We built Toward to solve our own problem —multiple projects everywhere, updates scattered, nothing organized. It's stupid-simple: update what happened, system threads it, intelligence surfaces. We've been using it internally and thought HN might appreciate it.
We’ve been experimenting with a “propose → approve → execute” workflow (like you suggested with “pause the underperforming ads”), so the AI drafts the plan, but a human clicks yes before it runs. Kind of like a pull request for actions.
Version control / auditability is a great call — especially if people want to roll back or see exactly what changed. We’ve been thinking about logging each action almost like a Git commit history for ops, so nothing is a black box.
Do you think teams would adopt “propose + approve” mode first, and then maybe move to full autonomy later as confidence grows?
Most teams we talk to still juggle data across Gmail, Slack, CRMs, Ads, spreadsheets, and custom internal systems. The dream is:
- Ask a natural-language question (“Which campaign gave us the best ROI last month?”) - Get the answer instantly, without waiting for a data team - And even take an action from the same place (“pause the underperforming ads,” “send a report to Slack”)
The obvious challenge: trust.
Would you let AI touch your production data or execute actions? Or should it remain read-only, with humans approving the final step?
We’ve built something in this space (hyperif.com), but I’m genuinely curious how you all see the balance between convenience and control.
- Where do you draw the line today? - What guardrails would you expect? - Is “analyze only” useful, or would “analyze + act” be the real unlock?
Would love to hear your perspectives.
Hi HN,We’ve been working on Hyperif, an AI assistant that connects directly to your tools (Google Calendar, Gmail, Slack, Ads, spreadsheets, etc.) so you can access data and take action — just by chatting.The idea came from our customers. Over the years, we’ve had teams come to us who struggled with building workflows and never really understood APIs. They always needed help setting up their...
I am the founder and am happy to answer any questions regarding user auth and app authorization
We are Sameera & Ralph, co-founders of Pathfix (https://pathfix.com).We have been working very closely with the no-code community for a few months now trying to bring our low-code oauth integration platform to the no-code community, starting with Bubble.Based off of these discussions, we released a few plugins that handle:- Entire oauth process for each provider - End-User authorization -...
So, I built Pathfix. I wanted to take away the pain of managing OAuth servers and tokens with an easy to use solution that allows you to offer integrations to your customers, in minutes.
Happy to answer any questions.