[Hands-on workshop] Managing AI Agents in Production - Sep 17 — 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?
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!
If your organization is required to keep data in the European Union, you can now use AgentControl there. Prompts, configs, variations, and targeting rules are managed in the EU, with the same approval workflows and audit history you already use for feature flags. Model choices are limited to providers approved for the region.
To get started, read the AgentControl documentation for the EU. If you do not see AgentControl in your EU account yet, contact your LaunchDarkly account team.
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!
LaunchDarkly now stitches related LLM and agent spans into conversations, so a run that spans many traces reads as one transcript instead of a pile of spans. Open Traces and select the Conversations tab to see duration, models, providers, token usage, errors, and estimated cost for the whole run, then read the transcript turn by turn, including tool calls and their payloads, with evaluation scores shown on the turn they describe.
To get started, read LLM observability and Instrumenting LLM applications.
Our team is happy to help you instrument your application. To get help or share feedback, contact your LaunchDarkly account team or email product@launchdarkly.com.
Share link copied!
You can now configure Amazon Bedrock as a model provider, so inference keeps running in your own AWS account while your prompts and model settings live in LaunchDarkly. Compare candidate models in the playground, then swap a model or edit a prompt at runtime without redeploying.
To get started, read Getting started with Amazon Bedrock and AgentControl configs.
Our team is happy to help you connect Bedrock. To get help or share feedback, contact your LaunchDarkly account team or email product@launchdarkly.com.
Share link copied!
