# Safeguarding LLM-Assisted Dev at Guardsquare | Guardsquare

DevFeed: [Safeguarding LLM-Assisted Dev at Guardsquare | Guardsquare](<https://devfeed.tech/articles/safeguarding-llm-assisted-dev-at-guardsquare-guardsquare-26891.md>)

Original publisher: [Read original article](<https://www.guardsquare.com/blog/llms-for-software-development>)

Author: Noah Fraiture - Backend Engineer

Published: 2026-09-15T13:03:38Z

Content type: article

Language: en

Sources: [Guardsquare Blog](<https://devfeed.tech/sources/guardsquare-blog.md>)

Topics: [Development](<https://devfeed.tech/topics/development.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Cybersecurity](<https://devfeed.tech/topics/cybersecurity.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [android](<https://devfeed.tech/tags/android.md>), [containers](<https://devfeed.tech/tags/containers.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data](<https://devfeed.tech/tags/data.md>), [dev](<https://devfeed.tech/tags/dev.md>), [developer](<https://devfeed.tech/tags/developer.md>), [development](<https://devfeed.tech/tags/development.md>), [ios](<https://devfeed.tech/tags/ios.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-gateway](<https://devfeed.tech/tags/llm-gateway.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>)

## AI overview

Guardsquare explains why it adopted LLM-assisted software development despite risks involving sensitive intellectual property, personally identifiable information, and agent access to developer infrastructure. The post describes safeguards including separating sensitive code, isolating agent execution, and controlling model access and outbound data through an LLM gateway and guardrail service.

## Source excerpt

This post is not meant to tell you how to use large language models (LLMs) or to claim we've found the right approach. As a cybersecurity company working with particularly sensitive IP, our decision to use LLMs for development was never just about productivity. The broader enthusiasm around LLMs was not itself a reason for us to adopt them quickly. For some time, our position was that the risks outweighed the productivity gains, and incidents involving AI agents elsewhere in the industry reinforced that assessment.