 508 CO6
Demonstrate Production LLMOps, Security & Mastery competence: complete the Day 76–90 builds, explain the underlying theory, and defend the phase artefact under live questioning.
Taught in weeks & phases
- AIN 401 · Week 7 — Agents & Tools: Function Calling, MCP & Memory
- AIN 401 · Week 8 — Mid-Term + Multi-Agent Patterns & Orchestration
- MST 502 · Phase 3 — Orchestration & Integration
- MST 502 · Phase 5 — Production, Security & Governance
- MST 508 · Phase 2 — Core LLM Engineering
- MST 508 · Phase 6 — Production LLMOps, Security & Mastery