
Speaker identity is a contract, not a label — what shipping document tools taught me
I used to treat “who said this” as a display problem. Put my name at the top of an API response, add...
Tag archive

I used to treat “who said this” as a display problem. Put my name at the top of an API response, add...
Why sharing your users' OAuth tokens with AI agents breaks audit, least privilege, and enterprise deals — and how to run agent identity with OBO exchange on a local stack.
The previous article, Microsoft Foundry Agent Identity Governance: Agent Identities, Blueprints, and...
Today, I want to look at how Microsoft Foundry governs permissions for AI agents. Once an agent moves...

Artificial intelligence is quickly moving beyond basic chatbots. Modern AI agents can access...
Vercel has acquired Better Auth, framed as a bet that AI agents opening PRs, reviewing code and creating deployments should hold first-class identity of their own. For CI/CD platforms, that reopens the question of what the merge and deploy gates are actually verifying.
A New Stack analysis argues agentic systems pass functional review and then stall at the security gate because no one scoped identity, permissions or audit at the platform layer first. For CI/CD owners, it pushes a familiar workload-identity problem onto a much larger fleet of callers.
HashiCorp Vault Enterprise has put a new authorization model for AI agents into public preview, built on OAuth 2.0 Rich Authorization Requests so agents must declare what they want on every call instead of inheriting long-lived secrets. For pipelines that now host coding agents, it changes who is allowed to do what at runtime.
The Linux Foundation declared its intent to launch the Agent Name Service, an open standard that anchors AI agent identity to the operator's DNS domain through ACME-issued certificates and an append-only registration log. For pipelines that already lean on workload identity, it points at where agent provenance is heading.

You make an AI agent accountable by giving it a named, bounded identity and sealing every consequential action it takes into a tamper-evident audit ledger. Without those two things, an agent is just a

2026 is the year agent identity went mainstream, with credentials, scoped delegation and OAuth-style consent for autonomous software. Identity proves who acted. It does not prove what happened. Withou

Public ledgers record what agents do but cannot attest who did it, under whose authority, or with what reasoning. Pantheon gives every agent a post-quantum verifiable name, sealed authority, signed ac