... tags, sources, and connection counts. More AI languages AI language support is much broader. You can choose from 62 languages for summaries, quizzes, and tags, including Traditional Chinese. Caption and transcript language matching is also more accurate for Simplified versus Traditional Chinese. New AI models More models are now available in the picker on the Max Plan, including GPT-5.6 Terra, GPT-5.6 Luna, and Grok 4.5. We will release more documentation on which model to use when ... ... release notes . Customer story - Ricardo Yule's nine-step trails

... issues, and changing usage patterns tend to show up here first. 2. AI Evaluations (Evals) Models improve. Prompts change. Workflows evolve. Evals help teams measure output quality, compare versions, and catch regressions before they become bigger problems. 3. Audit Trails & Traceability When someone asks why an AI-assisted decision was made six months ago, audit trails

... thing I've noticed with AI audit trails is that they tend to do a good job of recording events but not always the reasoning behind them. Take a simple example: An AI-generated report goes through an internal review before being shared with customers or stakeholders. Someone makes edits, approves the final version, and the workflow moves forward. Months later, if you look back, the audit trail

... launch support. Being clear about which pain you solve is half the battle. Manually reviewing real founder posts to test the tool is honestly the right approach at this stage. It's slow but it teaches you what real vs performative feedback needs actually look like. Automation comes later. Comment from Shahriar M Abu Hena(@imshaik0t): Thanks @nolan_vu for this thread. https://www.producthunt.com/prod... A year ago I started teaching an AI to cook, on evenings and weekends. This ... ... Comment from Ryan Weller(@ryan_weller): What you're building TrailSmoke

... action already happened. A person could intervene but the system makes it slow and inconvenient. One person monitors a dashboard tracking 40 agents running tasks they do not fully understand. None of that is oversight. It is a paper trail. The problem is not that people are lazy or careless. It is that most agent systems are built for speed first. Oversight gets added later to satisfy a compliance requirement or a nervous investor. The human ... ... shut it down. That was a design choice, not an afterthought. Three questions I want to put to people who actually build or deploy these systems: What does real oversight require? Veto rights? Visibility into the reasoning? Full audit trails