As teams put AI agents to work, they need to move quickly without
losing control of what they deploy.They’re combining models, tools,
and infrastructure from across a fast-changing ecosystem.Making
those pieces work together and keeping them accountable as the
stack evolves is becoming a core part of building AI applications.
Docker’s approach to this challenge is providing a trusted, common
foundation for containment, curation, and control of agent
workloads at its core, while pairing those capabilities with an
open ecosystem of partners and tools.
As teams put AI agents to work, they need to move quickly without
losing control of what they deploy.They’re combining models, tools,
and infrastructure from across a fast-changing ecosystem.Making
those pieces work together and keeping them accountable as the
stack evolves is becoming a core part of building AI applications.
Docker’s approach to this challenge is providing a trusted, common
foundation for containment, curation, and control of agent
workloads at its core, while pairing those capabilities with an
open ecosystem of partners and tools.
In our State of Agentic
AI report, 60% of organizations reported having AI agents
running in production.Those agents install packages, run scripts,
and call external services on their own, and much of that work now
happens on developer
laptops, with developer credentials.Running untrusted or
experimental code directly on your machine has always carried risk,
and handing that same machine to an autonomous agent raises the
stakes. A sandbox environment gives code a separate, controlled
space to run in, with limited
AI agents have come
a long way in both capability and everyday use since generative AI
went mainstream in late 2022.In Stack Overflow’s 2025 Developer
Survey, 84% of developers said they use or plan to use AI tools
in their workflow, up from 76% a year earlier.As those tools shift
from suggesting code to writing files and running commands on their
own, one practical question follows.How much should an agent be
allowed to do without stopping to ask?Turn that dial all the way
We believe the future is a multi-model, multi-harness world.And
we think it needs a new trust model. In 1988, Norm Hardy
described a problem that had been
quietly breaking systems for years:the confused deputy.A program
that takes action using its permissions instead of yours. Today,
every AI agent is that deputy.It inherits your authority:Your
credentials, your repo access, your ability to call APIs.But its
behavior is probabilistic.It might be acting on an instruction
found in its environment,
Are in-person tech conferences back in fashion?Or are engineers
just willing to travel for fresh baguettes?In this post, I round up
a few highlights from KubeCon Europe
2024, held March 19-24 in Paris. My last KubeCon was in
Detroit in
2022, when tech events were still slowly recovering from
COVID.But KubeCon EU in Paris was buzzing, with more than 12,000
attendees!I couldn’t even get into a few of the most popular talks
because the lines to get in wrapped around
Weitere Beiträge …
- Empower Your Development: Dive into Docker’s Comprehensive Learning Ecosystem
- OpenSSH and XZ/liblzma: A nation-state attack was thwarted, what did we learn?
- Building a Video Analysis and Transcription Chatbot with the GenAI Stack
- containerd vs. Docker: Understanding Their Relationship and How They Work Together
- Is Your Container Image Really Distroless?
Seite 1 von 23