DraftlizeVOL. 1 · 2026 EDITION
Start free →
Blog

Essays on product thinking with AI agents.

Card graphs, spec drift, decision logs, persistent agent memory — and what actually changes when the substrate underneath your AI agents is something other than chat history.

2026-06-29 · 9 min read

Obsidian vs Notion: An Honest Comparison and How to Choose

Obsidian and Notion sit at opposite ends of a real design spectrum: local-first Markdown files vs cloud-based blocks, personal PKM vs team collaboration. A no-spin, third-party comparison across seven dimensions — plus a clear framework for which one you should actually pick.

READ →
2026-06-29 · 9 min read

What do product managers do? A clear look at the role

Product managers own what gets built and why — not the building itself. A clear guide to the core responsibilities, the real day-to-day, the skills that matter, how the role differs from project manager and product owner, and the invisible work nobody warns you about.

READ →
2026-06-29 · 8 min read

Customer feedback analysis: turning the mess into product decisions

A practical guide to customer feedback analysis — collect across channels, tag and quantify by frequency, impact, and segment, surface the real themes, and turn them into decisions. Plus the part most guides skip: why the line from insight to decision to shipped product keeps breaking.

READ →
2026-06-29 · 9 min read

Competitor analysis framework: 5 frameworks and when to use each

SWOT, Porter's Five Forces, feature matrix, perceptual map, competitive matrix — what each is good at, when to use it, and a worked example for each. Plus the problem none of them solve: a competitor analysis is right the day you finish it and wrong the moment a rival reprices.

READ →
2026-06-29 · 8 min read

What is a PRD? A plain guide to the product requirements document

A PRD (product requirements document) describes what you're building and why, so the whole team can decide without re-asking you. What it answers, the parts it's made of, who writes it, how it differs from a spec, brief, or BRD — and the failure mode nobody warns you about.

READ →
2026-06-28 · 7 min read

Context engineering: the skill that replaced prompt engineering

Prompt engineering optimized the wording of one call. But agents run for many steps, and what decides their quality is what they're looking at when they read each instruction. That's context engineering — and why bigger context windows don't solve it.

READ →
2026-06-28 · 7 min read

LLM context window, explained: why a bigger one won't make your AI remember

A bigger context window raises the ceiling on what you can paste — but it isn't memory, and past a point it stops helping. Why a full window still forgets, and what actually keeps an AI consistent on long projects.

READ →
2026-06-28 · 7 min read

How to Write a PRD (That Survives Contact With the Team)

A practical guide to writing a PRD — the eight sections that earn their place, and the part everyone skips: why PRDs fail by drifting, not by being badly written, and what fixes that.

READ →
2026-05-28 · 6 min read

The Card Graph: A new substrate for AI-assisted product thinking

Chat history is the wrong shape for product thinking. Card graphs are a different substrate — one whose primary user is an AI agent collaborating with a human, not a human reading the document later.

READ →
2026-05-28 · 5 min read

Why your PRDs drift after every sprint (and how to stop it)

Spec drift isn't a discipline problem. It's a substrate problem. Here's how dependency tracking solves it the same way invalidated build artifacts get solved — automatically.

READ →
2026-05-28 · 6 min read

How I run product decisions with Claude Code + Draftlize

A concrete workflow walkthrough. Brainstorm in Draftlize, implement in Claude Code via /draftlize:cite, mark built, watch for drift_detected when the spec moves.

READ →
2026-05-28 · 5 min read

Decision logs in the AI era: what changes when AI can read them

ADRs have been around since 2011 — and have always atrophied. What changes when the audience isn't only humans? The AI agent becomes the discipline-enforcing reader.

READ →
2026-05-28 · 5 min read

5 PRD templates that don't drift

Five PRD templates built on cards instead of prose. The structure makes drift visible the moment dependencies move. Each ships as a starter pack in Draftlize.

READ →
2026-05-28 · 5 min read

Stop re-explaining context to AI: A PM's guide to persistent agent memory

Why ChatGPT Memory / Claude Projects don't fully fix the re-explanation problem, and what actually does. Plus a practical 4-step switch guide.

READ →
2026-05-28 · 6 min read

Why we built Draftlize (and what dogfooding taught us)

The personal version. The bet behind the substrate, the secondary bets we got wrong (free tier, voice input, audience), and what dogfood taught us about who actually loves it.

READ →
2026-05-28 · 4 min read

From chat to artifact: The Draftlize loop in 5 minutes

The conceptual heart of Draftlize is a loop: chat with the agent, agent writes cards, cards become artifacts, artifacts feed future chats. 5 minutes to understand.

READ →
2026-05-28 · 5 min read

The MCP integration: Why Draftlize is first-class context for Claude Code

Why Draftlize shipped MCP server support on day one of the protocol. What the integration enables. 60-second setup with Claude Code, Cursor, or Claude Desktop.

READ →
2026-05-28 · 4 min read

What happens to your PRD when you change one decision: a concrete demo

Real cards, real edits, real cascade. A walkthrough of what Draftlize does when you change a single decision in a 47-card project — and the 12 dependents that flag automatically.

READ →
2026-05-28 · 5 min read

Card graphs vs second brains: why context for AI is different from notes for humans

Obsidian / Roam / Notion are wonderful for human knowledge work. They're the wrong shape for AI context. The mismatch is structural — and explains why a new tooling category is emerging.

READ →