Playbook

21 articles on Playbook — programs, tooling, and delivery on Petralian.

Related topics

Browse by format

Browse by topicPlaybook

Showing 21 articles on Playbook

Everyday desk with laptop open to a workspace beside folders for study, work, and personal projects, warm natural light, no logos or readable text.
Hybrid

Is Cursor Only for Developers? A Better AI Interface for Anyone With Files

Best forAnyone outgrowing ChatGPT tabs who wants file-grounded AI that remembers your rules across projects, semesters, jobs, and side work

Cursor is sold as a coding IDE. I use it as a governed agent for writing, research, commerce, job search, client work, and code when needed. The win is file-grounded memory, not syntax highlighting.

Continue reading →
Desk with one labeled Obsidian notebook feeding multiple project folders on a laptop screen, warm editorial lighting, no logos or readable text.
Hybrid

How I Run Cursor With One Obsidian Brain Across Many Projects

Best forAnyone running Cursor across multiple contexts who wants one external memory system without rebuilding rules per folder

I stopped copying AI rules into every engagement. One Brain vault, native file reads, hooks, and a sync script align personal site, Shopify app, job applications, and client work — one memory system for program delivery.

Continue reading →
Git tag label beside a deploy pipeline diagram on a drafting table, warm desk lamp, editorial still life, no logos or readable text.
Hybrid

Deploy Without a Git Tag and You Cannot Roll Back Cleanly

Best forAnyone governing agent-assisted releases who needs traceable promote-and-rollback, not just faster commits

Agent-assisted delivery fails governance when production has no release handle. Tag or record the commit at promote time, reject dirty-tree releases, keep rollback traceable.

Continue reading →
Cinematic 16:9 wide shot of a conference table with four labeled trays
Hybrid

The Knowledge Work Agent Engine: A File-Based Stack for PM, Leadership, and Marketing

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 →
Cinematic 16:9 low-angle of a single chair at a round table, three empty
Strategic

Leadership and Decisions With an AI Session Engine (Purpose, Dissent, and Audit Trails)

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 →
Cinematic 16:9 macro of a printing press roller lifting, ink gradient
Hybrid

Marketing and Voice at Scale With a File-Based Agent Engine

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 →
Cinematic 16:9 overhead of a kanban board made of paper cards on a concrete
Hybrid

Project Management With a File-Based Agent Engine

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 →
Cinematic 16:9: spreadsheet notebook beside a CI pipeline light and
Hands-on

Measure Your Cursor Harness — CSV, CI, and OpenRouter Dollars

Best forProgram leads measuring whether a Cursor harness improves output and spend

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 →
Cinematic 16:9: three translucent drawers labeled Repo, Brain-Pack,
Hands-on

Agent Harness Memory Loop — Four Tiers, Feedback Loop, and Load Gates

Best forPractice leads connecting file memory, Obsidian, and agent loops across engagements

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 →
Cinematic 16:9: a single Composer pane on a workbench surrounded by
Hands-on

You Already Have an AI Harness in Cursor

Best forPractice leads governing Cursor Agent with 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 →
Cinematic 16:9: workbench with crossed-out proxy diagram, active OpenRouter
Hands-on

Beyond Headroom: What I Tried to Save Cursor Tokens, What Failed, and What I Use Now

Best forProgram leads optimizing Cursor token spend and context discipline without proxy middleware

I ran Headroom, built a 300-line proxy, wired a Cloudflare tunnel, and added RTK. On my Cursor + OpenRouter workload the dollars did not move. Here is what is worth doing instead.

Continue reading →
Cinematic 16:9 low-angle shot: two translucent IDE panes floating in
Hands-on

From VS Code Copilot to Cursor: What Changed in My AI Workflow

Best forPractice leads comparing Copilot and Cursor for governed agent workflows

Copilot had the same footer spec but dropped it on long chats. Cursor keeps it with alwaysApply rules, optional hooks, and a v3.1 mode-based Response Footer Contract.

Continue reading →
Isometric cutaway of three enterprise AI foundation layers—data, governance, and change—with a deploy capsule waiting above a hold line
Strategic

Getting Enterprise AI Right: The Work That Comes Before Deployment

Best forLeaders and program owners steering enterprise AI before go-live pressure wins

Enterprise AI programs that last share one pattern: data readiness, named governance owners, and change runway are gates before go-live—not parallel work you finish after the demo.

Continue reading →
Desk with layered notebooks and a laptop showing a linked note graph for session continuity.
Hybrid

External Memory Series: A Practical Guide to AI Session Continuity

Best forProgram leads and knowledge workers adopting file-based memory for AI-assisted work — start here for the series map

Chat is not memory. This series explains a file-based external brain for builders and leaders—four layers, hooks, and why it beats hoping the model remembers.

Continue reading →
Calm home office desk with an open Obsidian-style linked note graph
Hybrid

Beyond Chat History: Using Layered Obsidian Memory for Personal Productivity

Best forKnowledge workers layering Obsidian memory beyond a single chat thread

The same three-layer memory stack used for shipping code works for strategic work, client engagements, and cross-tool AI—short chat, operational handoffs, evergreen notes, and explicit feedback.

Continue reading →
Editorial overhead photograph of a developer desk with three labeled
Hands-on

Three Layers of External Memory for AI-First Development

Best forPractice leads implementing layered external memory for agent-assisted delivery (Playbook)

Chat context is not memory. A three-layer file system—session, operational, evergreen—plus hooks and git automation is how I keep production codebases coherent across hundreds of agent sessions.

Continue reading →
Editorial photograph of a printed runbook and decision log on a conference
Hybrid

Why Deliberate File Memory Beats Hoping Agents Remember

Best forTeams adopting governance for file-based agent memory instead of hoping context sticks

Chat memory is opaque and ephemeral. Deliberate files give audit trails, solo-shipping continuity, team handoffs, and survival when models or tools change.

Continue reading →
Editorial desk with two diagrams side by side on paper—one a simple
Hybrid

Why File Memory Beats the Three-Layer AI Diagram

Best forLeaders choosing file memory for governed AI programs over diagram-perfect architecture

The popular STM / LTM / feedback diagram optimizes in-model memory. A file-based external brain optimizes audit, handoff, and tool churn. Here is when each design wins—and why I chose files.

Continue reading →
A transparent engineering control room with six illuminated quality
Hands-on

How We Built Gravio’s Scoring Engine: From Repo Signals to Release Gates

Best forBuilders who want the architecture behind an AI quality scoring engine

A practical breakdown of how Gravio turns repository signals into six-dimension scores, hard quality gates, and actionable remediation plans.

Continue reading →
A network map of many software repositories connected to one quality
Hybrid

Team Playbook: Rolling Out Gravio Across Multiple Repositories

Best forPlatform and engineering leads rolling AI quality scoring across multiple repos

A practical rollout framework for introducing Gravio across many repos without creating process fatigue, policy confusion, or noisy quality signals.

Continue reading →
Hero illustration for Boutiques, Agencies, or Consultancies? Which one should you work with?
Strategic

Boutiques, Agencies, or Consultancies? Which one should you work with?

Best forLeaders choosing between boutique partners, agencies, and consultancies for transformation work

Having led digital transformation initiatives across Asia Pacific for global brands ranging from luxury retail to financial services, I've experienced the…

Continue reading →