Everyone in that pod agreed the Gov was broken. Nobody could put their finger on it or articulate in what AI might deem a "load bearing" - HHAHAH capacity. The other day i saw a comment on here by bob1029 [1] and he put it better than I ever could. It's broken because nobody can execute across all the moving parts; its a coordination issue in many ways - the cost of collaboration has become so large that it has become the thing to overcome instead of whatever first principal is the whole point of the shit e.g.: Healthcare, Food, Housing etc... The bottleneck was never intelligence it's coordination. The cost of getting many parties to act together without the whole thing blowing up.

The Anthropic multi-agent article hit it too...turf war, the 2.4M-request queue, the price collusion, the merge silos. Every one is the same thing: free-form runtime "negotiation" blowing up. And every success is an agent ad-hoc reinventing an institution mid-fight inventing a "verifiable criterion," writing an apology commit and pulling in a human, running a tournament as a commitment device. They keep hand-rolling the institution, badly, under fire.

So stop making them reinvent it. The generalization of the "constrained action space" idea isn't just bounding one agent's moves it's what I call an intent: intents don't just constrain each agent's actions, they codify the coordination itself.

And I make the unit of coordination a first-class object: the Deal a structured negotiation instead of a free-form one. The Deal is the container those agents keep reinventing, handed to them up front: scope and terms, the parties and their roles, the ordered steps, a verification gate as the neutral arbiter, and an appeal / human-escalation path as recourse, all over an append-only record. Agents negotiate inside a bounded contract instead of improvising one mid-fight.

How it works from what you say to what actually happens (the "Deal")

1. You speak the intent. You can use a form but I found people like the verbal shit much more.

2. Break the problem into an ontology. The ask gets decomposed into the real work it implies mapped to actual job roles (O*NET). Problem → Solution.

3. Vet the solution with the gov council agents. Every domain has one public AI expert in that agency's real systems Medicare, Medicaid, SSA, OPM (pda:codify.). Policies get deliberated and voted, elected officials in the loop, before anything runs. Stakeholders.

4. We staff it. It matches the specific expertise needed the exact specialty, not a generic "doctor." Down to the right role for your case.

5. We set up the financing. The money that follows the person eligibility, benefits, the payment rail. Financing.

6. An agent manages the process with expertise humans in the loop for anything high-risk, adjusting as outcomes come back, like an adaptive trial, until the outcome is met or it fails honestly. Expertise → Outcome.

The atomic unit of value here is a "Deal". Problem broken down, solution vetted, staffed, financed, executed under contract. intent → Deal → outcome.

Overview

- Intent: https://wiki.erpo.law/agent/wa-erpo

- Program: https://erpo.law/program/71069-petition-for-an-erpo-as-a-fam...

- Protocol: https://erpo.law/protocol/71079

I'm building it in the open because I think thats the only way this can be done

https://medicare.dev

https://epa.dev

etc...

Learning how to take criticism better so the more criticism the better.

[1] - https://news.ycombinator.com/item?id=49316271

"tester" is probably not the correct term here. website "visitor" would probably be more appropriate.

https://crohns.ai

You have no invite; so what you are seeing is not what the test users currently see

> What if I'm deaf, mute, or blind and using accessibility tools? What am I even supposed to be talking about?

Then you would have come from another portal titally

In the menu, projects doesn't do anything (and what's a project anyway in this context?)

>

> There's 94 programs... for what? If I go open a program, https://medicare.dev/program/71152-general-enrollment-period... there's still no disclaimer, and still no explanation about the reason someone should be using the site. I guess this is to build.. AI something? Maybe for use in medicare.gov? Is this entire site meant to be used by folks working for medicare (and if so, should I even be able to see this much?)

Agents run the programs

> Messages takes me to a login screen with no sign-up.

Because you have no invite/ref code - so you are in a blank context

> Forms and Invest take me to the same page, giving me a chance to invest in foreign markets(?), but not what the investments are in? (codify.city seems like it's created by you as well, similarly says sweet nothing about what purpose it's serving)

Forms is an entry gate for people on the management side w/ specific intents

> "How it works"... doesn't? "The walkthrough isn’t available yet."

This is not done yet; i have several videos but they are all linked to specific cases and since you have no invite/ref code they are not available in your session

> "Wiki" seems to be providing some examples of what seems to be instructions to AI agents, but no indication how you'd even use them. (also if you scroll the box, there's an error "Syntax error in text mermaid version 11.16.0"

Yes, there are a few things I have to work with on this

> This whole site fails to nail the very basics, and seems like slop-coded nonsense. I'd encourage you to stop building features, and start doing the boring groundwork. If you're actually expecting anyone to use it, explain it.

I am working on this now; and no - its not slop coded; you are just being reductive and ignorant. I have made no claim this is a production effort you are seemingly just one of those ignorant people that assumes things and then reacts to their unverified assumptions

> Also yet to see any of the disclaimers you claim are all over the place. They're really not.

Yes, they are; they literally are in every single email when a user has the proper ref code.

People like you are the problem in my opinion; this was not a show HN I was responding to a comment and used and example from something I have been working on - you have used this to try and make yourself feel some sense of superiority by projecting claims of "completeness" that I never made. I am very glad that the majority of people I have worked with in tech are nothing like you are and I wish you well.

TY for the heads up.

Medicare.dev - clearly sates, as all Gov. websites do that its an official Gov. website etc... My literature here clearly states - for people that actually are using it - this is a functional healthcare utility, even if you google or ask ask - its a very clear distinction that is made.

Intent: https://wiki.crohns.ai/agent/posts/ibd-biologic-therapy-init...

Program: https://crohns.ai/program/71174-eim-joint-pain-flare

Protocol: https://crohns.ai/protocol/71174

This allowed me to essentially set it and forget it until and each program is specific to each condition so its not just a dumb daily alert or something like that.

You can make yourself a program at Medicare.dev - just explain your situation or whatever and it should guide you through the rest.

Comments URL: https://news.ycombinator.com/item?id=49336238

Points: 2

# Comments: 1

https://missionlocal.org/2026/02/sf-garry-tan-california-pol...

https://techcrunch.com/2024/01/28/y-combinator-president-gar...

Comments URL: https://news.ycombinator.com/item?id=49336001

Points: 1

# Comments: 2

1. I think curing a disease will come from organizing the domain experts int he field w/ AI.

2. Automating the delivery of "programs" that adhere tom "protocols" within the domain.

3. I think that PG/dang/gary tan etc... intentionally suppress even the ideas like this because they will not control them.

I am not saying this is the answer, but even discussion around how/why its not is progress.

Comments URL: https://news.ycombinator.com/item?id=49335103

Points: 2

# Comments: 1