Automate review and auto-approve low-risk changes; escalate only exceptional cases
Automate review for the most part and only escalate to humans for exceptional cases. Auto-approve low-risk or internal changes to remove further bottlenecks.
42,308 results · Most relevant
Automate review for the most part and only escalate to humans for exceptional cases. Auto-approve low-risk or internal changes to remove further bottlenecks.
Enforce policy rules beyond CI — code compiling doesn't mean it complies with specifications like HIPAA or DORA; agents won't be aware of these unless enforced. A green CI does not mean the code is compliant in many cases.
Consistency beats intensity — a principle from Dan Garner — and adherence is the number one predictor of physical fitness outcomes in the literature. Choose a training program you will engage in, put effort into, and repeat consistently over time.
Dr. Andy Galpin says that for exercise splits, you shouldn't worry about which body parts to package together — only worry about how many times per week and total volume you achieve on a muscle group per week. How training is folded into a split is really a personal preference issue.
Dr. Andy Galpin argues that performing a movement without maximal intent will not produce the desired adaptation: a box jump done without powerful intent will not increase power, and intentionally lifting slower only reduces acceleration and therefore strength gains. He emphasizes executing every strength exercise with high intent, which also allows flexibility in how much load goes on the bar.
When adding type, systematize the font family (e.g., Inter, Instrument Sans), the font size, the matching line height for each font size, the font weight you're going to use, the purpose of use for each type style, and adjust letter spacing and tracking.
Katie lays out five goals for an RKO: culture building (the most important — a sales culture where everyone works together and is inspired by one another), inspiration (reps leave pumped to tackle the market), education (while warning enablement leaders often overcorrect and make the whole event about education, since people can't remember everything heard in a two-day period), celebration (the team worked hard all year whether they won or lost), and jumpstarting the year (doing actual work at the kickoff so the team is running by the next week in January).
described
A metric in the severe range will cap your performance. Get it up to just sufficient or concerning so it stops limiting you, then pursue optimization in any area you have a specific passion for.
The host argues that if you don't feel pain and grief, you will become numb to beauty — and getting everything you want doesn't matter if you can't feel it. He recommends breathwork for 20 or so minutes as a cheat code for accessing feelings you didn't think mattered, and says that once you clear the emotional sludge, you can be present, which makes you more creative, more dynamic, and more charismatic.
Dr. Chris Thompson cites the Whitehall II study, a prospective longitudinal study of British civil servants that tracked many metrics including fasting insulin. It found that people with high fasting insulin were more likely to get diabetes long-term, detectable 10-15 years in advance. He notes that no one acts on this finding because no one looks for fasting insulin, and that there are signs of metabolic dysregulation much earlier than a high A1C or high ApoB.
Jake Tuura advises that to know what is stressing and straining a tendon, look at the associated muscle and how hard it is working; the force or torque coming from the muscle is what tells you what is going on with the tendon, since the tendon is just the middleman between the bony position and muscular force.
Brooks states that people learn best by learning how something works, then actually practicing it, then teaching it — noting there is a ton of research on how people learn. The same process is true for golf, speaking Spanish, and understanding how to live a better life.
endorsed
Rick Rubin says that by the completion phase you can have a deadline and it won't hurt the project — it might even help. But if you dictate a deadline, keep it private to yourself rather than public, because a public deadline makes it harder to extend the project when a new discovery shows the work could be much better with more time.
Rick Rubin describes the seed collecting phase as wide open with no deadlines, and says he is always in phase one — collecting seeds all the time, whether or not he is working on a project, noting anything that interests him or has potential.
Breaking away from the current topic to voice real-time observations about her is rated S-tier; observations can also become labels or hooks for later techniques.
The coach advises against sitting down right after opening a conversation. He recommends carrying the conversation standing up for at least the first minute (or one to two minutes) before pivoting to sit down, and only sitting once there's enough interest from the woman.
If the sales process takes too many calls, too long, or generates too many questions, prospects need more education ahead of time. Educating prospects before asking them to buy produces more money, more convicted buyers, fewer and shorter conversations, faster purchases, and more prepayment. The one downside is losing some people who don't make it through the education, but in in-person selling environments where prospects are already at the office, there is no downside at all.
Solve the supply constraint first, and then the other things on the pipeline can increase. More marketing on a supply constraint does nothing; it does not increase throughput. Only pursue additional marketing if you have bandwidth after solving constraints. Marketing only works if you have a way to capitalize on the demand it creates, though the more people know about your business, the more money you make.
The first sandboxing strategy people experiment with is running agents inside Docker containers on their laptop — this is how OpenHands originally launched, spinning up a new container per conversation. Containers are ephemeral, so if the agent runs rm -rf / you just kill the container and start again. You can selectively mount things from your local file system (like a Git repo), mount ports so you can view the app in your browser, mount specific secrets and environment variables, and run MCP servers locally or inside the container. It's nice because the agent works with your local copy of the code and you decide when to git push.
The next strategy is gluing together Claude Code and GitHub Actions: the agent runs in an ephemeral environment inside GitHub Actions, clones the repo, does its work, and everything goes away when the action spins down. You can run as many agents as you're willing to pay for, GitHub Actions has built-in support for things like a secrets registry giving nice isolated environments, and you can run agents on a schedule (e.g., a Monday 9 a.m. dependency update) or on events (e.g., agent code review any time a PR opens).
Choose sources → to get a library of your own and a daily brief.