Technology / L2 detail
Architecture
Linked Level 3 activities
Level 3
API design and integration
Design APIs for agent orchestration (idempotency, retries, transactional boundaries, compensating actions) rather than simple prompt-in / text-out patterns
Open Level 3 detail
Level 3
Microservices and modular design
Modularise capabilities so agents can compose and swap tools/services dynamically, beyond embedding GenAI inside monolith workflows
Open Level 3 detail
Level 3
Event-driven architecture
Shift from “user-triggered GenAI” to agents reacting to events, maintaining state, and initiating multi-step actions automatically
Open Level 3 detail
Level 3
Data pipelines and orchestration
Evolve pipelines from feeding models to supporting continuous agent context refresh, policy checks, and remediation triggers
Open Level 3 detail
Level 3
Permissions and access model (RBAC / ABAC)
Extend human RBAC into agent identities and fine-grained tool/data entitlements, including per-task scoped permissions and action class constraints
Open Level 3 detail
Level 3
Runtime action ring-fencing and safety wrappers
Add hard technical boundaries around what agents can do - tool allowlists, parameter validation, spend/impact limits, jurisdiction constraints, red-line proximity checks, and kill-switch hooks enforced outside the model
Open Level 3 detail
Level 3
DevSecOps control gates in CI/CD
Insert policy-as-code and evaluation gates for agent behaviours (tool use, escalation, unsafe actions), not only model quality checks
Open Level 3 detail
Level 3
Secure experimentation sandbox (high-trust build environment)
Provide an isolated sandbox lane where teams can prototype agents with temporarily elevated permissions using controlled data and hardened tool stubs, with strict egress controls and full tracing
Open Level 3 detail
Level 3
Fallback and safe-state design
Add explicit safe-states, kill-switches, and manual override paths for autonomous execution, not just “model unavailable” handling
Open Level 3 detail
Level 3
Explainability instrumentation and provenance capture
Instrument agent runs so “why did it act” can be reconstructed - action rationale capture, evidence linking, step-level traces, and context provenance (not just final outputs)
Open Level 3 detail
Level 3
Evidence automation and compliance reporting pipelines
Automate evidence collection from build/run systems (tests, approvals, policies, logs, monitoring) into continuously updated evidence packs
Open Level 3 detail