Romain Lefort's profile on Product Hunt

About

Having experience in organization & management or even in the consulting activities mainly practiced in the banking market, I position myself as head of service and team leader in order to achieve companies' high expectations and objectives especially with their digital topics. Fitted with fine human qualities while being an organized, proactive, curious, observer and a thoughtful person, I always ensure the support of companies’ transformation by addressing continuous innovation, business operation transformation and customers’ experience improvement.

Badges

Tastemaker

Gone streaking

Forums

•

16h ago

git is quietly doing half the risk management

Think about what an agent session actually risks. It edits files in a working tree. If that tree was clean when it started, the entire session's damage is one diff you can read and one reset you can throw away. Branches cost almost nothing, so every task can live on its own one, and merging stays a human decision made after reading the evidence.

Underneath that sits the layer most people only meet in a crisis: the reflog. Every commit, reset, rebase, and branch move leaves an entry, kept for 90 days by default even when nothing points at it anymore. For a month or three, almost nothing an agent does to your history with everyday commands is actually gone.

We once had to defeat this on purpose: a clean-room experiment required one commit to be truly unfindable. Deleting it took five deliberate steps remove the remote, delete branches and tags, expire the reflog, garbage-collect, verify. Five steps to lose one commit. That's the strongest endorsement of a safety net we know how to write.

p/vois

•

20h ago

Vois 2.x goes live today: what should local text to speech do that cloud tools refuse to?

Hey everyone, Praney here, the maker of Vois.

Vois 2.x launches on Product Hunt today. The short version: a text to

speech studio that runs entirely on your desktop, with unlimited

p/openbox

•

7d ago

If your AI agent fails silently, who finds out first?

Imagine an AI agent responsible for routing inbound leads. Nothing crashes. No alerts fire. The workflow keeps running exactly as expected.

The problem is that the agent has slowly started sending high-value leads to the wrong queue. Maybe a few customer issues are being summarized inaccurately. Maybe records are being updated with small mistakes that seem harmless on their own. Each individual error is easy to miss. Over time, though, the impact starts to compound.

Those are the AI failures that interest me most because they rarely look like failures at first. There is no outage, no red warning message, and no obvious signal that something is wrong. The workflow continues operating, but the quality of the outcomes quietly drifts away from what the team intended.

That makes detection a different challenge altogether. It's less about system uptime and more about observation. Are there feedback loops? Quality checks? Escalation paths? Can someone spot a pattern before customers, revenue, or operations start feeling the effects?