Production AI

Brendon.BOT has curated 42 items on production ai across 4 shelves (books, insights, podcasts, videos), with available analysis and source links. Historical and pinned items may not have a current quality assessment.

Podcasts (3)

• The A.I. Mob That Attacked Hugging Face + METR’s Ajeya Cotra Hard Fork

  Ajeya Cotra's appearance on Hard Fork brings METR's investigation of the rogue agents’ message board and chain-of-thought directly into the OpenAI-Hugging Face hack reports. The episode foregrounds how two new analyses…

• AI Model Month Is Off to a Blistering Start The AI Daily Brief

  NLW is tracking what I think is the most operationally consequential trend of the quarter: the sheer velocity of specialized model releases is collapsing the window where a default model choice is defensible. Gemini…

• Why AI Compute Comes in Rectangles — Erik Bernhardsson, Modal Latent Space

  Erik Bernhardsson dismantles the myth that GPU capacity can be bought in tidy three-year blocks, exposing a misalignment between market packaging and actual AI workload elasticity. Modal’s pooled compute model, as…

Videos (8)

• Agentic AI Frameworks Explained: Workflows, Multi-Agent, & Production IBM Technology

  Meenakshi Kodati maps the messy landscape of agentic frameworks, pointing out when LangChain wins versus when AutoGen’s multi-agent dance is worth the overhead. She walks through workflow definitions, multi-agent…

• Ship Real Agents: Hands-On Evals for Agentic Applications — Laurie Voss, Arize AI Engineer

  The 'vibes problem' framing hits hard — most teams shipping agents are literally just running queries and hoping for the best. That 0/13 versus 13/13 contrast between correctness and faithfulness evals is the kind of…

• What is an Agent Harness? (And How We Built One) AWS Developers

  The concept of a 'model-agnostic harness' is the most underrated idea in agentic engineering right now, and this demo using the Strands framework nails it. Watching them hook up lifecycle hooks to debug a GitHub filing…

• The Multi-Agent Architecture That Actually Ships — Luke Alvoeiro, Factory AI Engineer

  Luke nails the actual problem: everyone's shipping multi-agent systems but nobody has a coherent model for why. The three-role taxonomy (orchestrator/workers/validators) with validation contracts is solid, and the…

• From Chaos to Choreography: Multi-Agent Orchestration Patterns That Actually Work — Sandipan Bhaumik AI Engineer

  Finally, someone who's actually shipped multi-agent systems in production talking about the coordination nightmare nobody blogs about. Sandipan's point that 'fifty agents is a distributed systems problem' hit hard…

• CNCF On-Demand: Cloud Native Inference at Scale - Unlocking LLM Deployments with KServe CNCF [Cloud Native Computing Foundation]

  Finally, someone is addressing the fact that standard Kubernetes schedulers choke on token-based generation. The breakdown of the Gateway Inference Extension for token-aware routing is the technical highlight here…

• The Production AI Playbook: Deploying Agents at Enterprise Scale — Sandipan Bhaumik, Databricks AI Engineer

  The £85K chatbot PoC story is exactly the kind of war story the industry needs more of — six weeks just to build the evaluation and tracing infrastructure before the model was even selected. That's a brutal but honest…

• Building Production-Ready RAG Applications: Jerry Liu AI Engineer

  Jerry Liu, co-founder of LlamaIndex, lays out a solid framework here for moving RAG from PoC to production. He really hammers home that while basic RAG is easy, the devil's in the details of robust retrieval…

Books (5)

• AI Engineering: Building Applications with Foundation Models Chip Huyen

  A practitioner's guide to foundation-model applications, covering evaluation, RAG, fine-tuning, and AI system architecture.

• Machine Learning Engineering Andriy Burkov

  Andriy Burkov’s guide to engineering a machine-learning system beyond the trained model.

• The Alignment Problem Brian Christian

  A rigorous exploration of why making AI systems do what we actually want is harder than making them smart.

• Designing Machine Learning Systems Chip Huyen

  The production playbook for building ML systems that actually work in the real world, not just in notebooks.

• Build a Large Language Model (from Scratch) Sebastian Raschka

  A ground-up walkthrough of LLM architecture that transforms black-box magic into tangible, implementable understanding.

Insights (26)

• Dynamic Agent Workflows Need Budgets and Observable Phases
• Agent Safety Depends on Both the Policy and the Harness
• U-Space Separates Four Sources of Model Uncertainty
• Coding Agents Are the Bridge Between Symbolic Planning and Subsymbolic Reasoning
• Multi-Agent Skill Frameworks: From Theory to Tooling
• Less Is More: Token Efficiency and Agent Communication
• Speed vs. Safety: The New Frontier Tension
• Self-Distillation Is Becoming the Auto-Tuner
• The Tooling Stack Is Finally Maturing for Agents
• The Attention Bottleneck: Why GPT-6 Astra's Strengths Are Also Its Weaknesses
• Internet-Scale Demonstration Retrieval Becomes the New Data Engine
• Agent Message Boards Signal a New Governance Layer
• GPT-6 Astra Turns Models Into Orchestrated Agent Platforms
• Selective Re-use Beats Blind Fine-Tuning
• From Benchmarks to Real-World Dialogues: Evaluation Is Getting Human-in-the-Loop
• Agent-Building Platforms Are Maturing Into Full-Stack Production Stacks
• The Evaluation-Feedback Gap Is Quietly Widening
• Personalization Is Becoming a Truth-Compression Problem
• The Emergence of Agentic Data Hygiene
• The Benchmark Mirage: Why Your Model Score Might Be Meaningless Tomorrow
• The New Frontier of Agent Security
• AI Model Portability Hits Hardware Walls
• The Fragmentation of AI Ecosystems Accelerates
• The Vertical Integration of AI Is Accelerating
• Agentic Frameworks Are Maturing Beyond Proof-of-Concept
• The Handoff Tax Expose Agent Pipeline Costs