==========================================================
GUARDRAILS — EASY SETUP GUIDE (no engineering degree needed)
Aigis · Divine Shield against data tampering
==========================================================

WHAT THIS DOES (in plain English)
----------------------------------------------------------
Right now your app talks directly to the AI company
(Anthropic or OpenAI). Guardrails sits in the middle, like
a notary: every question and answer passing through gets a
permanent, tamper-proof seal. Your app works exactly the
same — same answers, same speed — but now you have proof of
everything your AI ever said.

You do NOT need to rewrite your app. You change ONE setting:
the "address" your app sends AI requests to.

WHAT YOU NEED
----------------------------------------------------------
1. Your Guardrails API key  — shown in your dashboard after
   signup (starts with "gr_")
2. Your existing AI API key — the Anthropic key (starts with
   "sk-ant-") or OpenAI key (starts with "sk-") your app
   already uses
3. Access to your app's code, OR a developer/AI assistant
   who can paste in a few lines for you

----------------------------------------------------------
OPTION A — LET AN AI DO IT FOR YOU (easiest)
----------------------------------------------------------
If you use Claude, ChatGPT, Copilot, Cursor, or any AI
coding assistant, paste this prompt into it:

  "Find where this project creates its Anthropic or OpenAI
   client. Add a baseURL option pointing to
   https://aigisguardrails.com/anthropic (or /openai for
   OpenAI) and add these default headers:
   X-Audit-Key: <my Guardrails key>
   X-Provider-Key: <my existing AI key>
   Don't change anything else."

Replace the two <...> parts with your real keys. The
assistant will find the right file and make the change.

----------------------------------------------------------
OPTION B — DO IT YOURSELF (JavaScript / TypeScript)
----------------------------------------------------------
1. Open your project and search all files for the text:
      new Anthropic(        (or "new OpenAI(")
2. You'll find something like:

   const client = new Anthropic({
     apiKey: process.env.ANTHROPIC_API_KEY,
   })

3. Add the lines marked NEW:

   const client = new Anthropic({
     apiKey: process.env.ANTHROPIC_API_KEY,
     baseURL: 'https://aigisguardrails.com/anthropic',   // NEW
     defaultHeaders: {                                    // NEW
       'X-Audit-Key':    'gr_your_key_here',              // NEW
       'X-Provider-Key': process.env.ANTHROPIC_API_KEY,   // NEW
     },                                                   // NEW
   })

4. Save, restart your app. Done.

----------------------------------------------------------
OPTION C — DO IT YOURSELF (Python)
----------------------------------------------------------
1. Search your project for:
      Anthropic(            (or "OpenAI(")
2. Change it to:

   client = Anthropic(
       api_key=os.environ["ANTHROPIC_API_KEY"],
       base_url="https://aigisguardrails.com/anthropic",   # NEW
       default_headers={                                    # NEW
           "X-Audit-Key": "gr_your_key_here",               # NEW
           "X-Provider-Key": os.environ["ANTHROPIC_API_KEY"],  # NEW
       },                                                   # NEW
   )

3. Save, restart. Done.

For OpenAI, use base_url ".../openai" instead.

----------------------------------------------------------
HOW TO KNOW IT'S WORKING
----------------------------------------------------------
1. Use your app normally — ask your AI something.
2. Log into your console at console.aigisguardrails.com
3. You should see the call appear in "Audit Events" within
   seconds. After ~30 seconds its status turns to
   "committed" — that means it's permanently sealed on the
   blockchain.

----------------------------------------------------------
OPTIONAL EXTRAS
----------------------------------------------------------
Want to know WHICH user each conversation was with? Add two
more headers wherever you made the change above:

   'X-Actor-Id':   the logged-in user's ID
   'X-Session-Id': the conversation/chat ID

These show up in your audit log so you can search by person
or conversation later.

----------------------------------------------------------
TROUBLESHOOTING
----------------------------------------------------------
"401 Missing X-Audit-Key"   → the headers didn't get added;
                              re-check step 3.
"401 Invalid API key"       → typo in your gr_ key, or your
                              account is inactive.
"400 Missing X-Provider-Key"→ your AI key isn't being passed
                              through; check that header.
App errors after the change → remove the baseURL line and
                              your app instantly goes back
                              to talking to the AI directly.
                              Nothing breaks permanently.

Questions? support@aigisguardrails.com
==========================================================