PEP / PDP
Policy Enforcement Point · Policy Decision Point · PEP · PDP
The split between the component that intercepts a request and enforces a decision (the policy enforcement point, such as an API gateway) and the service that makes the permit-or-deny decision (the policy decision point).
In our briefings
The claim each of the newest briefings on PEP / PDP would have you leave with.
Uber runs per-hop token exchange with a full actor chain for AI agents in production, and has published sample tokens and a latency chart. Its security token service gives each hop a fresh token scoped to one audience, with a lifetime "in the order of minutes" (both sample payloads expire 300 seconds after issue), and the token carries the attested chain from the engineer to the agent making the call. Uber says "the system has been adopted by thousands of internal agents" and reports the exchange API's P99 as "consistently below 40 milliseconds" under current load; its chart sits mostly under 10 ms, with one spike reaching 40. The post covers this identity layer. Uber frames dynamic access control and a unified policy enforcement plane as its direction on top of it, and names session and intent claims as additions the token could carry in the future.
Uber runs per-hop token exchange with a full actor chain for AI agents in productionBI-FIND-2026-0081
AAuth's premise is that an OAuth client or an API key has no identity of its own and that SPIFFE and WIMSE stop at one trust domain, so it gives each agent one: an identifier of the form aauth:local@domain issued by an Agent Provider and bound to the agent's own signing key by a short-lived agent token (the draft recommends Ed25519, which every party must support), so that 'every agent has its own cryptographic identity' and 'the first API call to a resource is the registration'. No credential in the protocol is a bearer credential; every request is signed, and a resource can challenge for more at any time. In its lightest mode the draft pitches this as a drop-in for API keys: 'this replaces API keys with cryptographic identity.' What an agent token attests about the software behind the key is left to companion specifications.
AAuth gives every agent its own key, then keeps the delegation chain out of the token on purposeBI-FIND-2026-0365
A person's approved request is not, by itself, authority an agent can be held to, McGuinness argues, and relatively few deployments perform the step that would make it one. That step converts approved intent into a bounded authority artifact an enforcement point can evaluate. By his account, many systems instead fall into one of five patterns: scope enumeration, app-local mapping, LLM-generated requests, broad standing authority with prompt discipline, or a formal policy language. He says the most common land in the third or fourth, and that where nothing makes the conversion, the agent's own judgment becomes the effective policy engine. This is one author's argument, but two production designs we have read fit it. Uber's agent tokens carry the full chain of who asked through every hop, and Sierra's gateway runs interactive agent work as the user, with that person's permissions. In our reading, neither records what the person approved.
A user's approved request is not yet authority an agent can be held to, and most deployments skip that stepBI-FIND-2026-0202
›Cited in 22 briefings
Every briefing that discusses this term, newest first.
- Uber runs per-hop token exchange with a full actor chain for AI agents in production
Article · · Uber Engineering blog · Matt Mathew et al. · May 21, 2026
- AAuth gives every agent its own key, then keeps the delegation chain out of the token on purpose
Draft · · IETF Datatracker · Dick Hardt, Hellō · Sep 25, 2026
- A user's approved request is not yet authority an agent can be held to, and most deployments skip that step
Article · · Control Plane by Karl McGuinness · Karl McGuinness · Mar 17, 2026
- Five places to put authorization in microservices, and why Drus says the classic gateway one does not scale
Video · · OWASP Foundation · Uploaded October 21, 2026
- AAuth carries the signals an agent's approval needs, Hardt says; the brain that decides does not exist yet
Podcast · · Collateral Dialogue · Self-Driving Software: What OAuth Can’t Do for AI Agents | Dick Hardt, Hello · Sep 2, 2026
- OpenID's AuthZEN API can't say an agent acts for someone, and its policy service trusts whatever the app sends
Article · · OpenID Foundation · Omri Gazitt et al. · Jan 11, 2026
- Before an agent pays or changes data, Schrock's last check treats it as untrusted and keeps the record itself
Draft · · IETF Datatracker · Iman Schrock, EMILIA Protocol · Sep 26, 2026
- OWASP's agent Top 10 blames identity systems built for people, and does not say how it chose or ranked its risks
Article · · OWASP GenAI Security Project · John Sotiropoulos et al. · Dec 9, 2025
- Saviynt's strategy head calls agent discovery a commodity and pitches Zuma for runtime control
Podcast · · The Non-Human & AI Identity Podcast · Ep # 14 - Turning an AI Breach into a Case Study · Sep 15, 2026
- Coetzee's agent token is good for one declared call, and the hard part is hashing that call the same way twice
Draft · · IETF Datatracker · Rudolf Jacobus Coetzee · Jul 19, 2026
- A SANS instructor's broker vaults agents' real keys, but its third delivery model breaks the abstract's promise
Draft · · IETF Datatracker · Kenneth G. Hartman · Mar 29, 2026
- Transaction tokens are nearly a standard, and there is still no agreed place in them for the agent
Podcast · · Identity at the Center · #449 - Decoded - Transaction Tokens with George Fletcher · Sep 21, 2026
- OAuth handles an agent in one company, working while you watch. The OpenID paper says that is where it stops.
Article · · OpenID Foundation · Tobin South et al. · Oct 2025
- The IETF's workload-identity architecture gives AI agents one subsection, calling an agent a delegated workload
Draft · · IETF Datatracker · Joseph Salowey et al. · Jul 6, 2026
- Two ways to give an AI agent an OAuth identity clashed in April; a draft now lets them work together
Podcast · · Hybrid Identity Protection Podcast · Securing Non-Human Identities in the Age of Agentic AI with Sarah Cecchetti, Director of Product Management at Semperis · Apr 28, 2026
- Agent identifiers are split across JWT-based, SPIFFE, WIMSE and proprietary schemes, an identity lead says
Podcast · · Identity Decoded · Winning in securing agentic identity: Start with one team, one use case · Aug 12, 2026
- Huawei researchers add agent delegation to an existing permission model and prove each action traces to a human
Paper · · arXiv · Amjad Ibrahim et al. · Jun 2, 2026
- A Huawei agent draft keeps one 'master agent' as gatekeeper and drops the line that had servers re-check it
Draft · · IETF Datatracker · Yuan Ni et al. · Feb 28, 2026
- Ericsson researchers would check every query a telecom network agent sends to its knowledge base
Paper · · arXiv · Loay Abdelrazek et al. · Oct 22, 2025
- ETDI would sign MCP tool definitions against lookalikes, but leaves open who vouches for the publisher's key
Paper · · arXiv · Manish Bhatt et al. · Jun 2, 2025
- An MCP gateway can do OAuth for servers that have none; this one passes them a user header
Paper · · arXiv · Ivo Brett · Apr 28, 2025
- NIST's 2020 zero trust model named AI agents that manage security and left their authentication open
Article · · NIST · Scott Rose et al. · Aug 11, 2020
Related terms
What appears alongside PEP / PDP in the same briefings.
Authenticated workflowsTask Request EnvelopeCredential Broker for Agents (CB4A)