Operator memos
Notes on grounded AI systems, delivery, and the ugly middle in between.
Due diligence at scale: how I think about retrieval, evals, observability, constraint design, and integration-heavy delivery once the demo is no longer the hard part.
6 min read
Best Practices for Building Agentic AI Systems in 2026
A practical March 2026 playbook for agent systems: tool contracts, approvals, retrieval discipline, evals, and telemetry.
AIAgentsArchitecture
Memo
6 min read
Preventing Hallucinations in LLM Systems
A March 2026 playbook for groundedness: retrieval discipline, abstention, claim checks, evals, and guardrails.
LLMReliabilityRAG
Memo
4 min read
Spec-Driven Development for Agent Workflows
A practical 2026 view of SDD: project brief, research, architecture, ticket sync, implementation, janitor.
SDDAgentsWorkflow
Memo
5 min read
Prompt Engineering in 2026: From Phrasing to Policy
Prompt design now means output contracts, examples, tool posture, and eval loops — not incantations.
Prompt EngineeringAgentsLLM
Memo
4 min read
BI Storytelling That Actually Moves Decisions
A 2026 guide to executive BI storytelling: narrative, visual hierarchy, decision framing, and trust.
BIStorytellingAnalytics
Memo