---
title: "First-principles check: are we drifting?"
url: https://memory.wiki/dEgO6Qml
updated: 2026-05-15T16:43:23.889Z
hub: https://memory.wiki/hub/raymindai
bundle_count: 1
concept_count: 12
source: "strategy-note"
---
# First-principles check: are we drifting?

> Strategy reflection. Mapping today's product surface against the 8 founding principles. Where we're aligned, where we're drifting, what to double down on.

## The 8 first principles

1. **LLMs read markdown natively.** (empirical)
2. **URLs cross every boundary.** (empirical)
3. **Authored, not extracted.** (conviction)
4. **Cross-AI is a structural moat.** (argument)
5. **The graph lives in the response, not behind a service.** (conviction)
6. **Per-project + per-person scopes compose.** (observation)
7. **Zero friction.** (founding principle)
8. **Build in public.** (tactic)

## Per-principle assessment

| Principle | Alignment | Comment |
|---|---|---|
| **1. LLMs read markdown** | ✓ strong | Every output is markdown. No drift. |
| **2. URLs cross every boundary** | ✓ strong | `/llms.txt`, `?compact`, `?graph=0` are all URL-native. The image-rehost work today was a direct expression of "URL must be self-contained." |
| **3. Authored, not extracted** | ⚠ half | The product is aligned. **Risk: auto-analyze, concept index, related-in-hub may read as "AI organizes for you" if marketed naively.** The verb order matters — *"you write, the AI links"* must always be in that order. |
| **4. Cross-AI = structural moat** | ⚠ at risk | If the 4 native-skill plan is *framed* as "we support every AI," the cross-AI thesis reduces from "one URL works in 3 AIs" to "Claude one + ChatGPT one + Gemini one." Strictly worse framing. |
| **5. Graph in the response (not a service)** | ✓ strong | The auto-queue-on-bundle-create work shipped today is exactly this. Fresh bundles' URLs carry graph_data from the start. |
| **6. Doc / Bundle / Hub composable scopes** | ✓ strong, ⚠ marketing | This is our most differentiating part, but marketing emphasizes hub. **Bundle deserves equal billing — AGENTS.md fit is *bundle*, not hub.** |
| **7. Zero friction** | ⚠ weakening | "Zero friction to *try*" is intact. "Zero friction to *use well*" is weakening (image rehost / edit token / GitHub Action all need an account). Healthy for monetization but the founder narrative needs to be honest about it. |
| **8. Build in public** | ✓ strong | Today's GitHub Action dogfood is the proof. |

## Biggest single drift risk

**Feature breadth is growing faster than spine consolidation.**

One conversation today shipped: image rehost (6 import paths), 4 Marp decks + PDF/PPTX, native skill roadmap, GitHub Action dogfood, sign-out bundle clear, demo 50-doc seed + ID renumber, bundle readiness pill + auto-queue.

Each piece is justifiable. The risk: after 5 minutes of using mdfy, a user should be able to answer *"what is this?"* in 8 words — **"URL is the unit. Markdown is the substrate."** If they can't, breadth is hurting positioning.

## Three concrete recovery moves

1. **Add a self-check to every PR:** *"Does this make the URL more valuable, or just add another way to reach it?"* The first kind compounds. The second is breadth without spine.

2. **Lock native-skill positioning before any of them ship.** Each skill UI must say *"Your URL: mdfy.app/<X>"* somewhere visible — the skill is the *on-ramp* to the URL, not a substitute for it. Otherwise we accidentally train users that mdfy *is* the ChatGPT GPT.

3. **Promote bundle in the launch copy.** Current Show HN draft leans on hub. The hub URL is the "personal layer"; the bundle URL is the "per-project layer" — and that's exactly what AGENTS.md / .cursor/rules need. Add a bundle slide. In /spec, change the order to doc → bundle → hub (small to large, composition first).

## One-line summaries

**What's working:** Layered architecture on a markdown-URL foundation. Each new feature deepens that layering, not flattens it.

**What to watch:** "We have a Claude thing AND a ChatGPT thing AND a Gemini thing" is a concession framing. The principle is "one URL, every AI reads it." Hold that frame even while shipping the skills.

## Action items (this week)

- [ ] Add the PR-self-check rule to CLAUDE.md
- [ ] Lock the "Your URL: ..." visibility rule in any native skill mockup
- [ ] Add a bundle-first slide to the Show HN draft
- [ ] Reorder /spec sections: doc → bundle → hub


---

## Summary
The product is drifting from its core principle that URLs and markdown are the fundamental unit: feature breadth is growing faster than spine consolidation, and native skill positioning risks framing mdfy as a multi-AI tool rather than maintaining that one URL works everywhere. Three recovery moves are needed: add PR self-checks that prioritize URL value over alternative access paths, lock native skill positioning to emphasize the URL as the on-ramp, and promote bundle composition equally with hub in launch messaging.

## Themes
- URL as architectural core
- markdown-native design
- composable scope layers
- feature breadth vs positioning clarity
- cross-AI portability

## Key takeaways
- The eight founding principles exist to check whether current product direction maintains alignment with original thesis.
- Feature breadth is growing faster than spine consolidation, risking user confusion about what the product fundamentally is.
- Each new feature should increase URL value rather than simply provide another path to the same capability.
- Composable scopes (doc, bundle, hub) form the most differentiating aspect but are under-communicated relative to hub in marketing.
- The principle 'you write, the AI links' requires strict verb order to avoid positioning as AI-driven organization rather than AI-assisted authoring.

## Insights
- The product risks becoming a ChatGPT alternative rather than a URL-first platform if native skills are framed as separate per-AI implementations instead of on-ramps to shared URLs.
- Marketing emphasis on hub obscures bundle's differentiating value for per-project use cases like AGENTS.md and .cursor/rules.
- Zero friction to try versus zero friction to use well have diverged: account requirements for image rehost, edit tokens, and GitHub Actions represent a narrative shift the founders must acknowledge explicitly.

## Open questions / gaps
- What metrics or user feedback indicate whether users can articulate the eight-word core definition of mdfy after five minutes of use?
- How will the four native-skill implementations be rolled out without creating the 'separate per-AI product' framing that undermines the cross-AI moat principle?

## Concepts in this document
- **Chrome extension** _(entity)_
  Surface within memory.wiki ecosystem.
- **mdfy** _(entity)_
  A memory infrastructure layer that provides a URL-based knowledge hub for AI tools.
- **Claude** _(entity)_
  Specified AI tool for prototyping and validation before moving to high-fidelity design.
- **MCP server** _(concept)_
  A standard protocol allowing diverse AI tools to query and interact with the memory.wiki hub.
- **ChatGPT** _(entity)_
  One of the AI platforms currently suffering from isolated memory silos.
- **Electron desktop app** _(entity)_
  Current macOS/Windows distribution surface with high maintenance cost and limited unique value vs. web.
- **Competitive Positioning** _(tag)_
  Strategic differentiation from existing solutions in the AI memory and knowledge management space
- **Authored, not extracted** _(concept)_
  Principle that user intent comes first and AI linking is secondary, preventing product from reading as auto-organization tool.
- **Claude Skill** _(entity)_
  Web and desktop integration for Claude that reaches mobile and app surfaces the Chrome extension cannot cover.
- **Graph in response** _(concept)_
  Architecture where graph data lives in URL responses rather than behind service calls
- **Platform Integration** _(tag)_
  Category covering native AI platform skills and connectors implementation
- **Cross-AI structural moat** _(concept)_
  Competitive differentiation through one URL working across multiple AI platforms rather than fragmented per-AI variants.

## Concept relations (within this doc's concepts)
- **MCP server** integrates with **mdfy**
- **Claude Skill** demonstrates strategy **Platform Integration**
- **mdfy** distributed via **Chrome extension**
- **mdfy** integrates with **ChatGPT**
- **mdfy** integrates with **Claude**
- **Chrome extension** captures content for **mdfy**

## Bundles containing this document
- [Phase 2 strategy: connectors, replacements, first-principles](https://memory.wiki/b/Ih0eUczw)
  > Three working notes from a strategy review session on 2026-05-15. Native AI integrations roadmap, what current surfaces to replace, first-principles drift check.

_Hub canonical:_ https://memory.wiki/hub/raymindai
_Concept digest:_ https://memory.wiki/raw/hub/raymindai?digest=1&compact=1