mailwal

Till deployment do us part

The New Stack
October 31, 2026

Hold your agents

Microsoft is opening up the GitHub Copilot agent harness to outside developers through Microsoft Foundry, bringing the same orchestration infrastructure used across its Copilot products into a managed service for building and deploying autonomous agents.

Announced Wednesday, the Microsoft Copilot harness is now available in public preview through Foundry Agent Service. It comes with built-in sandboxing, reusable skills, MCP integrations, and support for subagents. Microsoft takes care of running the agent and managing its execution environment, leaving developers to choose a supported model and configure the instructions and tools for their applications.

Go deeper: Microsoft’s new Copilot harness makes agents easy — until you want to switch

More fresh reads from TNS:

▹Sam Altman almost scrapped token pricing. Here’s why he backed off.

▹“I don’t think the world needs a new GitHub”: What GitHub’s leaders really think about their new rivals

▹Mistral’s Large 4 open weights arrive with a 1-point coding lead over GLM-5.3: “There’s nothing you can’t do with this model that you can do with competitors.”

160 admin hours a year: how AI-guided diagnostics finds root causes faster

MFT admins can lose up to 160 hours a year chasing root causes after a failed transfer. Join us live on November 19 to see how Fortra uses AI to find the likely cause faster, using a real failure scenario. You’ll learn:

  • How AI-guided diagnostics points to the root cause in minutes, not hours
  • How anomaly detection flags problems before they turn into failures
  • How automated documentation keeps your team’s knowledge up to date

TOP OF THE STACK

GPT-6.1 Terra vs. GPT-6 Astra: One sacrifices accuracy for lower cost and higher speed at high effort

by Jessica Wachtel

OpenAI prices GPT-6.1 Terra at one-tenth of Astra’s standard input and output token rates. In these three tests at high reasoning effort, Terra used less time and cost less, but scored lower on two tests.

OpenAI released GPT-6.1 Terra on October 26, marketing it as a cheap, fast model for high-volume everyday work, priced at a tenth of its GPT-6 Astra flagship. As the...

WHAT ELSE IS NEW?

FROM OUR PARTNER

Is your SOC designed for AI scale attacks?

Mate’s agentic Security Operations Platform investigates every alert with full business context, scaling your team to machine speed.

  • Closes up to 85% of false positives automatically
  • Cuts investigation time to minutes, not hours
  • Runs on a live Security Context Graph of your org
  • Backed by $35M in new funding to scale the platform

FLOW STATE

BRIEF

It appears that investors are paying attention to the rising tide of cybersecurity fear permeating technology circles.

STACK

See how JioHotstar engineered their streaming architecture to deliver flawless live video to 32 million concurrent viewers during the IPL.

WATCH

Bit Cloud’s Ran Mizrahi explores how reusing reviewed code can give the next AI-built app a head start, with less new code for developers to review.

How did we do today?

ALSO FROM THE IMG FAMILY

More communities worth exploring

Community-powered role and skill-based roadmaps to guide your learning journey in tech.

A modestly upbeat breakdown of what's happening with tech, business and power.

Insights from the brightest minds in data science, machine learning and AI.

Join TNS on your favorite platform

The New Stack is a media platform for the people who build and manage software the world relies on.

© 2026 The New Stack. All rights reserved.
The New Stack 1111 6th Ave Ste 550 PMB 50938 San Diego, CA 92101-5211