Strands Harness bundles the tools, context and memory developers otherwise build. AWS says smarter context helped token efficiency — but one rival still beat it.
The analyst report that put AI agents on the endpoint map
Every generation of endpoint security chased a new threat. The newest arrives invited, holding real credentials. SACR mapped the layer. On October 1, join a live session about agent runtime observability with the analyst who wrote the report and Origin's founder.
A third option is emerging in the fight over AI and your data
Enterprises won't risk their data, and AI labs won't hand over their model weights — so most companies have been stuck choosing between the frontier and control. In this episode of The New Stack podcast, Vast Data co-founder Jeff Denworth talks about DataEnclave, a new approach that uses Nvidia's Confidential Computing to let proprietary models and proprietary data meet on trusted infrastructure, without either side's IP ever leaving the building.
AI writes the code faster than anyone can review it
Pull request volume is up nearly 2x since AI started writing code. Bugs are up 54%. Incidents per pull request have nearly tripled. The instinct has been to add more review, or have AI review AI's own work, but neither fixes it. Explore where human review still earns its keep, and what a pipeline that verifies every deployment actually looks like in practice.
How WHOOP turned days of vulnerability triage into minutes
For WHOOP's security team, a critical vulnerability used to mean an entire team of engineers and days of manual, all-hands triage. Join us live as we walk through the workflow that changed that, built with Datadog Bits AI and Workflow Automation.
AI is changing the speed of attacks, and SOC teams are stuck asking how to keep up without losing oversight. Join us for a candid take on where AI autonomy actually belongs in the SOC, followed by a live demo of AI agents handling a real alert investigation from triage to resolution. You'll walk away with a practical framework for how much control to hand off, and when.
No reranker, however capable, can recover a relevant result that retrieval never surfaced in the first place. Explore how to design retrieval as a multi-stage funnel instead of one expensive rerank pass, and how that changes when an agent, not a person, is doing the searching.
Six data requirements to get your AI agents from demo to production
Most enterprise AI pilots work perfectly. Most production deployments don’t. Join us on October 14 for the six architectural requirements that separate agents stuck in pilot from those running reliably at scale.
.png?height=72&upscale=true&name=The%20New%20Stack%20logo%20-%20Reversed%20(2).png){kind=small}
