AI Infrastructure Deep-Dive — September 24, 2026

Findings

1. [1] 2026-09-24 commit-rewriter 0.2

   Release: commit-rewriter 0.2 Support for branches other than the default branch. Use uvx commit-rewriter –branch other to run against another branch. #3 Tags: git

2. [2] 2026-09-24 datasette 1.0a41

   Release: datasette 1.0a41 Alec Garcia added support for OpenTelemetry to Datasette in this release. I've also refactored all of Datasette's modal dialogs to a single Web Component, which is now documented for other plugins to use. Tags: javascript, datasette, web-components, alex-garcia, opentelemetry

3. [3] 2026-09-24 Speaker-labeled transcription with WhisperX on SageMaker AI

   Any team working with spoken audio hits the same wall with generic speech-to-text. Think contact-center calls, all-hands meetings, podcasts, depositions, and broadcast media. These workloads need two things that standard transcription gets wrong. First, timestamps land at the utterance level,… A complete, runnable JupyterLab notebook that walks through these steps end to end is available in the AWS Samples repository. You can run it in Amazon SageMaker AI Studio against your own audio. Walkthrough: Real-time endpoint The real-time endpoint returns… Walkthrough: Asynchronous endpoint The asynchronous endpoint removes the 60-second cap and is the recommended path for long audio. Input and output are brokered through Amazon S3, and you poll for the result. Figure 2 is a sequence diagram that traces… Pin the GPU AMI – Always set InferenceAmiVersion=al2-ami-sagemaker-inference-gpu-3-1 on GPU variants. The default host AMI ships drivers that fail to start this CUDA 12.8 image. Scale by instances, not concurrency – Inference is serialized to one request per container. Set MaxConcurrentInvocationsPerInstance=1 on…

4. [4] 2026-09-24 Build a multi-account AI agent with AgentCore Gateway and MCP

   Enterprises increasingly want AI agents that can reason over data spread across many AWS accounts without copying or centralizing it. Each team keeps its data in its own account for good reasons: clear ownership, scope isolation, and independent deployment lifecycles.… When the agent invokes a tool, the Gateway retrieves OAuth 2.0 machine-to-machine (M2M) credentials from AgentCore Identity, attaches them to the outbound request, and routes it to the right LOB MCP server, which authenticates the token against Okta’s OpenID Connect… Figure 1: Multi-account AI agent architecture with AgentCore Gateway and MCP The following walkthrough traces a user’s question as it crosses account boundaries, invokes distributed tools, and returns a unified answer: The user logs in through the React webapp, which… @mcp.tool() def get_credit_score(customer_id: str) -> dict: """Get credit score and contributing factors for a customer.""" table = dynamodb.Table("CreditScores") resp = table.get_item(Key={"customer_id": customer_id}) item = resp.get("Item") if not item: return {"error": f"No credit score found for customer {customer_id}"} return item @mcp.tool()… { "agents": [ { "name": "lobfederation-agent", "authorizerType": "CUSTOM_JWT", "authorizerConfiguration": { "customJwtAuthorizer": { "discoveryUrl": "https://<your-okta-domain>/oauth2/<auth-server-id>/.well-known/openid-configuration", "allowedAudience": ["lobfederation"] } }, "requestHeaderAllowlist": ["Authorization"] } ] } After deployed, the agent reads the user’s JWT from the inbound request headers and passes it to… Because Policy in AgentCore uses a default-deny model, only actions with an explicit permit succeed. This gives the platform team centralized control over what the agent can do across registered LOBs, while individual LOB teams retain their own authorization at…

5. [5] 2026-09-24 Aderant builds intelligent ticket triage with Amazon Nova

   This guest post is co-written by Angela Mapes and Adam Walker of Aderant. In this post, we share how Aderant, a global provider of business management software for the legal industry, built an intelligent ticket triage system using Amazon Nova… Amazon EventBridge triggers AWS Lambda. The function retrieves credentials from AWS Secrets Manager, queries environment metadata through Amazon Athena, and calls Jira, Confluence, and Microsoft Graph APIs for ticket and knowledge context. Amazon Bedrock returns structured classification output from Amazon… Looking ahead Deeper client-history analysis: Connect related tickets over time to provide a broader view of ongoing client work. Improved knowledge matching: Evaluate Amazon Bedrock Knowledge Bases for semantic matching when ticket and documentation terminology differ. Layered AI support: Continue…

6. [6] 2026-09-24 Power your agents: Gemini 3.8 Live with Live Avatar is now generally available

   Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enterprise. First previewed at Google Cloud Next… Skill for building real-time, bidirectional streaming apps with the Gemini Live  If your application requires specialized, modular audio capabilities, explore our other audio models:   Gemini 3.5 Transcribe Gemini 3.5 Live Translate Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS…

Sources

1. [1] commit-rewriter 0.2
2. [2] datasette 1.0a41
3. [3] Speaker-labeled transcription with WhisperX on SageMaker AI
4. [4] Build a multi-account AI agent with AgentCore Gateway and MCP
5. [5] Aderant builds intelligent ticket triage with Amazon Nova
6. [6] Power your agents: Gemini 3.8 Live with Live Avatar is now generally available