The difference between a tool an agent chooses to call and a step that runs every time is the difference between a suggestion and a guarantee.
Microsoft's Copilot Studio documentation now describes a preview feature called hooks. The definition is plain: a hook runs one of your workflows automatically when something happens in your agent, and you use it "when you need something to happen every time, rather than only when the agent decides it's relevant."
"Companion chatbot" sounds like a product category you would know if you were in it. The statutory definition is broader than that, and the duties are already live.
California SB 243 (Chapter 677, Statutes of 2025) took effect on 1 January 2026. If you ship anything conversational and emotional, it is worth reading the definition against your product instead of assuming it is about someone else.
On 2 October Apple said it will make granting Full Disk Access on macOS require more explicit user action, and it named AI agents as the reason. If you let agents touch your files, that's a prompt to audit what you've already handed over.
On 2 October Apple posted a short developer news item titled "Updates to Full Disk Access in macOS." It says Apple will add controls that require more explicit user action when Full Disk Access is granted, because some developers misuse it to reach sensitive data such as files, mail, messages and browsing history without the user fully understanding. The sentence I keep coming back to is this one: "As AI agents become increasingly capable and autonomous, the risks associated with this level of access will grow substantially."
After our first launch on Product Hunt, our team spent a little over a month upgrading the product. There were major changes to the UI and several new features added, so the process took time from discussions and redesigning the interface to testing, fixing bugs, and updating AI prompts.
We re also a very small team, so everyone had to push themselves to give 200%. Time and resources are limited, and at the same time, we also had to work on securing funding for the next six months to keep the team running and continue developing the app.
Everyone building anything emotional with AI reaches for the emotion recognition article. The sentence that is more likely to apply to you is in Article 50(1), and it has applied since 2 August.
When I went looking at what the EU AI Act asks of an app like Murror, I assumed the provision about emotions was the one aimed at us. It isn't, quite, and the one that is aimed at us is simpler and already live.
I ve been working on another product alongside Murror a side project we re experimenting with, built almost entirely through AI. I m not a developer. I can t read most of the codebase. But I shipped a feature that three users have already told me feels exactly right.
On 6 October Sierra announced the Personal Agent Protocol, an open standard it is developing with Meta for how a consumer's AI agent deals with a business. On 9 October it published a first draft, called Poppy (Draft 0.1). Sierra sells customer-service agents, so read its framing as a vendor's view. The mechanics are worth learning from anyway.
A business publishes a file at /.well-known/poppy.json telling agents how to start a session and how customers sign in. The agent identifies itself and can begin as a guest, for example to check stock or a returns policy. When a task needs an account, the customer signs in on the company's own page using OAuth 2.0. Sierra's 6 October post says the customer chooses between read-only and write access. One session can span the website, the APIs (OpenAPI and MCP are named) and the company's own agent.
Six months ago, our team was obsessed with making Murror's AI more intelligent. Better pattern recognition, deeper emotional analysis, more insightful reflections. Every sprint, we'd ship something that made the AI sound smarter.
Our team is planning to launch a new version of our product on Product Hunt next week, after a period of optimization and improvements. As we get closer to launch day, I realize there s a lot to prepare, and I m curious about how other teams usually approach this process.
So far, here s what we ve been focusing on:
Most importantly, making sure the product works well and delivers real value
Continuous testing to ensure performance and stability
Designing clean and clear product screenshots
Preparing a summary of what s been updated, fixed, or optimized
Writing launch content (tagline, description, first comment, etc.)
Maintaining good health and a stable mindset for the launch
Expanding our network and connecting with other makers
Most software wants you to come back every day. The business model depends on it. More sessions, more engagement, more opportunities to monetize.
But what happens when your product's purpose is to help someone understand themselves better? At Murror, we've been wrestling with a paradox: if we do our job well, users should eventually need us less not more.
