Timestral Tested: How Much Data AI Demand Forecasting Needs
AI demand forecasting with Mistral's Timestral, tested on retail and GB grid data: how much history it needs, and when a model of how demand works wins.
Dr. Phil Winder
/
12 minThe Winder.AI Blog
Field notes on applied AI
Field notes on applied AI from the Winder.AI team. Practical writing on building production AI, drawn from our consulting and research work.
Every cover is one plate of a single engraving. Scroll the whole mural.
Latest articles
Page 1 of 22
Dr. Phil Winder
/
12 min
Harness Engineering: What We Learnt Building AI Agents
Harness engineering is choosing how much of an AI agent's loop to make deterministic. What we learnt doing it on three of our own agents, and where to start.
Dr. Phil Winder
/
13 min
Copilot Studio vs Azure AI Foundry vs Build: What One Document Costs
Copilot Studio vs Azure AI Foundry vs building your own, costed on one real 236-page report: $725 a document against $37, and where the line falls.
Dr. Phil Winder
/
17 min
vLLM vs Ollama vs SGLang: LLM Inference Compared 2026
vLLM vs Ollama vs SGLang on one H100 with Qwen3.8-27B and Llama 3.1 8B: throughput, latency and cost per million tokens, harness included.
Dr. Phil Winder
/
11 min
How to Build an Automated Pricing Algorithm
How to build an automated pricing algorithm: why fitting a demand curve fails, and a step-by-step build in an open-source simulator, up to RL.
Dr. Phil Winder
/
15 min
DeepSeek Harness vs OpenCode: Which One We Run in 2026
DeepSeek Harness vs OpenCode 2.0, compared from running both in our own fleet: architecture, model support, cost, containment and which one suits a team.
Dr. Phil Winder
/
13 min
A Comparison of AI Agent Harnesses in 2026
A comparison of AI agent harnesses in 2026: Claude Code, Codex, OpenCode, Qwen Code, DeepSeek Harness, Goose and Zed Agent, plus when you need a framework.
Dr. Phil Winder
/
17 min
AI Agent Evaluation: How to Test an Agent Before You Ship It
AI agent evaluation without a vendor selling the answer: which metrics to measure at each layer, how to build an eval suite that runs in CI, and when a platform is worth buying.
Dr. Phil Winder
/
18 min
Why AI Agents Fail in Production, and the Observability That Catches It
The five ways AI agents fail in production, and the AI agent observability and monitoring that catches them: tracing, retries, cost ceilings and approval gates.
Dr. Phil Winder
/
21 minNewsletter
AI engineering insights, in your inbox
Case studies and industry analysis from our team. No hype, roughly monthly.