Writing about AI, technology and commercial growth: what worked, what failed, and what helped me move from pilot to production.
Nathan Petralia
I have spent two decades leading digital and commercial programs across APAC. Today I build AI products and leverage AI across consulting, practice building, go-to-market, commercials, delivery governance, and operational leadership.
About me →Recent Posts
Best forLeaders and operators designing a knowledge-work engine around agents
The same session-continuity engine that ships software can run initiatives, decisions, and content. Maps memory, voice, and routing to Agile, Jira, Confluence, RACI, and RAG—with a replication kit an AI can execute.
Continue reading →
Best forExecutives making the leadership calls that determine whether agent programs scale
Simon Sinek's Why-How-What, Drucker's decision discipline, and RACI meet applied AI. Leaders keep accountability; the file-based engine holds purpose, dissent, and decision records agents need at session start.
Continue reading →
Best forMarketing leaders keeping brand voice consistent when agents draft at scale
Brand voice fails when it lives in a PDF nobody opens. This playbook maps Sinek's Why-How-What, voice-as-system governance, and content-batch routing to produce consistent, high-volume marketing with minimum rework.
Continue reading →
Best forProgram and delivery leads running projects where agents are part of the team
Agile, Scrum, Jira, and Confluence already own execution and narrative. This playbook shows where a file-based agent engine fits—iron triangle tradeoffs, RAG, RACI, RAID, and applied AI without pretending chat is a program office.
Continue reading →
Best forBuilders measuring whether their Cursor harness actually improves output
Do not build Phase 2 orchestration until Phase 0 data says so. Layer 4 feedback — CSV, footer Agents line, eval gate — plus weekly OpenRouter checks beat benchmark leaderboard anxiety.
Continue reading →
Best forBuilders connecting file memory, Obsidian, and agent loops in daily work
External memory is four tiers in practice — short-term, operational, evergreen, and a feedback loop hardened into rules and footers. The harness gates when each tier loads so you keep control without token bloat.
Continue reading →
Best forSolo builders and small teams who want harness discipline without microservice overhead
Terminal-Bench harnesses look like separate products. On a production Shopify app I already had subagents, CI gates, and session rules. You keep model and mode control — the harness supports routing, tests, and memory gates, not autopilot.
Continue reading →
Best forLeaders directing AI as primary engineer — and builders curious how that feels in practice
When the agent writes most of the code, the job shifts from typing to operating-system design: rules, file memory, session handoffs, and gates before deploy. Lessons from running that model on production repos.
Continue reading →
Best forBuilders comparing model cost versus quality with reproducible benchmarks
Anthropic's Fable 5 leads CursorBench 3.1 at 72.9%, but at $18 per task and 76 steps. I read the table for score per dollar, tokens, and steps, and where open models land.
Continue reading →