[Virtual event] Automate Your Software Factory - Nov 5 — Save my seat
What makes experimentation with LaunchDarkly stand out among other tools on the market?
What makes experimentation with LaunchDarkly stand out among other tools on the market?
What makes experimentation with LaunchDarkly stand out among other tools on the market?
You can now run a warehouse native experiment where audience assignment comes from a table in your own warehouse rather than a LaunchDarkly flag evaluation. If your team randomizes in its own service, or assignment happens in a third-party tool such as an email platform, those tests can now be analyzed in LaunchDarkly with the same statistics, exposures, and sliced results as any other experiment, rather than rebuilt in a notebook or dbt.
It works backwards too: assignment data already sitting in your warehouse can be analyzed retroactively, so you can get a read on a past experiment without waiting out a fresh one. Define an assignment source once and reuse it across experiments in the same project and environment.
See Assignment data sources and Manage assignment data sources in our documentation to get started.
Share link copied!
A dataset holds the inputs for an offline evaluation, where each row is one case that AgentControl runs your config against and scores. You can now edit those rows in place instead of uploading a replacement file every time one of them needs to change.
Open a dataset from the AgentControl Library page and you get a Rows tab. Add a row by hand or append a file, edit a row's input, expected output, variables and metadata, search by input or expected output, drag rows into a different order, and delete the ones you no longer want. You can also create an empty dataset and add rows to it, rather than needing a finished CSV or JSONL file first. Changes stage until you click Save, so a whole editing session commits at once.
Each save creates a new dataset version that records who made the change, when, and the resulting row count, and you can open any earlier version or restore it. Evaluation runs pin to the version that existed when the run started, so editing a dataset never changes the results of a run you have already completed.
To get started, read Datasets.
To get help or share feedback, contact your LaunchDarkly account team or email product@launchdarkly.com.
Share link copied!
You can now work out how much traffic a frequentist experiment needs, and how long it will take to get there, inside LaunchDarkly. Start from the experiment list for a quick gut-check before you commit to a design, or from the builder to attach the estimate to that iteration, so the experiment carries its own sample size target and anyone reviewing it can see when it's ready for a decision. You can view, edit, or remove that target from the results page while the experiment runs.
Settling on a sample size up front is what holds your false positive rate to the significance level you chose, and until now it meant a spreadsheet or a separate trip to our website. Estimates assume steady traffic, so an experiment may hit its sample size earlier or later. Available for fixed-horizon frequentist experiments.
Read Sample size calculations (https://launchdarkly.com/docs/home/experimentation/sample-size-calculator) and Sample size calculations for frequentist experiments (https://launchdarkly.com/docs/guides/experimentation/sample-size-calc) to get started.
Share link copied!
AI SDKs are now available for Go and Java. Your prompts, model settings, and targeting rules live in AgentControl configs instead of your code, so you can change a prompt, swap a model, or roll a variation out to a single customer segment without a deploy. Both SDKs report generation counts, token usage, latency, and errors back to AgentControl so you can watch cost and performance per config, and both run multi-step agent graphs.
To get started, read the Go AI SDK reference or the Java AI SDK reference.
Our team is happy to help you get set up. To get help or share feedback, contact your LaunchDarkly account team or email product@launchdarkly.com.
Share link copied!
Keep the gateway you already run, and decide the model, prompt, and parameters per request instead of per config file. Give enterprise customers your strongest model and free users a cheaper one. Roll a new model out to five percent of traffic, watch quality and cost, and revert in seconds if it degrades. None of it requires editing YAML, restarting the proxy, or shipping code, and every change is attributed and approval-gated like any feature flag change.
To get started, read Use LaunchDarkly AgentControl to control model administration with LiteLLM.
Our team is happy to help you set this up. To get help or share feedback, contact your LaunchDarkly account team or email product@launchdarkly.com.
Share link copied!
