Blog | Sentient Arc

Field Notes

Practical explainers on agents, RAG, and automation, written for the people who have to ship and operate these systems.

2026-07-107 min read

How to Turn Obsidian Into an AI Second Brain With a Claude Code Skill

An Obsidian vault is just a folder of markdown files, so a Claude Code skill can capture, file, link, and distill your notes for you. Here is how to turn Obsidian into an AI second brain, and where to keep a human in the loop.

Read

2026-07-046 min read

Claude Managed Agents, Explained for Operators

Claude Managed Agents is Anthropic's hosted platform for running AI agents: you define the agent, Anthropic runs the loop and the sandbox its tools execute in. Here is how it works and when to reach for it.

Read

2026-07-046 min read

What Is Claude Design? Anthropic's AI Design Tool, Explained

Claude Design is Anthropic's tool for creating designs, prototypes, and slides by describing them to Claude. It reads your codebase for a design system and hands off to Claude Code. Here is how it works.

Read

2026-07-046 min read

What Is Google Stitch? Google's AI UI Design Tool, Explained

Google Stitch is a free Google Labs tool that turns a text prompt or an image into a UI design and front-end code, then pastes into Figma. Here is what it does well, where it falls short, and when to use it.

Read

2026-07-047 min read

Claude Design vs. Google Stitch vs. Figma: How We Choose

Claude Design, Google Stitch, and Figma are three different bets on AI-era product design: prompt-first and code-native, free and fast, or the collaborative canvas. Here is how a studio actually chooses between them.

Read

2026-06-297 min read

n8n vs Zapier vs Make for AI Agents: How to Choose (2026)

n8n vs Zapier vs Make for AI agents: there is no winner. n8n self-hosts, Zapier is broadest no-code, Make is the visual canvas. How to choose by workload.

Read

2026-06-286 min read

Make.com AI Agents in 2026: Scenarios, ChatGPT & Claude

Yes, Make.com runs AI agents on a visual scenario canvas with ChatGPT and Claude. How agents differ from scenarios, the credit billing, and where it breaks.

Read

2026-06-276 min read

Zapier AI Agents & ChatGPT: Build One With No Code (2026)

Yes, Zapier runs no-code AI agents and connects ChatGPT and Claude across ~8,000 apps. How AI by Zapier, Agents, and MCP work, the billing, and the limits.

Read

2026-06-266 min read

n8n AI Agents in 2026: Build, Self-Host & Pricing Explained

Yes, n8n builds AI agents with its LangChain AI Agent node, free self-hosted or metered on Cloud. How it works, the costs, and when to pick it over Zapier.

Read

2026-06-257 min read

OpenClaw vs. Hermes Agent: How We Choose

OpenClaw and Hermes Agent are the two dominant local-first, open AI agent frameworks of 2026: one bets on ubiquitous presence, the other on compounding intelligence. Here is how a studio actually chooses between them.

Read

2026-06-246 min read

Hermes Agent, Explained for Operators

Hermes Agent is Nous Research's open, local-first agent framework built around a self-improving loop: the agent writes and refines its own reusable skills as it works. Here is what that means for a studio building for clients.

Read

2026-06-236 min read

What Is OpenClaw? The Local-First AI Agent, Explained

OpenClaw is a free, open-source, local-first AI agent that runs on your own hardware, connects to the model of your choice, and lives inside the messaging apps you already use. Here is what it is, how it works, and what we harden before shipping it.

Read

2026-06-096 min read

AI Automation vs. Traditional Automation

Traditional automation follows fixed rules; AI automation handles the judgment-heavy steps in between. Knowing where each fits is the difference between a system that scales and one that breaks.

Read

2026-05-285 min read

RAG, Explained for Operators

Retrieval-augmented generation grounds a language model in your own documents, so it answers from your sources with citations instead of hallucinating. Here is how it works and when to use it.

Read

2026-05-126 min read

What Is Agentic Development? A Field Guide for Operators

Agentic development builds software where an AI agent decides the next step: retrieving context, reasoning, calling tools, and checking its own work. Here is what that means in practice.

Read

Have a project in mind?

Start a ConversationExplore Capabilities