---
title: "Context engineering: where it goes next"
url: https://memory.wiki/AXAIfrBG
updated: 2026-05-14T18:15:49.480Z
hub: https://memory.wiki/hub/demo
concept_count: 11
source: "memory.wiki"
---
# Context engineering: where it goes next

> Trend note, written 2026-05-12. I'll mark this as out of date if it doesn't hold up.

## The bet

The phrase "prompt engineering" is collapsing into "context engineering" over the next 12 months. Both will exist; one will become the load-bearing skill.

## What I'm seeing

Every AI tool that mattered in 2024 was a chat box. Every AI tool that matters in 2026 has at least one persistent context layer:

- Cursor — project context, sidebar history, AGENTS.md
- Claude Projects — project files, project instructions, scoped memory
- ChatGPT — GPTs, memory, project workspaces
- Codex CLI — AGENTS.md, conversation transcripts
- Claude Code — CLAUDE.md, hooks, MCP servers

They all converged on the same primitive: shaped, persistent context that lives outside the live conversation. The thing that varies between them is *how* you shape it, *where* it lives, and *which AI can read it.*

## Why this matters for mdfy

The convergence is the wedge. If shaped context is the new primitive, then a **portable** shape — one URL that every tool reads — is structurally valuable. AI companies can't build it because their incentive is the wall. The third party can.

## The risk

The big AI companies could decide to interoperate. Anthropic and OpenAI could agree on a common context format. If that happens, mdfy's "we make context portable" pitch is weaker.

## Why I don't think that's the world we're in

- **The wall is the business model.** OpenAI's revenue comes from people staying inside ChatGPT. Anthropic's comes from people staying inside Claude. Neither has a structural reason to make context portable across providers.
- **MCP is the closest they've come.** And MCP is a tool-call protocol, not a memory protocol. It doesn't make context portable; it makes individual function calls callable from multiple hosts.

## What I'd do differently if I'm wrong

If the AI companies do interoperate, mdfy still has a wedge: **authored** context, where the user writes what they want preserved. The portable layer is the easier win, but the authoring layer doesn't depend on portability surviving.


---

## Concepts in this document
- **mdfy** _(entity)_
  A tool that stores project context and decision history, integrated into Cursor via custom rules.
- **Cursor** _(entity)_
  Code editor that consumes mdfy bundles as context for chat and composer sessions.
- **ChatGPT** _(entity)_
  Example of an AI provider whose memory feature is intentionally confined to its own product.
- **MCP protocol** _(entity)_
  Existing tool-call protocol that enables function calls across hosts but does not make context portable.
- **Claude Projects** _(entity)_
  Production system implementing episodic snapshots pattern for comparison.
- **Prompt engineering** _(concept)_
  The prior dominant skill for AI tool interaction that is being displaced by context engineering as tools mature.
- **Persistent context layer** _(concept)_
  The critical shared primitive across all modern AI tools: shaped, persistent context that lives outside the live conversation.
- **Context engineering** _(concept)_
  The emerging load-bearing skill replacing prompt engineering, centered on shaped persistent context layers outside live conversation.
- **Walled business model** _(concept)_
  The structural incentive preventing AI companies from adopting portable context formats, as user retention drives revenue.
- **Portability** _(concept)_
  The strategic value proposition of making context readable across multiple AI tools via a common format and single URL.
- **Authored context** _(concept)_
  Fallback strategic wedge where users explicitly write preserved context, independent of industry-wide portability.

## Concept relations (within this doc's concepts)
- **mdfy** solves problem for **ChatGPT**
- **mdfy** integrates with **Cursor**
- **Persistent context layer** enables **Context engineering**
- **MCP protocol** partial but insufficient for **Portability**
- **Cursor** implements **Persistent context layer**
- **Portability** strategic advantage for **mdfy**
- **Claude Projects** implements **Persistent context layer**
- **Context engineering** displaces **Prompt engineering**
- **Walled business model** prevents adoption of **Portability**
- **Authored context** alternative wedge for **mdfy**
- **ChatGPT** implements **Persistent context layer**
- **mdfy** integrated into **Cursor**

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