Oregon Engineering Teams Choose Vertex for Claude Sonnet 4.6
Infrastructure-level look at Claude Vertex Oregon, including Pacific Northwest cloud, deployment topology, region availability, and cost considerations.
8 min read
Agentic AI & LLMs
Agentic AI & LLMs archive page 171 of 631
Agentic AI & LLMs
Agentic AI, LLM engineering, and the models behind modern automation — multi-agent systems, LLM evaluation and comparisons, RAG, fine-tuning, AI infrastructure, security, and production AI engineering.
From the blog
Latest articles
The Claude Memory Tool: Persistent Context Across Sessions
An agentic-AI perspective on Claude memory tool, covering orchestration patterns, tool use, and how agent memory fits production agent stacks.
6 min read
Claude Sonnet 4.6 Workloads on AWS Bedrock from Seattle
Infrastructure-level look at Claude Sonnet 4.6 Bedrock, including AWS AI, deployment topology, region availability, and cost considerations.
9 min read
Braintrust Evals Platform 2026 Deep Dive: A Practical Review
Braintrust positioned itself as the eval platform for serious AI teams in 2026. Datasets, scorers, and CI integrations in practice with concrete pricing and trade-offs.
10 min read
Burr: A State-Machine Framework for Agents Worth a Serious Look
Burr from DAGWorks treats agents as explicit state machines. The trade-offs against LangGraph and where Burr fits a regulated workload that needs strict control flow.
9 min read
CrewAI for E-Commerce Merchandising Agents: A Real DTC Build
A Miami DTC brand uses CrewAI Studio to run a daily merchandising agent crew that updates collections, hero copy, and email sends — and the lift it produced.
9 min read
Forgetting Curves and Decay in Agent Memory: Four Strategies
Real human memory decays continuously over time. Why your agent should too — and the four decay strategies that keep recall accurate without exploding storage cost.
9 min read
AWS Bedrock + Transcribe + Polly Stitched vs Realtime: Real Cost
Bedrock Claude + Transcribe streaming + Polly Neural runs $0.06–$0.10 per minute on paper. The honest math reveals where the AWS-native stack beats and where it loses to OpenAI Realtime.
11 min read
Database Backup and Recovery for AI Agent State: Postgres + pgvector
Your agent's memory, embeddings, and conversation state all live in Postgres. Backups must include vector data and survive a full-region loss. Here's how CallSphere does PITR for 115+ tables.
11 min read