Topic
All digests tagged MLOps
Suggested route
Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.
Optiver details how its on-prem AI platform handles the immediate, high-stakes P&L feedback loop of trading. Learn about the Inference Gateway, Meta Harness, and Agent Swarm architecture.
Read article
Fuad Ali details the self-improvement loop for AI agents: trace failures, use Signal to detect issues, create living regression datasets, and run experiments to prove fixes. This automates reliability.
Read article
The future of agentic AI requires moving beyond model weights to optimizing the entire system. Speakers discuss advanced RL techniques, modular architecture, and the critical role of vetted environments in achieving reliable, scalable outcomes.
Read article
The future of AI agents requires 'babysitters.' We discuss moving from simple API calls to auditable, intent-based workflows using Jev and WebMCP, and how to verify business outcomes with tools like Cucumber.
Read article
Learn how to integrate AI agents into regulated, policy-driven workflows. We model processes using DAGs and DCGs, establishing trust through Evals and Traces.
Read article
CoreWeave Forge unifies the AI loop (Run, Observe, Curate, Improve, Evaluate) into one connected environment. The keynote detailed how to move AI agents from demo to production, featuring the NVIDIA Vera Rubin NVL72 and advanced evaluation techniques.
Read article
The future of AI engineering involves building robust, governed agent frameworks. Key architectural components include a centralized data vault, a five-layer agent lifecycle, and continuous evaluation loops to manage non-deterministic behavior.
Read article
CoreWeave announced CoreWeave Forge, a unified platform for the entire AI loop (Run, observe, curate, improve, evaluate). Key launches include Vera Rubin NVL72 and tools like Agent Lens and Model Distillation, streamlining LLMOps.
Read article
The reading group explores agent policy compliance, noting that LLMs struggle to follow complex SOPs. Solutions involve implementing deterministic and model-based guards outside the LLM to ensure reliable policy adherence.
Read article
The future of AI agents lies in specialization. We must move from 'god models' to thousands of hyper-scoped, domain-specific agents, requiring standardized runtimes and a microservices mindset.
Read article
Learn how to optimize AI compute capacity, control costs, and scale economically using CoreWeave's advanced capacity plans, Spot Instances, and the Mission Control platform.
Read article
Pinterest details its massive ML platform migration from MLflow to Weights & Biases. Learn about achieving system parity, zero downtime, and implementing governance guardrails at scale.
Read article
LangSmith Engine v2 automates agent development, offering validated fixes, red teaming, and cross-trace analysis to improve AI agents before production.
Read article
AI struggles with production because it spans code, infrastructure, and telemetry. To fix this, a robust agentic harness requires six pillars: Model Orchestration, Causal Reasoning, Context Engineering, and more.
Read article
Marc Klingen details the self-improving OSS agent stack, showing how AI can automate the loop between online tracing, offline datasets, and evaluations, moving teams from manual to automated agent refinement.
Read article
CoreWeave unveiled Forge, a unified platform for the AI Loop (Run, Observe, Curate, Improve, Evaluate). New hardware like the Vera Rubin NVL72 and Vera CPU accelerate the deployment of complex, agentic AI systems from concept to production.
Read article
This workshop details how to master AI Observability by building a continuous agent improvement flywheel. Using Braintrust, engineers can derive signal from production traces via custom scoring and Topics, automating the process of identifying failures and proposing code changes.
Read article
The talk details the shift from manual trace review to automated, continuous improvement loops for AI agents. By introducing 'Signal,' the system detects patterns in evaluation failures and automatically suggests fixes, closing the software development loop.
Read article
LangChain outlines the shift to 'owning your intelligence' by building domain-specific agents. The platform provides Managed Deep Agents, Jev decision models, and LangSmith Engine v2 for robust governance and production readiness.
Read article
Bogdan Gaza details the engineering lessons from generating 12 trillion synthetic tokens. He covers scaling from Slurm to a unified Ray/KubeRay/vLLM pipeline on EKS, solving bottlenecks like S3 metadata fetching and cross-cluster scheduling.
Read article