Skip to content

2026-03-28

Daily Framework for 2026-03-28

How I read this page: - [REL] Reliability & Evaluation — What fails in prod? How do we test + observe it? - [AGENT] Agents & Orchestration — What runs the loop? What actions can it take? - [DATA] Data, RAG & Knowledge — Where does context come from? How is it retrieved? - [GOV] Security, Privacy & Governance — What needs policy, permissions, and audit? - [COST] Infra, Hardware & Cost — What gets expensive (latency/tokens/GPU/ops)? How do we cap it? - [OPS] Product & Operating Model — Who owns this weekly? How do we roll it out safely?

Quick system map (to place each item): Model → Context (RAG/memory) → Orchestrator → Tools → Evals/Tracing → Governance.

1) Today's Signals

2) GenAI

Check Point's AI Defense Plane

Architectural Implication

  • [GOV] Security, Privacy & Governance — Need to integrate AI security controls across all AI components.
  • [OPS] Product & Operating Model — Must establish protocols for AI security governance and monitoring.

Open questions - How will AI security controls affect system performance? - What are the compliance requirements for implementing such security measures?

Cisco's Secure AI Factory Expansion

Architectural Implication

  • [COST] Infra, Hardware & Cost — Consider the cost implications of deploying AI across diverse environments.
  • [OPS] Product & Operating Model — Need to develop deployment strategies for AI at scale.

Open questions - What are the scalability challenges in deploying AI from data centers to edge sites? - How do we ensure consistent performance across different deployment environments?

3) Agentic AI

Semantic Kernel's Developer Adoption

Architectural Implication

  • [AGENT] Agents & Orchestration — Use Semantic Kernel for efficient AI orchestration.
  • [DATA] Data, RAG & Knowledge — Utilize its multi-model support for diverse data sources.

Open questions - How does Semantic Kernel handle data privacy and security? - What are the integration challenges with existing systems?

'AI-native' in the Travel Industry

Architectural Implication

  • [AGENT] Agents & Orchestration — Develop AI-driven agents for personalized travel experiences.
  • [OPS] Product & Operating Model — Adapt business models to incorporate AI-native services.

Open questions - What are the customer acceptance rates for AI-driven travel services? - How do we measure the ROI of AI-native implementations?

4) AI Radar

Axios AI+DC Summit

Architectural Implication

  • [GOV] Security, Privacy & Governance — Monitor policy developments affecting AI deployment.
  • [OPS] Product & Operating Model — Align product strategies with evolving AI regulations.

Open questions - How will upcoming AI policies impact our product roadmap? - What are the best practices for navigating AI-related legislation?

5) CTO Brief

  • Integrate AI security measures across all components.
  • Develop scalable deployment strategies for AI at various environments.
  • Adapt business models to incorporate AI-native services.

6) Rohit's Notes

  • Surprised by the rapid adoption of Semantic Kernel among developers.
  • Need to re-check the scalability of AI deployments across diverse environments.
  • Focus on integrating AI security controls into all components.

7) Design Drill

Scenario: A global e-commerce platform wants to implement AI-driven customer support across multiple regions.

Constraints: - Must comply with regional data privacy laws. - Ensure high availability and low latency. - Integrate smoothly with existing CRM systems.

Guiding questions: - How do we design AI agents that understand multiple languages and cultural contexts? - What infrastructure is needed to support AI-driven support at scale? - How do we monitor and evaluate the performance of AI agents? - What are the security implications of handling sensitive customer data? - How do we ensure compliance with diverse regulatory requirements?

Architecture Implications Index (Today)

  • [GOV] Security, Privacy & Governance — Component: AI security controls; Decision: integrate across all AI components.
  • [OPS] Product & Operating Model — Component: deployment strategies; Decision: develop for AI at scale.
  • [AGENT] Agents & Orchestration — Component: AI agents; Decision: use Semantic Kernel for orchestration.
  • [DATA] Data, RAG & Knowledge — Component: data sources; Decision: utilize multi-model support in Semantic Kernel.
  • [OPS] Product & Operating Model — Component: business models; Decision: adapt to incorporate AI-native services.