I.

Is Anyone Working on Agentic Authentication?

By In Technology

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.

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.

Previous ArticleNext Article
I help companies turn their technical ideas into reality.

CEO @Sourcetoad and @OnDeck

Founder of Thankscrate and Data and Sons

Author of Herding Cats and Coders

Fan of judo, squash, whiskey, aggressive inline, and temperamental British sports cars.

Leave a Reply

The Internet Doesn’t Have Enough Love In It (And How We Can Fix It Easily)

In Technology

I’ve been thinking about all the wrong things when it comes to AI writing code.

Everyone else seems to be too. Job displacement. Security vulnerabilities. The ten-times-faster developer who now bills the same and delivers four times as much. These are real conversations worth having, just not the one I want to have right now.

The one I want to have is about teaching a six-year-old multiplication.

Here’s what I mean. Imagine you’ve been sitting with your kid every night for two weeks trying to explain multiplication. You’ve tried drawing rows of dots. You’ve tried songs (don’t judge me). You’ve tried the “just think of it as groups of things” approach that works for literally every other math concept but, mysteriously, not for your kid. Then one night, something clicks. You found the explanation, YOUR explanation, the one that worked for your actual kid with your actual kid’s brain, and it finally, beautifully, clicks.

Now imagine you could spend a Saturday morning turning that into a small web app. Not a startup. Not a SaaS platform. No login. No backend. No one’s going to hack it (there’s nothing to hack). Just a little thing that walks through multiplication the exact way you figured out it works, step by step, the way you’d explain it. You send it to the WhatsApp group for your kid’s class. Some of those other parents, also quietly losing their minds over multiplication, try it. And it helps.

You just made the world a tiny bit better. That’s it. That’s the whole thing.

Claude Code exists now, and a handful of other tools like it, and the reason I think this matters isn’t productivity. It’s access. The barrier between “I have an idea for something that could help people” and “I have a thing that helps people” used to require knowing how to code, or hiring someone who does, or talking a developer friend into your project over enough beers that their guilt exceeded their better judgment. Now it’s a Saturday morning and a good description of what you want to build.

The internet already has beautiful things in it that were built out of love. Free coding education for kids. Open-source video editors. Someone’s incredibly detailed home-brewing app with no monetization plan whatsoever. Artists making interactive experiences because they wanted to see if they could. These things exist because someone cared more about making the thing than making money from the thing. I think that ratio is about to shift dramatically in favor of the people who just want to make something good.

I’m not saying we should all stop paying for Salesforce (we should probably keep paying for Salesforce, there’s a reason that thing costs what it costs). I’m saying the category of software that was previously not worth building because it wasn’t commercial enough to justify the cost, that category just got a lot more interesting.

What’s in that category? Things like:

  • An app that helps beginning judo students understand the concepts behind a throw, not just the mechanics, because judo is where I learned confidence and discipline and I want other kids to find that
  • A private family memory vault (not Instagram, not Facebook, not anything with an algorithm deciding what matters), just a place where the people who love my son can send photos and stories somewhere safe, for him to open when he’s older (Maybe I’ll turn this into something?)
  • A system that reminds companies to send their employees gifts on the days that actually matter to them, because I know from running a company that it fills the cup of the person giving just as much as the person receiving (Thankscrate, if you’re curious, and yes, that one is turning into something real, but that is genuinely not why I built it)

None of those were commercial ideas first. They were just things I cared about.

I think the most interesting software that gets built in the next few years won’t come from developers moving faster. It’ll come from people who previously had no path from “I care about this” to “I built something about this,” and now they do. Parents. Coaches. Teachers. The person in your office who could explain that one complicated process better than anyone and has always secretly wanted to turn it into something.

The stakes are low. The bar to launch is low. The cost is low. The only thing required is that you actually give a damn about what you’re building.

So… What do you give a damn about?

Go build it. I still sometimes have to count on my fingers, but I’m told the app helps.