The Future of AX: When Domain Experts Become Software Owners
From a Dentist’s AI Stack to the Reinvention of Enterprises and Private Equity
Section 02
AI & AX
Agents, RAG, enterprise transformation, and AI engineering.
↗
Multi-Agent Is Not Multiple Agents: Parent Runs, Fan-out, and Fan-in
Model child lifecycles, isolated state, and partial failure as one execution tree
From Retrieval Engineering to Task Engineering
What changes when retrieval becomes part of an end-to-end task?
LangGraph Is Not Architecture: Where the Runtime Actually Belongs
Separate graph state from application state to assign responsibility across workers, Redis, databases, and browsers
Let the Agent Speak While It Works: SSE, Generators, and Redis Streams
Safely stream snapshots and events over an HTTP connection with async generators
Why Our Agent Platform Got Off to a Rocky Start
From a convincing demo to a predictable production system
Can an Agent Tool Execute Exactly Once? Approval, Idempotency, and Retries
Linking user intent to side effects so a transfer tool does not run twice
State Is Not an Event: Designing Real-Time Agent UIs
Restore the screen from a snapshot, then keep its timeline complete with cursors
Do Agents Have to Be Graphs? Why I Am Removing LangGraph from My Default Stack
From prescribing every route to designing the environment and boundaries around an agent
Where Does Agent State Live? Redis, PostgreSQL, and Checkpoints
Durable records, hot projections, and resumable snapshots survive different failures
Why Is vLLM Slow?
Diagnosing bottlenecks with TTFT, TPOT, and KV cache
A Worker Is Not a Thread: Why Agent Execution Should Leave the API Server
Separate concurrency primitives from ownership of the execution lifecycle
What is vLLM tuning?
Serving LLMs when GPUs are scarce
Async, Threads, and Processes: What to Know Before Agent Workers
Waiting, blocking SDKs, and CPU-bound computation require different execution tools
Why Agent Systems Need Async: Making Waiting Time Useful
Turn time spent waiting on LLMs, databases, and search APIs into concurrency
Why Serve Open-Source LLMs with vLLM on Internal GPUs?
Deciding internal open-model serving for security, data control, cost, and performance
Agent Backend Architecture at a Glance: How APIs, Queues, Workers, State, and SSE Fit Together
Execution architecture boundaries — mental model, failure modes, optional deep dives
Agent Pattern Design: From Tool Use to Planning, Parallelism, HITL, and Reflection
Compose bounded control flows instead of building one giant autonomous loop