AI Infrastructure Deep-Dive — September 23, 2026

Findings

1. [1] 2026-09-23 How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows

2. [2] 2026-09-23 From portal-hopping to instant answers: HEMA’s journey with MCP and Amazon Bedrock

   This post is co-written with Mauro Rallo and Patrick van der Plas from HEMA. When engineers at HEMA needed an answer, they went portal-hopping, navigating disconnected wikis, service catalogs, and IT portals to find it. To turn that friction into… Together, these gave us enterprise-appropriate footing: Entra ID OAuth, read-only access today, and access control driven by existing Active Directory groups, safe enough to expose real internal knowledge. Building HAL, step by step HAL didn’t arrive fully formed. It grew… Figure 4: The OAuth and DCR authentication sequence For the end user, the payoff is that configuration is only the proxy URL and an empty oauthScopes list, no AWS credentials, a browser login on first connect, and automatic token refresh…

3. [3] 2026-09-23 Agentic conversational video intelligence built on AWS

   With video intelligence powered by agentic AI, you can ask natural language questions about uploaded videos and get answers within seconds. Organizations across media, security, insurance, and professional services are generating more video than their teams can review. Meeting recordings… Amazon Rekognition provides visual analysis, including detecting objects, scenes, activities, and faces in video frames. The agent invokes Amazon Rekognition when the user’s question concerns something visible in the video. Amazon Transcribe converts spoken audio to text with automatic language… The rest of the production prompt inventories the available tools and defines workflows for file selection, cache reuse and explicit re-analysis, BDA setup and access-denied fallback, reference-image search, transcription and captions, sports highlights, architecture diagrams, and choosing between BDA and… [Response] Here's the meeting summary with chapters: Summary The team discussed the Q3 roadmap… Chapters – 00:00 – Introductions When results are ambiguous, the agent communicates uncertainty explicitly. A borderline confidence score (for example, 62 percent) produces a qualified answer:… The $6.00 Amazon Rekognition cost is one-time per-video costs (subsequent queries only incur Bedrock reasoning costs). Based on AWS service pricing as of July 2025 and the preceding cost table, a typical transcript-based query on a 60-minute video costs approximately… Current limitations Videos longer than two to three hours require several minutes for initial transcription, though subsequent queries return near-instantly from cache. Face-matching accuracy depends on the quality of the reference photo. Clear, well-lit images produce the best results, while…

4. [4] 2026-09-23 Use open weight models as your AI coding agent with Amazon Bedrock

   AI coding agents have become a core part of how developers write, debug, and refactor software. Open weight models on Amazon Bedrock now make these agents practical to run privately and cost-effectively. But most options require you to send your… Reasoning depth: For complex debugging, architecture decisions, or plan generation, reasoning models trace through problems step by step. Kimi K3 reasons before answering. You set the depth with reasoning_config (low, high, or max). You trade latency for correctness on hard… Figure 2: OpenCode generating the event-sourced CQRS order service with GPT-OSS 120B OpenCode routes this to GPT-OSS 120B through the Bedrock Converse API with IAM authentication. The model generates the full service structure, including handlers, event store, projections, and CDK… This routing can help reduce overall total cost of ownership (TCO) compared to sending everything through a single expensive model without degrading quality. The Amazon Bedrock unified API makes this practical: switching models is a parameter change, and the models… Aris Tsakpinis Aris is a Senior Specialist Solutions Architect for Generative AI focusing on open source models on Amazon Bedrock and the broader generative AI open source community. Alongside his professional role, he is pursuing a PhD in Machine Learning…

5. [5] 2026-09-23 Gemini 3.8 TTS Playground

   Tool: Gemini 3.8 TTS Playground Google released two new Gemini text-to-speech models today – gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. They come with a library of over 2,000 voices, plus the ability to create a custom voice with "just a 30-second audio sample of your voice or a voice you have the rights to use". I vibe coded this bring-your-own-key playground interface with…

6. [6] 2026-09-23 Shadow roots, explained with live examples

   Tool: Shadow roots, explained with live examples Prompt to Fable 5.1 Medium: Build an artifact to explain shadow roots in CSS with interactive examples Tags: css

Sources

1. [1] How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows
2. [2] From portal-hopping to instant answers: HEMA’s journey with MCP and Amazon Bedrock
3. [3] Agentic conversational video intelligence built on AWS
4. [4] Use open weight models as your AI coding agent with Amazon Bedrock
5. [5] Gemini 3.8 TTS Playground
6. [6] Shadow roots, explained with live examples