Part 1 of 3

The Agentic AI Pyramid — Part 1 — The 5-Layer Map

A simple five-layer map of agentic analytics — and the plain-English difference between an LLM (Large Language Model), an AI agent and an AI platform.

In short


Why I drew this

For years I built marketing analytics the same way: GA4 (Google Analytics 4), Google Tag Manager, BigQuery, Looker Studio. Collect the data. Clean it. Build a report. Wait for somebody to open it.

In 2026 the last part changed.

Earlier this year I built a conversational AI agent for an SEO (Search Engine Optimisation) and content team, so people could ask questions in normal words instead of SQL. It worked. But the hard part was not the AI. It was everything under the AI.

The agent kept giving confident wrong answers. Not because the model was weak. Because it did not know what our team meant by "organic traffic", or which table was the good one. Nobody had written that down. A human analyst keeps it in their head. An agent cannot.

So I drew a pyramid. It helps me explain to clients why an agentic analytics project is 80% boring data work and 20% AI.

The Agentic AI Pyramid for Data Analytics Five layers. What each one does for a marketing team, and a few tools that live there. 5 Action 4 Thinking 3 Access 2 Meaning 1 Data Layer 5 — Action How do you get the answer? At 08:00 you get a message: costs rose 22% in one campaign. You decide what to do. PAID Power BI Copilot · Gemini Enterprise · Claude FREE Apache Superset · Metabase Layer 4 — Thinking Who finds the answer? You ask why costs rose. The agent tests four reasons and writes a short answer. PAID Claude Opus · GPT-5 · Gemini FREE Qwen3 · DeepSeek R1 Layer 3 — Access How does the agent read your data? You ask a question. The agent checks your real data before it answers. PAID BigQuery MCP · Snowflake MCP · Azure MCP FREE The MCP standard — free for everyone Layer 2 — Meaning What do your numbers mean? The company agrees what ROAS means. The agent uses that same rule. PAID Looker · Snowflake Semantic Views · Fabric IQ FREE Cube Core · dbt Core Layer 1 — Data Where is your data kept? Ad costs, website data and sales sit in one place. One question, one answer. PAID BigQuery · Snowflake · Microsoft Fabric FREE PostgreSQL · DuckDB Examples only — Part 2 has the full map. Build from the bottom up. Source: makskulish.com. Informational only; not advice. Believed accurate as of August 2026, without warranty. Vendors change names, features and licensing — check official sources before deciding. Trademarks belong to their owners.
The 5-layer Agentic AI Pyramid for Data Analytics

A note on the names

Most versions of this diagram say "tooling layer" and "orchestration layer". I used those words too, until a reader told me they were confusing.

He was right, and it is worth explaining why. Those names are different kinds of thing. "Reasoning" is something a model does. "Orchestration" is how you manage several agents. "Tooling" can mean almost anything. You cannot compare them, because they are not comparable.

So I renamed the layers. Each one now answers one plain question about the same journey:

Layer Name The question
1 Data Where is your data kept?
2 Meaning What do your numbers mean?
3 Access How does the agent read your data?
4 Thinking Who finds the answer?
5 Action How do you get the answer?

If you have seen the industry words: Data = data foundation, Meaning = semantic and context layer, Access = tooling, Thinking = reasoning and orchestration, Action = the top of the pyramid.

Each layer needs the one below it. That is the only rule the pyramid is trying to show.


LLM, AI agent, AI platform — what is the difference?

People use these three words as if they mean the same thing. They do not. And they are not three sizes of one product.

The easiest way to see the difference is to think about hiring somebody.

Think of it as hiring somebody The easiest way to tell an LLM, an AI agent and an AI platform apart. AN LLM · THE BRAIN A clever new person, on their first day ? Fast. Has read a lot. Has never seen your company. Ask about last month and they will guess — politely. AN AI AGENT · THE EMPLOYEE The same person, after you give them 3 things a key a dictionary a job A key — to open your systems. A dictionary — what your words mean. A job — finish it, then report back. Same brain. Now useful. AN AI PLATFORM · THE WORKPLACE One supplier sells you the whole office The building, the filing cabinets, the locks and keys — and the person. Snowflake, Microsoft Fabric, Google Cloud, Gemini Enterprise. In 2026 it is rarely one new hire — it is a small team Layer 4 usually runs several narrow agents. They check each other, so mistakes are caught before they reach you. The analyst Pulls the ROAS numbers. Employee A The checker Tests the work against the dictionary. Employee B The writer Turns it into a short summary for you. Employee C A bigger brain does not fix a missing dictionary. It just makes the guessing sound better. The layers are horizontal. Agents and platforms are vertical. So “we bought an AI agent” tells you nothing about whether your dictionary exists. Writing it is your job. agent Source: makskulish.com. Informational only; not advice. Believed accurate as of August 2026, without warranty. Vendors change names, features and licensing — check official sources before deciding. Trademarks belong to their owners.
LLM, AI agent and AI platform explained as hiring a new person

The LLM — the brain

The model that reasons and writes text: Claude, GPT, Gemini, Llama.

Think of a clever new person on their first day. Fast. Has read a lot. Has never seen your company.

Ask how your ROAS (Return on Ad Spend) was last month and you will get an answer. It will sound good. It will be invented, because they had nothing to look at.

A bigger model does not fix this. When a new hire does not know but wants to impress you, they guess something that sounds right. That is exactly what a wrong AI answer is: confidence without anything behind it. A bigger brain only makes the guess sound better.

This matters when you are choosing tools. Moving from a mid-size model to the biggest frontier model does not give the model your data. It buys you a slightly better guesser.

The AI agent — the employee

The same brain, after you give it three things:

  1. A key — access to your systems, so it can look instead of guess. (Layer 3)
  2. A dictionary — what your company's words and numbers mean. (Layer 2)
  3. A job — something to finish, and a way to report back. (Layers 4 and 5)

Same brain. Now useful.

One more thing has changed recently. In 2026 an agent is rarely one person. It is usually a small team of specialists:

This is why agentic AI works better than one very long prompt. The agents catch each other's mistakes before anything reaches you. A single model answering in one pass has nobody checking it.

The AI platform — the workplace

One supplier selling you several layers bundled together: the building, the filing cabinets, the locks and keys, and the person. Snowflake, Microsoft Fabric, Google Cloud, Gemini Enterprise.

LLM, AI agent, AI platform — what is the difference? They are not three sizes of the same thing. The LLM is one layer. The other two are bundles that cut across layers. comes in the box it uses this — but you have to build it yourself THE FIVE LAYERS WHAT IS ACTUALLY BEING SOLD TO YOU Layer 5 — Action Sends you the answer. You decide what to do. Layer 4 — Thinking Finds the answer. Layer 3 — Access Opens your systems and looks things up. Layer 2 — Meaning Explains what your words and numbers mean. Layer 1 — Data Keeps all your data in one place. LLM the brain, on its own AI agent the brain, given a job needs yours nobody can sell it to you AI platform one vendor, many layers Think of hiring somebody An LLM is a clever new person on their first day. Fast, well read — and has never seen your company. Ask about last month’s results and they will guess. Politely, and with confidence. An AI agent is that same person after you give them three things: a login to your systems, a handbook that explains what your words mean, and a job to finish and report back. Same brain. Now useful. An AI platform is one supplier selling you the office, the filing cabinets, the login system — and the person. Nobody sells you the handbook. Writing it is Layer 2 — and that is where most projects quietly fail. Source: makskulish.com. Informational only; not advice. Believed accurate as of August 2026, without warranty. Vendors change names, features and licensing — check official sources before deciding. Trademarks belong to their owners.
Where the LLM, the AI agent and the AI platform sit across the five layers

The layers are horizontal. Agents and platforms are vertical.

An agent does not bring your dictionary — it reads yours. Nobody can sell you the definition of your own ROAS. A vendor gives you the place to write it down; writing it is your job.

So when somebody says "our AI agent will answer your business questions", ask one thing: whose dictionary does it read? If the answer is "it works that out automatically", you now know which layer will fail first.


The five layers in one minute each

Part 2 goes through the tools on each layer. Here is the short version, so the map makes sense on its own.

Layer 1 — Data. One place where everything lives, in tables an agent can read. Your GA4 events, Google Ads costs, CRM (Customer Relationship Management) deals and offline orders together, instead of five exports that never match. If you already use BigQuery, Snowflake or Microsoft Fabric, this layer is done.

Layer 2 — Meaning. The layer that explains your business to the agent. What "active customer" means. Which of the six revenue columns is real. Which table is old. It has three parts: a semantic model for your numbers, vector search and RAG (Retrieval-Augmented Generation) for your documents, and a catalog for your rules. This is the layer that decides whether the project works, and it is the one nobody can sell you.

Layer 3 — Access. The key. Without it, the agent can only talk. With it, the agent can look things up in your systems and show you where the number came from. In 2026 this mostly means MCP (Model Context Protocol), the open standard almost every vendor now supports.

Layer 4 — Thinking. Where the model lives — and only here. It splits a big question into small steps, checks each one, and fixes mistakes. Two parts: the model (the brain) and the framework that manages several agents (the manager). People confuse these two constantly, and I will untangle them properly in Part 2.

Layer 5 — Action. How the answer reaches a person. Nobody opens a dashboard; at 08:00 you get a message saying paid search cost per order rose 22%, which campaign it was, and what changed on Monday. Then you decide what to do about it.


Where to start

Three steps, in order. This is the part people get wrong most often.

Step 1. Write down ten definitions.

Not a hundred. Ten. The ones your leadership actually asks about. Put them in a semantic model — LookML, dbt, Cube, Snowflake Semantic Views, a Power BI semantic model. Whatever your stack already uses.

This is unglamorous and it is the highest-value week you will spend on this whole subject.

Step 2. Connect one agent to one question.

Pick a question you get every week. "What did we spend on paid media yesterday, by channel?" Give the agent read-only access. Test it against answers you already know are correct.

Do not go live until it gets twenty known questions right in a row.

Step 3. Add one alert.

Only after step 2 works. One metric, one threshold, one channel — and check who is in that channel before you switch it on.

Most teams try to start at step 3. That is how you end up with an expensive chatbot nobody trusts.


Glossary

Every word in this series, in plain English.

Word What it means Layer
LLMthe brain The model that reasons and writes text (Claude, GPT, Gemini, Llama). General knowledge, but it cannot see your company's data by itself. 4
AI agentthe employee The LLM given a system login, a company dictionary and a specific job. It reads your Layers 1 and 2 — it does not supply them. 3–5
AI platformthe workplace One supplier selling you several layers bundled together (Snowflake, Microsoft Fabric, Google Cloud). 1–5
Semantic model Your business rules written once: what revenue is, how ROAS is calculated, who may see what. 2
Vector database A store that lets you search text by meaning, not exact words. 2
RAG The agent searches your documents first, then answers from what it found. 2
MCP A free open standard for plugging an agent into a data source. Like USB, but for AI tools. 3
Multi-agent Several narrow agents doing one step each, instead of one agent doing everything. 4
Open source Free to self-host. Often has a paid cloud or enterprise tier alongside — that is normal, not a trick. any
Open weights You can download and run the model, under the vendor's own licence. Not the same as open source. 4
Human in the loop A person approves before anything changes for real. all

Coming next

Part 2 — The tools on each layer. What Google Cloud, Snowflake, Microsoft, OpenAI and Anthropic actually sell on each layer, which free open-source tool does the same job, and whether open source is really free and really safe.

Part 3 — Privacy, security and the human in the loop. The risks that are specific to each layer, including the one almost nobody plans for: how a vector database quietly becomes a data leak.


Disclaimer

Informational only; not advice. Believed accurate as of August 2026, without warranty. Vendors change names, features and licensing — check official sources before deciding. Trademarks belong to their owners.

This article reflects my personal views, not those of any employer or client.

I write about data, analytics and AI at makskulish.com. You can also find me on LinkedIn.