---
mw_bundle: 1
id: bf24c8b646ef
title: "App Store submission checklist"
url: https://memory.wiki/b/bf24c8b646ef
document_count: 2
updated: 2026-06-15T16:53:47.121Z
analysis_generated_at: 2026-06-15T16:53:47.121Z
source: "memory.wiki"
---
# App Store submission checklist

> App Store submission checklist — a curated set of memories grouped by theme. Reviewer note: this is generated demo content.

**Intent:** decompose

## Summary

The documents collectively explore a shift from retrieval-centric design to delivery-centric UX in long-context models, emphasizing how to surface the right information rather than simply fetch it. Across multiple pieces, there is a repeated emphasis on branding as a systemic design principle, the importance of error messaging, and practical rules for product delivery (ship deeply, interface is the product, keep things simple). The bundle also highlights the idea that durable infrastructure (permalinks/public URLs) and performance considerations shape how the user experiences and trusts a knowledge tool.

## Themes

- Long-context models
- Delivery-first UX
- Branding as system-wide discipline
- Error messaging design
- Durable infrastructure (permalinks)

## Cross-document insights

- Delivery-centric framing reframes resource allocation: invest in output surfaces and user-facing flow rather than solely chasing retrieval accuracy.
- Branding consistency is treated as a core product trait, not marketing fluff, signaling a holistic design philosophy.
- A simple playbook (ship deeply, interface is the product, one-screen rule) recurs across authors, suggesting tacit product discipline.
- Permalinks/public URLs emerge as a resilience principle to survive vendor pivots and maintain context.

## Key takeaways

- Long-context models can reduce retrieval friction by shifting focus to what to show.
- A repeatable product playbook (ship deeply, branding, interface-first) governs multiple docs.
- Permalinks/public URLs emerge as a durable infrastructure principle for resilience.

## Open questions / gaps

- Lack of concrete user stories or success metrics comparing long-context vs. retrieval-focused approaches.
- Missing explicit discussion of security/privacy considerations and scalability implications for real-world deployments.

## Notable connections

- **doc:50bca01254b9** ↔ **doc:53bac621b960** — Shared thesis on long-context and retrieval reduction
- **doc:50bca01254b9** ↔ **doc:c9e5203af6ee** — Delivery-first framing echoed
- **doc:6263deae1899** ↔ **doc:53bac621b960** — Permalink idea appears in longer context discussion
- **doc:765898a65d1f** ↔ **doc:e4305e5f15fe** — Error messaging and branding intersect across texts
- **doc:7fd64130bf2d** ↔ **doc:8476baa9a014** — Branding and open questions recur together

## Concepts (this bundle)

- **Long-context models**
- **Retrieval optional**
- **Delivery vs Retrieval**
- **Output-heavy value**
- **Permalink infrastructure**
- **Error message structure**
- **Three rules**
- **Interface is the product**
- **Anything fits on one screen**
- **Edge cache**
- **URL title script**
- **Branding principle**

## Documents

### 1. [Reading: Karpathy on LLM evals](https://memory.wiki/c9e5203af6ee)
A good error message answers three questions: what happened, why it happened, and what to try next. Most ship the first, hint at the second, and forget the third. The fix is usually a single sentence longer.

### 2. [Reading log: October-November](https://memory.wiki/53bac621b960)
The interesting thing about long-context models isn't that they can read more — it's that they finally make the *retrieval* problem optional. When a model can hold the whole repo in context, the question shifts from "what should I fetch?" to "what should I show?". That's a UX question, not an infrastructure one.


_Digest view — follow any link above to fetch that doc's full markdown. Add `?full=1` to this URL for the concatenated payload._