# AI agents are getting more complex. Developers shouldn't have to babysit them.

DevFeed: [AI agents are getting more complex. Developers shouldn't have to babysit them.](<https://devfeed.tech/articles/ai-agents-are-getting-more-complex-developers-shouldn-t-have-to-babysit-them-121553.md>)

Original publisher: [Read original article](<https://thenewstack.io/harness-engineering-coding-agents/>)

Author: Kimberly Fessel

Published: 2026-11-06T19:35:59Z

Content type: article

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-factories](<https://devfeed.tech/tags/ai-factories.md>), [ai-hallucinations](<https://devfeed.tech/tags/ai-hallucinations.md>), [ai-harness](<https://devfeed.tech/tags/ai-harness.md>), [ai-trends](<https://devfeed.tech/tags/ai-trends.md>), [automated](<https://devfeed.tech/tags/automated.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [guardrails](<https://devfeed.tech/tags/guardrails.md>), [harness-engineering](<https://devfeed.tech/tags/harness-engineering.md>), [human-oversight](<https://devfeed.tech/tags/human-oversight.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [security](<https://devfeed.tech/tags/security.md>), [sponsor-thoughtworks](<https://devfeed.tech/tags/sponsor-thoughtworks.md>), [sponsored](<https://devfeed.tech/tags/sponsored.md>), [sponsored-podcast](<https://devfeed.tech/tags/sponsored-podcast.md>), [thoughtworks](<https://devfeed.tech/tags/thoughtworks.md>), [video](<https://devfeed.tech/tags/video.md>)

## AI overview

Harness engineering aims to let coding agents catch and correct mistakes before human review by combining automated tests, feedback loops, and guardrails. This can support longer tasks and parallel agents with less supervision. For organization-wide use, AI factories provide standardized infrastructure for model selection, workload management, and cost optimization. Greater autonomy also requires agents to access more data, systems, and tools, creating potential security vulnerabilities. The excerpt describes guardrails that can restrict tool access, enforce test environments, and require human approval for sensitive changes; it also notes renewed emphasis on practices such as penetration testing and understanding the path to production.

## Source excerpt

What if your coding agent could catch its own mistakes before you ever reviewed its work? A few years ago, The post AI agents are getting more complex. Developers shouldn't have to babysit them. appeared first on The New Stack.