Everyone is building AI-powered tools, even people who shouldn’t be. Agents seem to be the next obvious (and big?) step. But these little bots need a secure way to act on behalf of users without causing chaos.

Richard Dulude at Underscore VC wrote about the lack of identity standards for AI agents in this LinkedIn article. I don’t know Richard or Underscore VC (sorry). But, he’s right, traditional authentication assumes either a human or a machine with static credentials, and that doesn’t work for AI agents that need to make decisions and take actions. Companies want accountability (and probably liability), and users need control of what their potentially psychedelic robot is doing on their behalf. This balance doesn’t exist yet.

This is probably for another blog post, but right now, everyone, including the bots, are using human interfaces as a stopgap. OpenAI’s Operator is a great example, agents pretending to be humans to interact with systems that weren’t built for them. That’s fine for now, but eventually, the human interfaces will be an afterthought. Like how “mobile-first” design took over, we’ll be doing “agent-first” design with human-accessible backups. Having a dedicated standard for agentic authentication might be a good first step in that machine-to-machine way of thinking and designing systems.

Agentic Proxy Credentials (APC): A Solution (A Term I Totally Made Up)

I made this up. It’s probably a bad term, but naming things is fun. This doesn’t exist… if you are a large battery and power supply company, don’t sue me. I’m spitballing here.

One possible fix is the “sucked out of my thumb” Agentic Proxy Credentials (APC). This would let users grant their AI agents secure, limited permissions to interact with systems while making sure the right level of oversight are in place. There are things that I wanted to do this very week, but I don’t trust my bots with my actual usernames and passwords:

Stop me talking to Airline Idiot Bots

Talking to airline chatbots is painful. Right now, they can only regurgitate FAQ answers. With an APC, my AI assistant could log into my airline account, check flights based on my loyalty status, and rebook me without you having to touch anything. This would make AI actually useful instead of just a slightly smarter help page.

Paying for small things without having to deal with entering my ACH data AGAIN

I don’t want to give an AI full access to my bank account. But I wouldn’t mind letting it handle small transactions in a controlled way. With APCs, I could grant my assistant time-limited access to approve payments or move money within strict limits. The AI does the work, I stay in control, and my bank account doesn’t mysteriously empty overnight… unless I’m Ambien shopping again.

AI Dungeon Master’s Assistant

D&D is great, but session prep is a time sink. I want an AI that logs into my D&D Beyond account, manages stat blocks, generates lore-friendly content, and even takes session notes. The AI handles the boring admin work, and you get to focus on making your players cry (or cheer, if you’re nice). Yes, serious stuff here.

How It Could Work

There are a few ways to make this happen, I think. I’m no longer allowed to do actual engineering at my own companies I founded, so this blog is my outlet. Everyone needs a hobby.

• Zero-Knowledge Proofs (ZKP): Let the agent verify credentials without exposing sensitive data.
• Time-Limited OAuth-like Tokens: Give agents temporary access that expires after a set time.
• Multi-Factor Delegation (MFA->MFD): Require multiple checks before an agent gets access (biometric + device trust, for example).

Is Someone Already Building This?

Honestly, I wouldn’t be surprised if Okta, OAuth, or OpenAI are already working on this and I’m just ranting for no reason. But if they aren’t, they should be. The pieces are all there, someone just has to put them together.

I need this, but I can’t find it. If anyone is working on it, let me know. I’m too busy trying to solve employee gifting at scale at Thankscrate, implementing AI into every existing business at Sourcetoad, and making sure passengers can watch TV and book dinner reservations in the middle of nowhere at OnDeck.