DevRel newsletter — September 2026
Hello from the Elastic DevRel team! In this newsletter, we cover jina-ocr-v1, the latest blogs and videos, and upcoming events like Elastic{ON}.
// Company Updates
All companiesFrom the Industry Leaders
When to choose x86-64 vs aarch64
ARM and x86 can give you different performance at the same vCPU count. Here's what differs, what to measure, and how to choose.
DuckDB and Hugging Face: Querying Datasets Directly
Hugging Face hosts hundreds of thousands of datasets, and DuckDB can read them directly, exactly where they are and without downloading anything, over the DuckDB `hf://` protocol. This post looks at...
Automating coherent long-form video generation
Generative AI
Ship agents faster with expanded model choice, voice agents, and continuous optimization
The best model for your business will keep changing. Adopting it should move your business forward, not send your team back to rebuild the architecture around it. The post Ship agents faster with...
New in LangSmith Engine: red teaming and automated testing
LangSmith Engine now includes Red Teaming to proactively detect agent issues and automated agent testing. Learn more about the Engine v2 release.
Kimi K3 on Snowflake Cortex AI
Kimi K3 is in private preview on Snowflake Cortex AI. Explore Moonshot AI's open-weight model for coding, research, and enterprise applications.
Running open-Jev in SQL on Databricks
Over the weekend, “System One” decision models such as Jev have launched, which are...
Deploy and manage coding agents at scale with the Unity Gateway CLI
In the last six months, GPT-6, Claude Opus 5.5, Gemini 3.8, and Grok 4.7 all shipped,...
Speaker-labeled transcription with WhisperX on SageMaker AI
The AWS WhisperX Deep Learning Container packages Whisper, wav2vec2 forced alignment, and speaker diarization into a GPU-ready image. Learn how to deploy it to Amazon SageMaker AI real-time and...
Build a multi-account AI agent with AgentCore Gateway and MCP
Build a multi-account architecture that keeps each team's data in its own AWS account while giving AI agents a unified way to query across them. A central platform account runs the agent using Amazon...
Aderant builds intelligent ticket triage with Amazon Nova
Learn how Aderant built an intelligent ticket triage system on Amazon Nova Lite through Amazon Bedrock, automating context gathering, classification, routing, and knowledge enrichment for its cloud...
Context engineering is already possible in your warehouse. Here's how to get started.
Analytics teams have always modeled data for BI. Context engineering models data for agents, starting with semantic search.
Trajectories now in LangSmith: A readable view of every agent session
Trajectories in LangSmith provide a conversational view of an agent session. Trajectories make trace data easy to navigate and speed up debugging for long-running agents.
Managed Deep Agents delivers a better user experience for agents in production
Managed Deep Agents is the simplest way to build, deploy, and run agents in production. The 0.8 release adds support for user-owned credentials, user-level memory, HTTP channels, file transfer in...
Introducing LangSmith Fine-Tuning
LangChain introduces LangSmith Fine-Tuning and SmithTune, a CLI built for post-training models. Train specialized models without building data pipelines by hand.
What a dbt project is worth to an agent | Blog | Fivetran
What happens when AI agents query the same dbt project? One experiment reveals how the Semantic Layer impacts accuracy, cost and conversational analytics.
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...