LaunchDarkly

Nobody wants to talk about the AI-generated code sitting in their codebase that they reviewed once and never thought about again. So, how confident are you that it's doing what you think it is?

Has everyone seen this yet?! We're #1 in Feature Management in the G2 Spring 2026 Grid® Report. Again! 99/100 satisfaction, 97 overall G2 Score, all powered by real customer reviews. Thank you to everyone who showed up! Check out the full report → bit.ly/3PsLWBz

TLDR if you don’t feel like reading 20 pages: 379% ROI 20% boost in dev efficiency failure rates down from 50% to 3% Turns out control after deploy matters more than speed. If you do have the time to read, we’ve got you: bit.ly/4lFuLsG

let’s be real for a second. if your team is shipping faster but still rolling back every week, something isn’t adding up. speed isn’t the problem anymore, what happens after deploy is. you know how that story goes. 🤷 more here: bit.ly/4rB43m4

AI output is rising, so your level of quality shouldn’t drop. Customizable judges are now GA in AI Configs: -Define what good looks like for your product -Monitor it during rollout -Pause or roll back when quality shifts Implementation steps in docs: bit.ly/4rq6OXi

@forrester jjust validated what our customers have been saying for years. When a third party interviews your customers and calculates a 379% ROI, you know the impact is real. This report captures the wins that actually matter to engineering teams: lnkd.in/g6cHRUWx

It always starts small A simple JSON file works great at first. Over time, it grows into production infrastructure with databases and APIs layered in. What started as a shortcut becomes critical. That’s when runtime risk becomes real. → bit.ly/47Ck9ET

OUTAGES HAPPEN. This isn't anything new; infrastructure goes down sometimes. It's moments like this that make you appreciate when switching models or rolling back is simple and doesn’t require a deploy.

Ways to control your AI feature in production ranked: 8. ship 7. it 6. then 5. hope 4. the 3. rollback 2. works 1. LaunchDarkly

sales team: “Let's circle back to align on next steps and ensure we’re providing a seamless customer experience.” developer team: "can u handle this"

DeveloperWeek 2026 is coming up, and we’re making it a little easier to say yes. We’re giving away 50 free tickets for developers who want a week that’s actually worth leaving their desk for. Grab a ticket while you can: bit.ly/3Z15ZZy

be honest...this is exactly how you’re sitting right now.

pretty simple call honestly. one system should not serve both users and learn at the same time. lots of “AI problems” are really system design problems.

🎙️ Tom Totenberg, head of release automation at @LaunchDarkly, sits down with us to discuss the perils of taking too many shortcuts in software development, the danger of cutting corners with AI code tools, and the importance of balancing speed with sustainability. stackoverflow.blog/2026/01/02/the…

@green4ranger @ABTasty @VWO @statsig Thanks and noted! If you have any other pains pls let us know.

A/B Testing Tools Tier List 🧵 I really wanted @LaunchDarkly in the GOAT tier, my personal favorite but it just doesn't cut it. Requires some learning to adapt, also some recurring dashboard bugs, overall fire though 🔥

“Just point it at a folder.” Sure, what could possibly go wrong? All jokes aside, @claudeai Cowork makes powerful agentic workflows much easier to use. Just means we all need to be a little more thoughtful about how we guide these tools.

inspired by Hamnet’s Golden Globes win last night can't help but wonder what Shakespeare would make of modern developer life

@green4ranger @ABTasty @VWO @statsig I'm glad we at least made the list. Do you mind sharing some of your thoughts and feedback? We would love to know!

if you were wondering where the focus is shifting, this feels like a pretty clear answer. observability is clearly going to be the focus of the year.

you get one programming language for the next decade which are you choosing and why?