How far do you actually let your agents write to production systems, not just draft/suggest?
Summary
The discussion explores the current stance on allowing AI agents to make unsupervised writes to production systems such as ERP and CRM, questioning the barriers and comfort levels in the industry.
Similar Articles
Anyone here running AI agents that can actually write to production systems?
A user is seeking practical experiences from others running AI agents with write access to production systems, discussing operational challenges like action verification, retry handling, audit trails, and internal ownership.
How much do you actually let an AI agent touch in production?
Discussion about scoping permissions for AI agents in production to avoid dangerous database actions, suggesting read-only mirrors, approval steps, or hard walls between suggestion and execution.
People running agents in production: how do you control what they're actually allowed to do?
A developer seeks advice on how to control and bound AI agents' actions in production environments, particularly when they interact with real systems like databases and customer data, asking about current practices and whether this is a known headache.
What's your biggest fear about letting an agent take real actions in production?
A developer shares concerns about deploying AI agents that perform real actions in production, such as API calls and data manipulation, and asks the community about their fears and mitigation strategies like guardrails and human approval.
How are you letting AI agents touch your production database without it being terrifying?
A developer asks the community how to safely let AI agents interact with production databases, highlighting concerns over SQL injection, data leaks, and lack of audit trails.