# Welcome

Welcome to the official documentation for **@ai.ntellect/core**, the framework for building production-grade LLM agents that don't drift.

## The Core Thesis

**LLMs are exceptional at generating text, but they are unreliable at controlling systems.**

Most AI frameworks treat the LLM as the "brain" that makes every routing decision. As your agent grows in complexity, this leads to:

* **Routing Hallucinations**: The LLM forgets the rules and calls tools in the wrong order.
* **Context Bloat**: The prompt grows too large as it tries to explain every possible path.
* **Unpredictability**: The same input can lead to different execution paths.

**@ai.ntellect/core solves this by splitting the brain:**

1. **The LLM is the Classifier**: It identifies *intent* once.
2. **The System is the Controller**: A verified Petri Net handles the *routing* deterministically.
3. **GraphFlow is the Executor**: Typed graphs handle the *execution* without further LLM interference.

***

## 🧭 Navigation Guide

### 🚀 Getting Started

* [Quick Start Guide](/core/getting-started/pour-commencer.md) — From `npm install` to your first workflow in 5 minutes.
* [The Philosophy](/core/getting-started/philosophie.md) — Understand why deterministic control is the only way to scale AI agents.
* [Key Concepts](/core/getting-started/concepts-cles.md) — GraphFlow, CortexFlow, and State Management.

### 🛠️ The Engine

* [GraphFlow Deep Dive](/core/the-engine-core/graphflow.md) — Nodes, Parallelism, and the Send API.
* [Event-Driven Architectures](/core/the-engine-core/les-evenements.md) — Building reactive systems that wait for the world.
* [Resilience & Checkpoints](/core/the-engine-core/checkpoint.md) — Time-travel debugging and human-in-the-loop.
* [Technical Architecture](/core/the-engine-core/architecture.md) — The blueprint of the engine.

### 🧠 AI Orchestration (CortexFlow)

* [Deterministic Routing](/core/the-engine-core/graphflow.md) — How intent classification works.
* [Formal Verification](/core/the-engine-core/architecture.md) — Deadlock detection and reachability analysis.
* [Hybrid Fallback](/core/the-engine-core/architecture.md) — Balancing determinism with conversational flexibility.

### 🧩 Modules & Tooling

* [Memory Systems](https://github.com/ai-ntellect/core/blob/main/docs/modules/memoire/README.md) — Pluggable persistence (Redis, Meilisearch).
* [Agenda & Scheduling](https://github.com/ai-ntellect/core/blob/main/docs/modules/agenda/README.md) — Cron-based automation.
* [Interactive CLI](/core/modules-and-tooling/cli.md) — Debugging and running agents from your terminal.

### 📈 Real-World Application

* [Design Patterns](https://github.com/ai-ntellect/core/blob/main/docs/cas-dusages.md) — How to model Approval Flows, RAG, and ETL pipelines.
* [Benchmarks](/core/the-engine-core/benchmark.md) — CortexFlow vs LangGraph: Performance and Reliability.

***

## 🛠️ Quick Reference

| If you want to...                    | Go to...                                           |
| ------------------------------------ | -------------------------------------------------- |
| Build a simple sequence of tasks     | [GraphFlow](/core/the-engine-core/graphflow.md)    |
| Create an agent that handles intents | [CortexFlow](/core/the-engine-core/graphflow.md)   |
| Make a workflow pause for a human    | [Checkpoints](/core/the-engine-core/checkpoint.md) |
| Trigger a workflow via Webhook       | [Events](/core/the-engine-core/les-evenements.md)  |
| Run an agent in your terminal        | [CLI](/core/modules-and-tooling/cli.md)            |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://ai-ntellect.gitbook.io/core/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.