Topics / Knowledge hub
Reliability, quality, cost, and failure modes in AI systems.
Foundation
Compose bounded control flows instead of building one giant autonomous loop
A plain-Python guide to tool use, parallel orchestration, planning, HITL, retry, and reflection—and to the boundary between LLM judgment and deterministic code.
Read article ↗Deciding internal open-model serving for security, data control, cost, and performance
When internal GPU serving and vLLM make sense: compare external APIs, adoption trade-offs, batching and prefix caching in plain terms, and a pre-flight checklist.
Read article ↗Research
What changes when retrieval becomes part of an end-to-end task?
AI engineering is moving from optimizing retrieval pipelines to specifying, constraining, and evaluating end-to-end enterprise tasks.
Read article ↗General-purpose AI is a Swiss Army knife; enterprise AX is a purpose-built blade. A Market Intelligence case shows why transformation means redesigning work, not automating it.
Read article ↗Implementation
Diagnosing bottlenecks with TTFT, TPOT, and KV cache
A practical guide to diagnosing vLLM serving bottlenecks by reading TTFT, TPOT, queue, prefill, KV-cache, and preemption signals together.
Read article ↗Serving LLMs when GPUs are scarce
A practical guide to serving LLMs on limited on-premises GPUs: diagnose prefill, decode, KV cache, queues, and tail latency to tune vLLM for sustainable throughput.
Read article ↗Perspective
From a Dentist’s AI Stack to the Reinvention of Enterprises and Private Equity
If AI changes the economics of software and technical debt, how might domain expertise, organizational design, mid-market firms, and private-equity value creation change with it?
Read article ↗From a convincing demo to a predictable production system
Our agent platform worked in demos but stumbled in production. A retrospective on predictability, trust debt, and earning abstractions through deployment.
Read article ↗