531 posts tagged with "AI agents"
AI agents and autonomous systems
Uber Burned Its Entire 2026 AI Coding Budget by April: What Ungoverned Agentic Spend Means for Teams Running Their Own Deploy Infra
Uber burned its entire 2026 AI budget in four months after Claude Code adoption jumped from 32% to 84% of its 5,000 engineers. The timeline, the token economics behind it, and a six-control governance playbook for teams whose agents also deploy.
Your AI Agent Pushed Code and Nothing Deployed: Vercel's Git-Author Check vs the Age of Agent Committers
Vercel blocks deployments when the git commit author is not a recognized team member — a check that silently fails the moment an AI agent commits as itself. Four real cases, four working fixes, and why agent-first platforms authenticate the deploy call instead of the commit.
A2A Joins MCP Under One Roof: How to Hand an Ops Agent a Deploy Investigation Without Handing Over Deploy Authority
A2A joining MCP under the Agentic AI Foundation settles which protocol does what: A2A moves the diagnosis between agents, MCP moves capability between an agent and the platform. Here is the handoff design that keeps it that way — a worked deploy-investigation task, a three-tool audited MCP surface, and the identity, approval, and least-privilege invariants mapped to Kubernetes RBAC.
AGENTS.md Has a Neutral Home Now: What the Agentic AI Foundation Means for Deploy Platforms
OpenAI, Anthropic, and Block put MCP, goose, and AGENTS.md under the Linux Foundation's Agentic AI Foundation. Here is what neutral governance for the repo-instructions file means for deploy platforms — plus a copy-pasteable deploy-ready AGENTS.md.
E2B vs Daytona vs Modal: Picking an Agent Sandbox You Can Self-Host
E2B, Daytona, and Modal now ship as native providers in the OpenAI Agents SDK — but only one is still open-source and self-hostable. A numbers-backed comparison of boot times, isolation tech, GPUs, and licenses, with a build-vs-integrate verdict for self-hosted PaaS roadmaps.
The Four Capabilities an AI Coding Agent's Deploy Sandbox Actually Needs in 2026
Sub-second provisioning, hardware-isolated execution, agent-readable validation, and canary rollback: the four capabilities a deploy sandbox needs before an AI coding agent can ship unsupervised — scored against what a self-hosted Kubernetes fleet already provides.
Your Agent Can Call 7,000 SaaS APIs. Can It Deploy to a Machine You Own?
Arcade.dev gives agents 7,500+ SaaS tools behind brokered OAuth; Capix MCP gives them 37 tools that deploy models, provision GPUs, and emit signed receipts. Only one of those surfaces operates infrastructure you own — here is the checklist your PaaS MCP server still has to complete.
The Agent Is the Primary Tenant Now: Auditing CNCF's Platform Engineering 2.0
CNCF says internal platforms must be rebuilt for AI agents. A pillar-by-pillar audit of Platform Engineering 2.0 separates the genuinely new constraints — agent identity, MCP tool surfaces, machine-readable state — from old good practice, with a four-item checklist for self-hosted teams.
CNCF's 'Agentic Enterprise' Essay, Scored: What First-Class Agent Consumers Actually Require
CNCF's July 2026 agentic-enterprise essay lists what treating AI agents as first-class platform consumers requires. A row-by-row score against a self-hosted PaaS: five requirements ship, the shared context model is half-built, and the enterprise catalog baggage can be skipped.