DMOOP API Reference

Base URL

https://www.dmoop.com/api/v1

Authentication

All requests require an Authorization header:

Authorization: Bearer dmoop_live_<your-key>

Generate keys at /settings/api-keys. Each key is shown once at creation — save it in your secrets manager. If lost, revoke and regenerate. Keys inherit the owning user's brand agents and documents.

POST /api/v1/chat

Generates a completion, optionally grounded in a brand agent's voice profile + top brand documents.

Request body

Response

Status codes

Example — cURL

curl https://www.dmoop.com/api/v1/chat \
  -H "Authorization: Bearer dmoop_live_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Write 3 LinkedIn ad headlines for our new AI-accelerated data platform.",
    "agent_id": "YOUR_AGENT_UUID"
  }'

Example — Node.js (fetch)

const res = await fetch("https://www.dmoop.com/api/v1/chat", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.DMOOP_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "Write 3 LinkedIn ad headlines for our new AI-accelerated data platform.",
    agent_id: process.env.DMOOP_AGENT_ID,
  }),
});
const data = await res.json();
console.log(data.response);

Example — Python (requests)

import os, requests

r = requests.post(
    "https://www.dmoop.com/api/v1/chat",
    headers={"Authorization": f"Bearer {os.environ['DMOOP_API_KEY']}"},
    json={
        "prompt": "Write 3 LinkedIn ad headlines for our new AI-accelerated data platform.",
        "agent_id": os.environ["DMOOP_AGENT_ID"],
    },
    timeout=60,
)
r.raise_for_status()
print(r.json()["response"])

Example — multi-turn conversation

curl https://www.dmoop.com/api/v1/chat \
  -H "Authorization: Bearer dmoop_live_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "YOUR_AGENT_UUID",
    "messages": [
      { "role": "user",      "content": "Write a landing page hero for our AI Engineering practice." },
      { "role": "assistant", "content": "…first draft here…" },
      { "role": "user",      "content": "Shorten the sub-headline to under 12 words." }
    ]
  }'

Brand grounding

When agent_idis provided (and owned by the API key's user), DMOOP injects:

• The agent's voice profile (tone, audience, preferred vocab, terms to avoid)
• The top-4 brand documents most relevant to the user prompt via similarity retrieval

No brand context is injected when agent_id is omitted. To get the most on-brand output, always pass agent_id and keep the corresponding agent's brand library up to date at /brand.

Support

Bug reports and integration questions: support@dmoop.com. Include the request timestamp and the response body — never the API key itself.