BetterClaw

The Intern that asks before acting is the part I would build the whole product around, and it is also the part that quietly decays. We run approval-gated sending on our side, and the failure mode is never the agent doing something reckless. It is the human. Reviewing every action works until the volume goes up, then you start skimming, and the ones that get through are never the obvious ones.So the thing I would watch is what keeps an approval meaningful on day ninety. An agent that asks rarely, and only where it is genuinely unsure, is worth more than one that asks every time and trains you to click yes.

Is this like Hermes ?

Nice product to have! Keep building!

Someone on our team shared this and I set up an agent that pulls my calendar and Slack messages in the morning and sends me a briefing at 8am. That's it. That's my whole use case. Took about 2 minsThe Intern thing is smart. I would not have connected my work Gmail to something that could just do whatever it wanted. Knowing it has to ask me first made me actually try it instead of closing the tab.

Been burned by "no-code agent" tools twice before so I went in expecting to hit a paywall or a "contact sales" screen within 5 minutes. Neither happened.Set up a Gmail triage agent on a free Gemini key. Took maybe 90 seconds, not 60, but close enough. It's been running for 11 days now and the only time I touched it was to promote it from Intern after day 4 because I got tired of approving the same correct classification over and over.The BYOK part is what keeps me here. I switched from Gemini to Groq for one agent and to Sonnet for another, took about 10 seconds each time. No price increase on BetterClaw's end because they're not in the billing path.Solid tool. Genuinely free. Would've saved me about three weekends I lost to Docker last year.

Is it really going to be 0$ forever?

How does the agent 'earn' promotion, is that manual on your end or does it track some kind of track record automatically?

@shabb_katoch Congrats on the launch, Shabnam! Love that you doubled down on security from day one and also mentioning it right on the top of the fold in the website.

congrats on the launch you guys!

As an agent gets promoted from Intern to Specialist/Lead, can you set granular custom rules for what actions trigger a permission prompt, or is it based on predefined roles? Super excited to see where you take this!

I ran into what seems like a loop bug when retrying the agents. I initially tried it with a Groq API key, and even after switching to a Gemini API key, I kept getting the same error:“The agent hit an unexpected error while responding.”I’m not sure if the issue is with my API keys or something else in the retry flow, but sharing it here in case it helps you guys identify what’s going on

Congrats on the launch! The trust-level idea feels especially practical: starting agents as Interns before giving them more autonomy is a smart way to make non-technical users comfortable with scheduled AI workflows.

I like the idea of agents as Interns. That approval step could make this mucg easier to trust especially when connecting Gmail or Slack for the first time.

Not needing Docker or a VPS removes a pretty big barrier for people who just want an agent running. Congrats!

The "Interns that ask before acting" model is the right instinct, most agent tools skip that approval step entirely. Question on the other side of it: once an Intern acts on something external, an email sent, a Slack message posted, how do you verify the action actually landed rather than trusting the connector's own success response? I've spent today running browser automation and roughly one in three actions reported success while nothing actually happened, a click that never navigated, a submit that never posted. Curious whether BetterClaw checks real downstream state after an agent acts, or trusts the tool call's response.