The architecture solves visibility gaps caused by isolated native logging, which previously limited companies to analyzing high-level aggregate bills. Subscription log filters collect raw invocation records from local accounts and deliver them through Amazon Data Firehose into a single querying repository. Platform engineers can then use Amazon Athena to inspect flattened call details, including the exact prompts, model outputs, and stop reasons such as hitting token limits. The entire deployment is packaged as infrastructure as code across two AWS CloudFormation templates available in a public repository.
Key points
Centralizing raw telemetry enables platform teams to calculate precise per-invocation cos…: Centralizing raw telemetry enables platform teams to calculate precise per-invocation costs across multi-account deployments.
Infrastructure as code templates allow organizations to deploy the unified observability…: Infrastructure as code templates allow organizations to deploy the unified observability architecture using repeatable CloudFormation scripts.
Consolidating invocation records reveals exact token consumption and stop reasons that ag…: Consolidating invocation records reveals exact token consumption and stop reasons that aggregate cloud bills typically obscure.
Sources checked by our analysis pipeline: 1
Artificial Intelligence
Amazon Bedrock tokenomics data lake
If you need an observability data lake for your Amazon Bedrock workloads, you’re not alone. When you’re running thousands of model invocations a day across multiple accounts, after a request is sent you might be wondering, what happened? You can see the aggregate bill, but you can’t see what happened inside each call.
You might start to ask questions: what prompt was sent, what the model returned, how many tokens it used, which model handled it, and whether the response was any good! If you’re a platform or machine learning (ML) engineer looking after a fleet of Amazon Bedrock workloads across teams, that’s a real problem. You can’t debug a spike, you can’t spot wasteful prompts, and you can’t tell one team’s usage from another’s.
We built something to help: a centralized observability data lake for your Amazon Bedrock invocations. In this post, I cover what native data you have and how we designed the lake. I also show how to use it to see your prompts and derive the per-invocation cost. The…
A new beta hub allows verified enterprises to manage their presence and launch specialized agents for direct customer inquiries on the artificial intelligence platform. This strategic pivot focuses on commercial discovery and engagement tracking rather than facilitating direct e-commerce transactions. The transition positions the service closer to established search engines by serving as an informational directory for consumers.
The latest rollout introduces tools that facilitate direct communication between enterprises and everyday consumers on the AI platform. Organizations gain the ability to establish an official presence through a dedicated hub while deploying automated agents to connect with an audience. This move expands the software's functional scope into corporate customer engagement.
Developed by Amazon Connect Customer, this newly released open-source system enables enterprises to run predictive analytics across structured business data without creating bespoke machine learning setups for every task. By using in-context learning to infer missing values from unseen tables, it reduces the friction of deploying tailored algorithms. The release is published under an Apache-2.0 license on Hugging Face to broaden commercial and research adoption.