Managing AI Workflows in SDLC: A 2026 Guide
Managing ai workflows in sdlc: Learn how to manage AI workflows across your software development lifecycle.
Read →Macleod Labs
Field Notes
Explorations in AI and Technology
AI Agent Observability for Managers: 2026 Guide
AI agent observability for managers: track performance, control costs, and keep agents audit-ready. Learn the frameworks that matter. Get started.
Read →
The Agentic SDLC: What Actually Changes When Agents Plan, Review, Test, and Operate Your Software
How autonomous coding agents are rewiring the software development lifecycle — and the primary-source evidence on where they help, where they hurt, and what you must keep human.
Read →
The Agentic SDLC: When Execution Gets Cheap, Verification Becomes the Job
How autonomous coding agents reshape planning, review, testing, and ops — and why the hard part of shipping them is governing what they produce, not generating it.
Read →
Project Fetch: A Model Programmed a Robodog 20x Faster Than Humans — and Still Couldn't Fetch
Anthropic's Project Fetch Phase Two shows Claude Opus 4.7 crushing the software side of robotics autonomously, while precise physical control remains stubbornly unsolved.
Read →
Loops All the Way Down: How Coding Agents Actually Run, and Where They Break
A primary-source deep dive into the agent execution loop — plan/act/observe/repeat, stop conditions, context management, verification, sub-agents, and the failure modes (doom loops, reward hacking, context rot) you must engineer against to ship agentic AI.
Read →
Dynamic Workflows: When Your Agent Writes Its Own Orchestrator
Agentic AI just learned to delegate at scale—and the architecture is simpler than you'd think.
Read →
Returns to Expertise: What 400K Claude Code Sessions Say About Shipping Agentic AI
Anthropic's new economic study argues coding agents amplify domain expertise rather than replace it — here's what's real, what's contested, and what it changes about production agent design.
Read →
Multi-Model Fusion Systems Challenge the Frontier Pareto Curve
Frontier models may not own all the best points on the cost-accuracy Pareto curve—and they may not be on the curve at all.
Read →
Model Neutrality as Offensive Strategy: Why Agent Harnesses Are the New Lock-In Layer
AI vendor lock-in just became more dangerous than cloud lock-in ever was—and the solution isn't what you'd expect.
Read →
Post-Trained Evaluators: How to Monitor Production Agents Without Burning Your Budget
Production agent monitoring has a brutal cost-accuracy trade-off. Frontier models (Claude, GPT) give you high-quality judgments but burn money at scale. Rule-based evals are cheap but brittle. Human review doesn't scale past hundreds of traces per day.
Read →
Parallel Subagent Orchestration: From Monolithic Agents to Coordinated Workflows
Agentic AI is moving from monolithic loops to orchestrated multi-agent systems, and the shift is visible in production tooling.
Read →