What Is a Context Layer? A Plain-Language Guide

In the previous piece we argued that your AI tools underperform because they have no memory of your business. The fix is a context layer. Below is what that is, in plain language, with enough detail that you could sketch it on a whiteboard afterward.

One sentence first

A context layer is one memory of your business that every AI tool you use can read from and save to.

It is not a chatbot, and it is not another app your team has to live in. It sits underneath the tools, the way a database sits underneath your website. Your AI tools do the thinking, and the layer remembers. People on the team can open it to see what was saved and by whom, or to ask it a question, but mostly they notice that every AI tool they use already knows the company.

The three moving parts

1. AI tools save to it. The AI tools your team already uses (ChatGPT, Claude, Claude Code, Cursor) connect to the layer once. From then on, as they work, they save what matters: the decision made on a call and why, the commitment a client is waiting on, a new contact, the note that explains how an account really works. Where the work involves another app (a calendar, a CRM, a transcript tool), the AI tool reaches that app through its own connectors, does the work, and saves what is worth keeping. You can also drop files in directly: documents, a whole folder, a zip. Your team does not have to change much about how it works, and that is deliberate: systems that depend on people stopping to type things in tend to go unused. Here the saving is done by the tools that were already doing the work.

2. The layer keeps itself in order. This is what makes a context layer different from a pile of notes. Every memory has a type: a note, a decision (which must carry its reason), a task (open or done, with an owner and a due date), a person, a customer, a meeting, a file, or part of your identity, such as your values or your voice. Memories link to each other, so a customer connects to their people, their meetings and the decisions made about them. The layer writes Summaries: a plain account of each day, rolled into weeks and months, so the picture stays readable as it grows. A tool that tries to save something already there under the same name is pointed to the existing memory to update instead, and is told about lookalikes. Every change records who made it, with which tool, and what it was before. The next piece unpacks the structure itself; it is simpler than you would expect.

3. AI tools read from it. Any AI tool that supports MCP (the open standard AI tools use to connect to other services) can ask the layer: who is this person, what is open with this account, what did we decide about pricing, what changed this week. At the start of a session it gets a brief: what the memory is for, what happened recently, and what changed since it was last there. Searches work by meaning, not just keywords. And because there is only one memory, two different tools asked the same question give the same answer.

What a brief looks like

Here is an illustration of the kind of brief an AI tool receives when a session starts. The names are invented.

Engine: Client work
Purpose: Everything about our client relationships: who they are,
what we promised, what we decided. Not internal HR or finance.

Recently
- Meridian Freight quarterly review (Tue): agreed to move to annual
  pricing; Sarah asked for a revised proposal by Friday.
- Decision: annual-only pricing for new customers (rationale saved).
- Task: send Meridian revised proposal, owner Deniz, due Fri.

Since you were last here
- 3 new memories from ChatGPT · Deniz
- Task "Meridian onboarding checklist" marked done

The tool starts the conversation already knowing this, without you pasting anything.

A day in the life, concretely

Tuesday, 8:30 a.m. You open Claude and ask it to prepare you for today’s calls. Claude reads your calendar through its own calendar connector, then looks up each attendee and account in the memory: who they are, where things stand, what is open. Nobody assembled that by hand. (The pre-meeting briefs piece goes deeper.)

10:00. The client call happens. Afterwards you hand the transcript to your AI tool and say “save what matters.” It saves the meeting, the decision made on the call with its reason, and the two commitments, yours and theirs, as tasks with owners and due dates.

10:45. Your colleague asks ChatGPT for the follow-up email. ChatGPT already knows both commitments and the decision, because it reads the same memory Claude just saved to. The draft is right the first time.

6:00 p.m. The Summaries tab has the day written up: what moved, what was decided, what is open going into tomorrow.

Nobody maintained a knowledge base at any point. The tools saved as they worked, and the layer kept it in order. Over a year that adds up: each day’s work gives every later task more to start from.

What a context layer is not

Several things are called “memory”, so it helps to be precise:

• It is not the memory feature inside ChatGPT or Claude. Those are personal and tied to one vendor: they remember your preferences, inside one product. A context layer is shared and neutral: it remembers the business, for every tool.
• It is not enterprise search. Search finds documents when you ask. A context layer holds a structured picture and hands your AI tools the slice they need. The difference shows in the questions each can answer: search handles “find the Meridian contract”; the layer handles “what do we owe Meridian and why?”
• It is not a wiki or a knowledge base. Wikis go out of date because people have to maintain them, and people are busy. The layer is written to by the tools doing the work, so it stays current as a side effect of the work.
• It is not a vector database. Technical people on your team may ask about this. Search by meaning is a useful index inside a context layer, but “throw everything in and search by similarity” produces a heap of fragments rather than a picture of a business. What matters is the structure (typed memories, links, history); similarity search is one part underneath it.
• It is not tied to one AI vendor. Models will keep overtaking each other every year. The layer is where accumulated knowledge lives, so you can swap tools freely and lose nothing. Why that may matter more than model choice is the subject of One brain, many agents.

The questions owners actually ask

“Where does it run?” Context Engine is a hosted service at app.contextengine.com. Each engine, which is what we call one memory, gets its own database, its own search index and its own Worker, so isolation is physical rather than a filter on a shared table. What you save is never used to train models, and you can export the whole engine as Markdown and JSON that opens without us. Piece five takes the ownership question head on.

“Can it act on its own? Send things?” No, by design. The layer holds memory and answers questions. It does not run your agents and it does not reach into your other apps. Your AI tools, which you authorize, do the acting.

“What does my team have to change?” Very little. Each person connects their AI tool once and gets used to saying “save that” at the end of work that matters. Every so often someone looks at Memories, archives what is stale, and corrects what is wrong, which is what keeps the memory trustworthy. Otherwise the change is that people stop pasting context into their AI tools, because it is already there.

“How is this different from just buying more AI tools?” Without a shared layer, every new tool adds another silo. With one, every new tool arrives already knowing the company, and every tool you retire leaves its knowledge behind.

Build this yourself

1. Create an engine and give it a purpose: a few sentences on what it is for and what does not belong. AI tools read the purpose to decide what to save there.
2. Connect two AI tools you actually use, say Claude and ChatGPT, each with Can read and save. For Claude Code it is one command: claude mcp add --scope user --transport http ce-clients https://app.contextengine.com/mcp/c/<id>, with the address the app gives you.
3. Have one tool save a decision and its reason. Then ask the other tool what was decided, and check Memories to see both the decision and who saved it.

Start free, or see plans.

Why “layer” is the right word

Because it is infrastructure. Businesses already accept this for their data: every serious company runs on a database, and nobody considers it optional. A context layer does the same for what your AI tools know. The tools on top will keep changing. The memory underneath should stay put, and it should be yours. Next in this track: how the layer actually structures a business, and further on, the question that follows from concentrating all this in one place: who should own it.