Skip to content
Effloow
~/articles · 111 PIECES

Articles, one at a time.

Every piece cites primary sources and adds something you can act on: a worked example, a tested command, a documented limitation. Drafts that only summarize what already exists stay unpublished.
AI INFRASTRUCTURE 2026-09-24 ·Effloow Editorial

Google A2A 1.0 in Production: An Interoperability Audit

We tested Google A2A 1.0 between local Python agents: discovery, task lifecycle, artifacts, auth, pre-1.0 agent card migration, and where adapters remain.
Read →
AI INFRASTRUCTURE 2026-09-23 ·Effloow Editorial

Langfuse vs Arize Phoenix Self-Hosted: Traces, Evals, and Ops Cost

We ran Langfuse and Arize Phoenix locally, sent synthetic LLM traces over OpenTelemetry, exercised evals, and measured the operational cost of self-hosting.
Read →
AI INFRASTRUCTURE 2026-09-22 ·Effloow Editorial

Pydantic AI in Production: Type-Safe Agents vs LangGraph Overhead

We ran Pydantic AI's structured outputs, dependency injection, retries, and tool calls, then compared it with LangGraph across a 160-scenario test matrix.
Read →
DEVELOPER TOOLS 2026-09-21 ·Effloow Editorial

DSPy GEPA vs Manual Prompts: Cost, Overfitting, and Model Upgrades

We benchmarked DSPy GEPA against manually engineered prompts, measuring held-out accuracy, optimization token cost, latency, and transfer to a newer model.
Read →
DEVOPS 2026-09-20 ·Effloow Editorial

Windmill vs Airflow: A Hands-On Production Review for AI Workflows

We deployed Windmill with Docker Compose, built a mixed-language data and AI workflow, tested worker isolation, and mapped trade-offs against Airflow.
Read →
DEVELOPER TOOLS 2026-09-19 ·Effloow Editorial

CodeRabbit vs Greptile: PR Review Catch Rate, Noise, and Cost

We tested CodeRabbit and Greptile on seeded bugs in TypeScript, Python, and Go pull requests: what each caught, where noise built up, and what seats cost.
Read →
AI INFRASTRUCTURE 2026-09-18 ·Effloow Editorial

FastMCP Streamable HTTP in Production: Auth, DNS Rebinding, Docker

We deployed FastMCP behind Docker and nginx with OAuth token introspection, then tested Streamable HTTP sessions, proxy headers, and DNS rebinding defenses.
Read →
AI INFRASTRUCTURE 2026-09-17 ·Effloow Editorial

SGLang RadixAttention vs vLLM on One H100: Throughput Reality Check

We benchmarked SGLang RadixAttention against vLLM prefix caching on one H100: shared prefixes, multi-turn chat, structured output, latency, and GPU cost.
Read →
AI INFRASTRUCTURE 2026-09-16 ·Effloow Editorial

Unsloth on One GPU: Llama 3.1 8B Throughput, VRAM, and Quality

We compared Unsloth with a standard Hugging Face TRL QLoRA pipeline on one RTX 4090: training time, VRAM, quality, dependency failures, and limits.
Read →
AI INFRASTRUCTURE 2026-09-15 ·Effloow Editorial

Pipecat vs LiveKit Agents: Voice Latency and Lock-In Benchmark

We benchmarked Pipecat, LiveKit Agents, and Pipecat over LiveKit with synthetic calls and identical voice providers: where latency spikes and what breaks.
Read →
COST OPTIMIZATION 2026-09-14 ·Effloow Editorial

E2B Sandbox in Production: Cold Starts, Costs, and Pause/Resume

We tested E2B sandbox lifecycle under multi-turn agent workloads: cold starts, per-second costs, auto-pause, resume failures, and parallel creation storms.
Read →
AI INFRASTRUCTURE 2026-09-13 ·Effloow Editorial

Docling in Production RAG: Where PDF Chunking and Tables Break

We tested Docling 2.92.0 on digital and scanned PDFs for table fidelity, chunk quality, memory pressure, and serialization failures in a RAG pipeline.
Read →

Weekly field notes.

One short dispatch with new guides, tools, and what we tested that week.

Get weekly AI tool reviews & automation tips

Join our newsletter. No spam, unsubscribe anytime.