In this case your demand coop might buy REI using the funds your contribute to its wealth fund, while REI you might only just be able to get items for cheap from being a member and the ability to vote on new products.

We build a replacement for github, the most you personally drive demand to the git replacement and for that demand you gain equity. And for that equity you get a larger say on how the fund is used and increased access to privileges

But after you create this charter the person who would evaluate it would be AI steward. He can tell you why your proposal aligns with the charter, why it doesnt. How it can come in line with the charter. After that given the money you need falls under a certain amount it just gets passed. If its over a certain amount though it goes through the vote.

but no proposal goes forth without AI steward being the fair evaluator of whether your proposal aligns with your coops charter.

Comments URL: https://news.ycombinator.com/item?id=48216619

Points: 81

# Comments: 94

The chinese just this week shut down the entire US auto industry because of rare earth if they blockade taiwan how long until they win that.

Which is exactly what you want. It’s like if you ask a group of five people what they want to eat, knowing they’re all vegans. If you wanted a fair decision-maker, you’d hope they pick something close — vegan and good. An AI will always give that answer in a boring and predictable way. But a human might take outside context into account or selfishly pick a non-vegan restaurant — not because it’s consistent, but due to any number of random outside factors.

I’ve been building Sashi — a developer tool that reads your existing codebase and lets you create AI-driven workflows out of your backend functions.

Imagine giving your ops/product/dev team a natural-language interface to: • Search users from your DB • Filter and chart usage data • Send emails or Slack messages • …all by just describing what they want to do

It works with TypeScript + Zod functions, generates UIs automatically, and connects to your GitHub so it stays in sync.

The long-term goal is to help teams move faster without rebuilding internal tools every time someone needs a new dashboard or button.

Right now it supports: Dynamic function registration AI workflow planning Automatic UI generation (tables, charts, forms) GitHub function ingestion Secure execution via a centralized hub

Automatically installs into any node.js/next.js codebase with a cli command

If you’re curious or want to try it out, I’d love your feedback we are looking for beta users: https://www.usesashi.com

Also I had a question if you wanted to be help:

What’s one task in your codebase you’d love to turn into a “just say it and run it” flow?

Like i know changing a users roles especially if its tied to a bunch of side effects in you code base is something i deal with a lot

Comments URL: https://news.ycombinator.com/item?id=44494999

Points: 4

# Comments: 1

Sashi is an open-source workflow automation system that lets you turn real backend functions into reusable, shareable workflows—created with AI, validated by code, and executed from a secure dashboard.

*What makes Sashi different?*

- *Real Code, Not Just Integrations:* Register your actual backend functions (Node/TypeScript) with a lightweight library. Sashi uses Zod for type-safe validation and auto-generates UIs based on your return types.

- *AI-Generated Workflows:* Describe what you want in plain English—Sashi’s AI chat interface builds and validates multi-step workflows, connecting your registered functions in powerful sequences.

- *No Admin Panels to Build:* Sashi provides a secure, auto-generated dashboard for your team to run, manage, and visualize workflows. No more custom admin UIs or glue code.

- *Secure by Design:* All execution happens server-side, with scoped API tokens and session management. You control your stack and infra—no vendor lock-in.

- *For All Teams:* Support, product, DevOps, and engineering can automate internal tasks, trigger backend logic, and collaborate—without waiting on developer cycles.

*How it works:*

1. *Register Functions:* Use the Sashi library to expose backend functions with type-safe schemas.

2. *Create Workflows:* Use the chat or flow builder to compose workflows—AI helps connect steps and validate data flow.

3. *Execute & Visualize:* Run workflows from a central dashboard, see results in real time, and auto-generate UIs (tables, cards, graphs, etc.) based on your data.

*Example Use Cases:*

- Support: “Refund a user” or “Reset password” via dashboard, no SQL or custom tools.

- Product: “Send weekly usage report to Slack” or “Find users who abandoned signup.”

- DevOps: “Spin up preview envs” or “Rotate API keys” as repeatable, auditable workflows.

*Try it or learn more:* https://www.usesashi.com/