Screen Every Inbound Call at the Carrier Edge: A Fraud Firewall in 178 Lines of Python

A developer built an Edge Fraud Firewall in 178 lines of Python that screens inbound calls at the carrier edge using Telnyx APIs and AI inference. The system classifies callers as CLEAN, SUSPICIOUS, or BLOCK, routing suspicious calls to a honeypot that wastes scammers' time.

Originally published on lowlatencyclub.ai Every inbound call is a decision. Is this caller legitimate, or is it a scammer, robocaller, or toll-fraud bot? Most systems make that decision too late — after the call reaches the application layer, consuming resources and potentially connecting to a human agent who wastes 5 minutes on a fake call. The Edge Fraud Firewall flips the order. It screens every inbound call at the carrier edge — before your app sees it — using three Telnyx APIs on a single platform: Number Lookup for caller identity, AI Inference for risk classification, and Call Control for reject/forward/route decisions. The entire firewall is 178 lines of Python in a single Flask file. When a call hits a Telnyx number, the platform sends a call.initiated webhook to the Flask server. Before doing anything else, the server verifies the Ed25519 webhook signature — if the request is not from Telnyx, it returns 401 and stops. For verified webhooks, the screening pipeline runs in order: CLEAN , SUSPICIOUS , or BLOCK . CLEAN → answer and forward to your real number SUSPICIOUS → answer and route to a honeypot endless hold loop BLOCK → reject and add to the blocklistThe system prompt is deliberately constrained — one word only: python def classify caller phone, lookup data : try: resp = requests.post INFERENCE URL, headers=HEADERS, timeout=15, json={ "model": AI MODEL, "messages": {"role": "system", "content": "You are a fraud detection system. Analyze caller data and respond with ONLY one word: CLEAN, SUSPICIOUS, or BLOCK."}, {"role": "user", "content": f"Caller: {phone}\nCarrier: {lookup data.get 'carrier', {} .get 'name', 'unknown' }\nType: {lookup data.get 'carrier', {} .get 'type', 'unknown' }\nCountry: {lookup data.get 'country code', 'unknown' }"} } if resp.ok: return resp.json "choices" 0 "message" "content" .strip .upper except Exception as e: app.logger.error "Classification failed: %s", e return "CLEAN" One-word output keeps inference latency to a single token and makes parsing trivial — no JSON, no regex, just a string comparison. If the AI call fails for any reason, the function defaults to CLEAN . This is a safe-fail — if the screening service is unavailable, legitimate callers still get through. When the AI classifies a call as SUSPICIOUS , the firewall routes it to a honeypot instead of rejecting or forwarding. The honeypot answers the call and plays a hold message, then loops indefinitely: call.answered → honeypot flow if flow == "honeypot": requests.post f".../calls/{call control id}/actions/speak", json={"payload": "Please hold while I connect you to a specialist.", "voice": "female", "language": "en-US", "client state": encode state {"flow": "honeypot hold"} } call.speak.ended → loop forever if state.get "flow" == "honeypot hold": time.sleep 2 requests.post f".../calls/{call control id}/actions/speak", json={"payload": "All specialists are currently busy. Please continue to hold.", "client state": encode state {"flow": "honeypot hold"} } The scammer stays on the line, burning their time and resources. Telnyx Call Control is webhook-driven — each call action triggers a new webhook event. To track which flow a call is in forward vs honeypot , the app uses client state , a base64-encoded JSON blob that Telnyx passes back in the next webhook: python def encode state data : return base64.b64encode json.dumps data .encode .decode def decode state b64 : try: return json.loads base64.b64decode b64 .decode except Exception: return {} No external database needed — the state travels with the webhook. The first thing the webhook handler does is verify the request is from Telnyx: try: client.webhooks.unwrap request.get data as text=True , headers=dict request.headers except Exception: return jsonify {"error": "invalid signature"} , 401 The Telnyx Python SDK verifies the Ed25519 signature against the raw request body. If verification fails, the request is rejected before any processing happens. git clone https://github.com/team-telnyx/telnyx-code-examples.git cd telnyx-code-examples/edge-fraud-firewall-python cp .env.example .env pip install -r requirements.txt python app.py ngrok http 5000 Configure the webhook URL in the Telnyx Portal https://portal.telnyx.com/call-control/applications — set the Call Control Application webhook URL to https://<your-ngrok-id .ngrok.io/webhooks/voice . Fraud screening typically runs at the application layer — after the call is already connected. By that point, the fraud has already consumed SIP trunks, media servers, and agent time. Screening at the carrier edge means the decision happens on the same network that carries the call. Number Lookup and AI Inference run on Telnyx infrastructure, not a third-party API called over the public internet. The screen-then-route decision is fast enough to sit inline on every inbound call. This sample uses in-memory state. For production: gunicorn -w 4 app:app as a process manager