# Why PILSO

The crypto world is rapidly converging with AI — but most attempts to combine them are either superficial or insecure.

Smart contract interfaces are too technical. Wallets are isolated. LLMs are powerful, but untrusted. What’s missing is a **secure, programmable layer between intelligent agents and onchain execution**.

That’s exactly what PILSO provides.

***

#### The Problem: AI agents can’t sign securely

Many LLM-based tools have been built to “talk” to the blockchain — but they all hit the same wall:

> ✅ The LLM understands what to do\
> ❌ But it can’t **safely sign the transaction**

This leads to broken UX and dangerous tradeoffs:

* Agents that require the user’s private key (!)
* Bots that act as middlemen between the user and the chain
* Custom custodial wallets acting on behalf of LLMs

These are **non-starters** for serious users, institutions, and developers.

***

#### The Solution: Keep the signer, separate the brain

PILSO OS makes it possible to **safely delegate intent to agents**, without ever handing them control of your assets.

It separates:

* **The brain (LLM)** → interprets your goals
* **The hand (MCP tools)** → constructs the correct onchain action
* **The key (your wallet)** → signs it securely, with no exposure

***

#### The Missing Piece in the Crypto Stack

PILSO isn’t just a product — it’s a protocol-level primitive that slots into any agent architecture, LLM pipeline, or crypto infrastructure.

| Layer     | Tools              |
| --------- | ------------------ |
| LLM       | Claude, GPT...     |
| Execution | MCP server modules |
| Signer    | MetaMask           |

PILSO OS makes these layers work together safely, modularly, and transparently — without breaking trust boundaries.

***

#### Why now?

* **Wallets are standardizing** — MetaMask, Safe, WalletConnect all support signing APIs.
* **LLMs are programmable** — Open tools like Claude and GPT can now be directed like functions.
* **AI-native UX is rising** — Smart interfaces will soon outpace dApp UIs.
* **Security expectations are rising** — Users no longer accept bots with access to keys.

PILSO meets this moment with real infrastructure — not hype.

***

#### In short: Why PILSO?

Because crypto needs **secure agents**, not bots.\
Because AI needs **wallet-level permissions**, not private keys.\
Because modular infra always wins.


---

# 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://docs.pil.so/introduction/why-pilso.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.
