A context layer built for AI agents.

import requests, os

HEADERS = {"X-API-Key": os.environ["SENSO_KEY"]}
BASE    = "https://apiv2.senso.ai/api/v1"

# 1 — Ingest a document
upload = requests.post(f"{BASE}/org/kb/upload",
    headers=HEADERS,
    json={"files": [{"filename": "policy.pdf", ...}]})
content_id = upload.json()["results"][0]["content_id"]

# 2 — Search verified knowledge
result = requests.post(f"{BASE}/org/search",
    headers=HEADERS,
    json={"query": "What is the refund policy?"}).json()

print(result["answer"])
# → "Customers may request a full refund within 30 days..."

How it works

Quick start

# pip install requests
import hashlib, os, requests

KEY  = os.environ["SENSO_KEY"]
BASE = "https://apiv2.senso.ai/api/v1"
HDR  = {"X-API-Key": KEY, "Content-Type": "application/json"}

file_bytes = open("your-doc.pdf", "rb").read()

resp = requests.post(f"{BASE}/org/kb/upload", headers=HDR, json={
    "files": [{
        "filename":         "your-doc.pdf",
        "file_size_bytes":  len(file_bytes),
        "content_type":     "application/pdf",
        "content_hash_md5": hashlib.md5(file_bytes).hexdigest(),
    }]
})
upload = resp.json()["results"][0]
requests.put(upload["upload_url"], data=file_bytes)
content_id = upload["content_id"]
print(f"Ingested. content_id: {content_id}")

import time

while True:
    item = requests.get(
        f"{BASE}/org/content/{content_id}",
        headers={"X-API-Key": KEY},
    ).json()
    if item["processing_status"] == "complete":
        break
    time.sleep(1)

print("Ready.")

answer = requests.post(f"{BASE}/org/search", headers=HDR, json={
    "query":       "What does this product do?",
    "max_results": 3,
}).json()

# Grounded answer — relay directly to your user or agent
print(answer["answer"])

# Source citations included
for r in answer["results"]:
    print(f"  [{r['score']:.2f}] {r['title']}")

result = requests.post(
    f"{BASE}/org/content-generation/sample",
    headers=HDR,
    json={
        "geo_question_id": "your-prompt-id",
        "content_type_id": "your-content-type-id",
    }
).json()

print(result["raw_markdown"])

Getting started

If you are an AI agent

The core loop: ingest → search → generate

No OAuth flows, no token refresh — one key, scoped to your org. Ask your human operator to sign up and generate an organization-scoped API key.

API endpoints

CLI for agents

Claude Code, Gemini CLI, and OpenAI Codex can call the Senso CLI directly from their tool-use loop.

npm install -g @senso-ai/cli

Set SENSO_API_KEY as an environment variable. Use --output json and --quiet for structured output.

Key commands: senso search, senso ingest, senso generate, senso kb, senso brand-kit, senso content-types. Run senso --help for the full list.

Agent skills

Portable instruction sets that teach AI coding agents how to use Senso. Follow the open Agent Skills standard. Work with Claude Code, Cursor, Codex, GitHub Copilot, Gemini CLI, and Cline.

senso skills install --all

Available skills:

Skills activate automatically based on conversation context once installed.

Reference

Supported file formats

HTTP status codes