One challenge I've noticed in workplace learning is how much attention goes into creating and delivering courses, while what happens afterward gets less attention.

Employees may complete training, but when they face a real situation at work, they often still need guidance, clarification, or practice.

I've been building an AI-powered invoice and payment workflow, and one question keeps coming up:

Should an AI agent that recommends a payment also be allowed to execute it?

During testing, I ran into an interesting problem.

An invoice could look perfectly valid, but there was no confirmation that the work had actually been delivered.

A couple of years ago, sharing revenue numbers and progress updates on X felt like a cheat code. Now my feed is full of Day 47 of building my SaaS posts, and I m not sure anyone is reading them anymore, including me.

I ve been posting updates, and it s brought honest result, e.g. some founder friends, but very few actual customers.

Has building in public brought you real customers, or mostly other builders?

If you still do it, what kind of posts actually get traction for you?

After Spotify celebrated its 20th anniversary with a new logo (the Spotify disco ball), it was criticised by many people, and dozens of other brands followed suit, also making a disco logo as a form of recession.

I don't think it was that bad. I'm not a graphic designer, and I can see that the contrast there is not good, but I still think there are many worse designs and rebrands.

A real situation from freelance work: a project was delivered and approved, and then the client sends a change every few days. Each one takes 15 minutes, so saying no feels petty. After a month it is several hours of unpaid work and the client has stopped treating it as extra.

The options I know: a fixed number of free changes in the contract, a small monthly support plan, batching requests into one weekly list, or just charging every time. Each has a cost, and the first one only works if it is agreed before the project starts.

Many people who want to achieve the Product of the Day badge prefer to schedule their product for a less busy day (aka, when there is less competition), but also less site traffic and product testing.

You may lose a little promotional opportunity this way.

Today, I m doing a slightly more relaxed and bizarre corner.

The internet is full of things that are either amusing or scary, but mostly things that capture something outside the norm (and over time, even these weird things tend to become normalised).

I thought feeding the entire repo to the agent would make it smarter. Instead, it starts getting distracted by legacy code and tries to "clean up" stuff completely unrelated to my prompt.

you literally ask for a button color change and it delivers a pull request touching twelve different files.

How do you guys restrict the working directory or keep the agent focused on just one file?

I was reading up on API spend limits for a post, and one detail stuck with me.

On Anthropic s standard tiers there s a monthly spend cap ($500 on the lowest). When you hit it, requests come back as a 429 that looks like a rate limit, but with no retry-after header. Automatic retries just keep failing until the 1st. OpenAI s hard spend limits return 429s too.

Run it on an ordinary month: $280 spent by day 10, about $32 a day. That crosses a $500 cap on day 17. The invoice would have said around $920, but the app stops working almost two weeks before anyone opens it.

Do you know which day your app would hit its limit, or do you find out when users start reporting errors?