DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.

1,180+ deals tracked  ·  22 AI investment memos  ·  Updated daily

← Back to leaderboard

Agent that refuses to run commands without human approval

Show HN: Agent that refuses to run commands without human approval

53 AI Score
Show_hn devtools Added Apr 30, 2026

Details

Sector
devtools
Total Funding
$0
Last Round
$0

About

In light of recent news about an agent deleting a production database, I thought now would be a good time to share this.<p>As the use of AI tools in production is becoming more common, sadly so will the high profile incidents like the one mentioned.<p>Fewshell is a terminal agent specifically designed to avoid this.<p>There is no setting to enable command auto-approval. This is by-design, so that the user never has to second-guess or worry about accidentally having it enabled.<p>Originally my intention was to build an AI mobile terminal to make typing shell commands easy. But with so many mobile-enabled &#x27;claw&#x27; agents being available, I decided to make Fewshell the opposite of an autonomous agent.<p>Please star if you like, let me know what you think. Happy to answer questions.<p>About me: I&#x27;m an ex Amazon Sr. SDE for Alexa AI, and currently am working in AI safety research for agentic RLVR. I use this tool to run and check on my lab experiments.

AI Score Reasoning

The founder's background in AI safety and experience as a Senior SDE at Amazon provides strong technical credibility for a timely problem. However, the product currently functions more as a niche utility or feature than a standalone company, with a low defensive moat and minimal traction beyond a small community signal.

Source

Show_hn — View original →