LaunchDarkly

Runtime control for the AI era. Helping engineering teams ship, govern, and control code and AI agents in production without waiting on a redeploy. 🚀🧑‍🚀

[LaunchDarkly @LaunchDarkly]

Can't wait to talk about all things AI!

[The AI Conference @AIconference]

As AI systems become more complex, safe and controlled deployment matters more than ever.

We’re proud to have @LaunchDarkly as a sponsor of The AI Conference 2026, helping teams ship, test, and iterate on software and AI-powered products with confidence.

[Sociaall Inc. @dez_blanchfield]

I had the pleasure of catching up with Tom Totenberg, Head of Release Automation at @LaunchDarkly, to discuss their latest news, insights & more, as well as their sponsorship of the 2026 #BeerOps 2026 events. Click to tune-in to this great conversation:

https://t.co/XEtMcExj1c

[Andy McLoughlin @Bandrew]

Since launching in 2015, @LaunchDarkly has been synonymous with enterprise-grade feature management (50 trillion feature evals per day, serving many of the most exciting companies in the world).

Today they're announcing AgentControl, the first product as they become the runtime control platform teams trust to move quickly with AI. While staying in control of code (and agents) in production, of course. Very excited for LD's next chapter! 🚀

[LaunchDarkly @LaunchDarkly]

Every engineering team is already asking these questions. On June 11, we're answering them.

Be in the room → https://t.co/K0HKtH8Vg2

[LaunchDarkly @LaunchDarkly]

G2 named us a Leader in Feature Management for Summer 2026!!!

Customer recognition means everything, so thank you for the trust and honest reviews.

See the full report: https://t.co/PYbWPGnX0o

[LaunchDarkly @LaunchDarkly]

The teams pulling ahead have already figured out what comes after shipping AI.

On June 11, @edith_h , Cameron Etezadi, and Marek Poliks are talking runtime control, production safety, and what hasn't worked. Come find out → https://t.co/1qlluUME62

[LaunchDarkly @LaunchDarkly]

So proud of this one! The team crushed it, and @speakeasydev was an incredible partner on the MCP server.

[Speakeasy @speakeasydev]

@LaunchDarkly launched AgentControl today: runtime control for AI agents in production, with configuration changes that propagate in under 200ms, fast enough to reroute a model or trigger a fallback mid-conversation.

LaunchDarkly partnered with Speakeasy to build the MCP server that lets AI agents interact with AgentControl programmatically: creating flags, configuring targeting rules, managing rollouts. The same workflows human developers rely on, now accessible to agents.

What surprised them was how quickly it became useful internally. Their own engineers started using it daily to clean up stale flags accumulated over years. What was scoped as a customer-facing product became infrastructure for their own team.

Benjamin Woskow, their Senior Director of Engineering, said their takeaway was that building the MCP server wasn't the hard part. Keeping it production-grade as the protocol evolves is where the overhead accumulates. Speakeasy owns that layer so they don't have to.

The full story: https://t.co/F4bQl0X3Xl

[LaunchDarkly @LaunchDarkly]

AgentControl is live! 🚀
Real time model swaps, automatic rollbacks, guardrails that block bad responses before they reach a customer, and Agent Optimization that handles the tuning for you. One place to manage your agents in production. Try it for free → https://t.co/tIRyTjmotf

[LaunchDarkly @LaunchDarkly]

Today we shipped something that reflects over a decade of thinking about what it means to control software in production. AI agents are now making decisions on behalf of engineering teams, and that changes the mission entirely.

[Edith Harbaugh @edith_h]

I started LaunchDarkly because teams deserved better control over what they shipped. With AI, that matters more than ever.

Today we’re launching AgentControl: real-time visibility and control for AI agents in production.

https://t.co/X0QuAksjtn

[LaunchDarkly @LaunchDarkly]

The AI era needed a new kind of control layer, and today we shipped ours.

AI delivered on speed, innovation, and agents that get things done. Keeping up with what they do in production is where it gets interesting.

Stay close 👀

[claire vo 🖤 @clairevo]

I love past me for asking @LaunchDarkly to build this AI configs product

[LaunchDarkly @LaunchDarkly]

We'll be at LeadDev London! If you're an engineering leader looking to ship AI faster without things going sideways in production, come find us.

Grab some time ahead of the event → https://t.co/ilKrCgbLbx

[LaunchDarkly @LaunchDarkly]

Multi-agent observability: staring at disconnected traces until something starts to make sense. There's a better way 😏

Agent graphs put your entire workflow on one screen so you can spot issues and fix them without a redeploy → https://t.co/IFSB0HBWcK

[LaunchDarkly @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?

[LaunchDarkly @LaunchDarkly]

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 → https://t.co/hGpM5iQUdg

[LaunchDarkly @LaunchDarkly]

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: https://t.co/hN4sa2a6Qe

[LaunchDarkly @LaunchDarkly]

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: https://t.co/C7oIXp855C

[LaunchDarkly @LaunchDarkly]

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: https://t.co/pgsL8mA0nB

[LaunchDarkly @LaunchDarkly]

@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: https://t.co/Sc3eOC0kzV

[LaunchDarkly @LaunchDarkly]

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.

→ https://t.co/oQQmKteEqz