# Former Apple Engineer Builds Szn, an Autonomous AI Agent That Handles Shopping and Messaging Inside iMessage > Developed by former Apple engineer Nikhil Gupta, the upcoming AI agent szn will run tasks like online shopping, vendor communications, and file management entirely through iMessage. **Type:** article · **Category:** Technology · **Published:** 2026-10-03 · **Source:** TrendKia **Canonical:** https://trendkia.com/en/technology/apple-ke-purva-injiniyara-ne-banaya-szn-imessage-ke-jarie-khuda-kharidari-aura-batachita-snbhalega-naya-ai-ejenta-42185 · **Language:** English **Tags:** szn, Nikhil Gupta, iMessage, Apple Intelligence, Siri, AI Agents, Tech News Artificial intelligence is shifting rapidly from passive text answering systems toward autonomous agents capable of executing tasks on behalf of users. Nikhil Gupta, an engineer who previously worked on Apple Intelligence and Siri initiatives at Apple, has built a new AI agent named szn. Slated for rollout in October, the service relies on iMessage as its operational interface, enabling users to delegate routine chores through natural messaging conversations. ## Executing Multi-Step Chores Directly in iMessage Standard AI chatbots generally reply to direct prompts with text explanations, but szn is structured as an active agent that takes real-world action. A user simply texts instructions within iMessage, and the system can navigate external websites, conduct product searches, and complete online shopping orders independently. When a purchase or inquiry demands direct coordination with merchants, the agent can communicate with vendors directly to finalize the transaction, removing the friction of juggling multiple retail apps and websites. ## Dedicated Phone Numbers and Virtual Assistant Identity To act as a genuine proxy for the user, szn receives its own dedicated name, phone number, and email address. With these credentials, the AI assistant can send outbound messages to external contacts and answer incoming replies directly. Operating seamlessly within the iMessage environment, it takes on the practical responsibilities of an executive personal secretary, handling logistical follow-ups without requiring constant manual intervention from the device owner. ## Integration Across the Apple Service Ecosystem While an independent application is planned for future release, every subscriber will receive a distinct, dedicated AI model rather than sharing a consolidated instance. Addressing digital privacy concerns, Nikhil Gupta stated that private user information will not be utilized to train the underlying AI models. The platform is also engineered to coordinate with standard Apple services, including reading and editing shared Apple Notes, accessing location coordinates through Find My, and managing files stored across iCloud, all while keeping the user inside the existing iMessage thread. ## Platform Dependence and Policy Considerations By centering the user experience on chat interactions rather than traditional software dashboards, szn presents a distinct architectural direction in consumer AI tools. However, relying on Apple's proprietary messaging network introduces notable platform risks. Apple has previously moved to restrict third-party software that attempts to bridge or operate on top of iMessage. The long-term viability of the service will depend heavily on how Apple chooses to treat an outside AI agent leveraging iMessage as its primary interface. ## What this means for you This development could fundamentally change how smartphone owners handle routine online purchases and communication without opening multiple individual apps. - **Daily Convenience:** Users can delegate online orders and vendor follow-ups directly through text messages. This cuts down the time spent manually browsing disparate retail stores and mobile applications. - **Data Privacy:** Each subscriber receives a separate AI model and personal records are excluded from training pipelines. This approach safeguards private conversations and personal files from broader dataset pooling. - **Workflow Productivity:** The system manages Apple Notes, cloud documents, and location tracking within the messaging thread. Users accomplish administrative tasks without context-switching across different utilities. - **Service Continuity:** The long-term availability of the tool depends on Apple's stance toward third-party iMessage integrations. Early adopters should track potential platform policy responses and the arrival of the dedicated app. ## Why this happened Artificial intelligence systems are shifting from simple conversational interfaces toward autonomous execution of multi-step practical tasks. This platform was created to meet user demand for actionable assistance within familiar messaging environments. - **Evolution Beyond Chatbots:** Standard conversational tools only answer prompts, leaving the actual execution to users. Developing an agent that navigates websites and interacts with vendors directly addresses this functional gap. - **Primacy of Messaging Apps:** Device owners spend significant daily time inside native texting applications. Utilizing iMessage as the front end eliminates the learning curve associated with adopting separate utility dashboards. - **Domain Expertise:** Nikhil Gupta previously developed features within Apple Intelligence and Siri. That specialized familiarity with Apple's software architecture enabled seamless integration with native cloud and note services. - **Platform Precedents:** Apple has traditionally restricted unauthorized external tools operating over iMessage. Anticipating friction on the native messaging network spurred plans for an eventual standalone application. ## Questions & Answers ### 1. What is szn and who created it? Szn is an autonomous AI agent developed by former Apple engineer Nikhil Gupta. ### 2. What tasks can szn perform on behalf of users? It can browse websites, make online purchases, communicate with commercial vendors, and send messages or replies. ### 3. Can szn integrate with native Apple features? Yes, it can coordinate with shared Apple Notes, access Find My location data, and interact with files stored in iCloud. ### 4. Will customer data be used to train the AI model? No, Nikhil Gupta stated that private user information will not be used to train the AI models. ### 5. When is szn expected to become available? The service is expected to launch in October, with a dedicated standalone application planned for a later release. --- _TrendKia — Har trend, sabse pehle.. Machine-readable view; canonical HTML at the URL above._