29 articles on Agentic AI — programs, tooling, and delivery on Petralian.
Loading articles…
Browse by topic
Click a topic to open its archiveTap a topic to browse
29 articles on Agentic AI
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 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 →
Best forPower users optimizing token spend and context windows in Cursor
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 →
Best forDevelopers comparing Copilot and Cursor in a real daily workflow
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 →
Best forManagers and team leads translating people-management instincts to AI workflows
Five management habits that transfer directly to directing AI agents: show examples, write context down, guide in steps, define outcomes, and close the loop with review.
Continue reading →
Best forBuilders feeding UI context to agents who want to understand prompt-injection risk
Design capture CLIs that dump outerHTML into SKILL.md files can smuggle instructions. Sanitize at the trust boundary before agents read the DOM.
Continue reading →
Best forDevelopers standardizing on a single coding model and tighter agent bootstrap
I run Cursor on Composer 2.5 only—not to save money alone, but to get predictable rule compliance. A tighter session bootstrap beat chasing frontier models for my workflow.
Continue reading →
Best forAnyone 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 →
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 →
Best forBuilders implementing the three-layer external memory model for AI-first dev
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 →
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 →
Best forBuilders choosing pragmatic file memory 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 →
Best forDevelopers comparing real monthly cost across Copilot, OpenRouter, and similar stacks
GitHub Copilot's new token-based pricing changes everything. Here's what it actually costs compared to OpenRouter and third-party relays when you code extensively.
Continue reading →
Best forBuilders publishing from Obsidian with GitHub Actions and minimal friction
A practical way to move from writing in Obsidian to publishing on a live site without copy-paste, manual uploads, or brittle one-off scripts.
Continue reading →
Best forBuilders curious how this site is wired — Obsidian, sync, and Next.js in practice
The why was clean. The how had corners. A ground-level account of building petralian.com — the masonry layout that fought back, a 404 page with a working Asteroids game, the TinaCMS newline problem nobody warns you about, and how AI wrote most of it.
Continue reading →
Best forDevelopers weighing a Next.js rebuild for content, SEO, and shipping speed
WordPress was slowing down the actual writing. Here's why I rebuilt petralian.com on Next.js, how Obsidian now sits at the center of my publishing workflow, and why I decided to open source the whole thing.
Continue reading →
Best forBuilders and product leads comparing durable memory approaches for agents
Every AI session starts from scratch. Four tools are racing to solve the AI memory problem - OpenClaw, Hermes, Karpathy's LLM wiki, and a plain Obsidian vault. Here's how they differ and which approach actually survives tool churn.
Continue reading →
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 →
Best forBuilders wiring AI quality checks into CI and release pipelines
Unit tests catch code failures. They do not always catch AI quality regressions. Here is how to add quality thresholds as a first-class release gate.
Continue reading →
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 →
Best forTeams running agent workflows who need a practical quality signal before drift becomes production risk
Your AI outputs can look great this month and degrade next month without obvious failures. Here is why drift happens and how to detect it before it reaches production.
Continue reading →
Best forBuilders trying Gravio scoring on a real repo in one sitting
A practical, no-fluff walkthrough for getting Gravio running from a clean folder to your first quality score, including the exact command flow and common mistakes.
Continue reading →
Best forBuilders exploring privacy-preserving AI quality scoring with Gravio
Most AI quality platforms ask you to trust them with your source code. Gravio takes a different path: encrypted scoring designed to keep plaintext out of the server path.
Continue reading →