Part 2 ended with a debt: when I own the runtime, I have to implement trim, a facts block, tiered compress, and placement myself. Claude Code already does a version of that. A product I ship does not get it for free.

This is Part 3 of 6 in my Agentic Coding with Claude Code series. The working model I am keeping is simple: the model reasons, the harness decides what happens next.

Claude Code is one harness. The Agent SDK is that same loop as a library. The Messages API is the loop with the cover off: every response has a stop_reason, and your code chooses whether to run a tool, ask the user, route, escalate, or halt.

Later posts will cover MCP, evals, and guardrails. This one stays on the runtime around the model.

Read More

In Part 1, I treated Claude Code as a bounded loop: perceive, reason, act, then feed the evidence back in. The reasoning engine is only as good as the working set it sees. A precise goal still fails if the window is full of directory trees, stale chat, and a vague tool contract.

This is Part 2 of 6 in my Agentic Coding with Claude Code series. The working model I am keeping is simple: context is assembled, not typed, and it is a budget, not a bucket.

CLAUDE.md, path-scoped rules, skills, memory, tool results, and the conversation all compete for the same tokens. Unfiltered tool output is paid for on every later turn. The job is to load the right slice at the right time.

Later posts will cover the harness and Agent SDK, MCP, evals, and guardrails. This one stays on the context layer that shapes every decision in the loop.

Read More

Source: Cordis 在做什么：从 DeepSeek Harness 看 by Antinomie on antinomie.org. The piece is the site’s current homepage post.

DeepSeek Harness (DSH) is an agent harness built on Cordis. The first thing that clicks is not a privileged core loop. Model adapters, tool registries, session logs, and the agent loop itself are all plugins.

This is the first post in my DeepSeek Harness series. I am starting with a close reading of how DSH actually uses Cordis: services, inject, reversible ctx.effect registration, Loader, and the config layers that turn composition into data.

Read More

Claude Code is the interactive experience. The Claude Agent SDK is the programmable interface to the same agent loop, tools, and context management.

That distinction changes what we can build. Instead of opening a terminal and guiding one task by hand, we can place the agent inside a product, internal service, CI job, or document pipeline. Our application defines the goal and operational boundary. Claude decides which permitted actions to take, observes the results, and continues until the task is complete.

This is Part 2 of my Agentic Coding with Claude Code series. We will move from the concepts in Part 1 to the SDK primitives that make an agent work: query(), message streams, sessions, tools, and permissions.

Read More

Most people first meet Claude Code as a chatbot in a terminal. That mental model is too small.

Ask it to explain a bug and it may answer once. Give it a concrete engineering objective and permission to work, and it can read the repository, trace the code, edit files, run tests, inspect the result, and change course when the evidence contradicts its plan. That repeated cycle is what makes the workflow agentic.

This is Part 1 of 6 in my Agentic Coding with Claude Code series. The working model I am keeping is simple: Claude Code is a bounded loop of perceive, reason, act, and feedback, not a longer chatbot reply.

Later posts will cover context, the harness / Agent SDK / stop-reason loop, MCP, evals, and guardrails. This one stays on the loop, the components, and the patterns.

Read More

I learned agentic AI concepts in Python - agent loops, tool calling, multi-agent coordination, production patterns. I even built my own Python assistant - MiuBot - with 10 chat channels, Temporal workflows, and multi-tenant workspaces. Python works well for most of these cases. But while building MiuBot, I kept hitting the same question: what happens when you need to serve many users concurrently over WebSocket with streaming responses? That’s when I discovered GoClaw from the NextLevelBuilder team, and it changed how I think about the problem.

Read More

After months of studying agentic AI patterns in theory - agent loops, tool calling, multi-agent coordination - I wanted to build something real. Not another tutorial project, but an AI assistant I could actually use daily, connected to the chat platforms I already live on. That’s how MiuBot started - forked from Nanobot, then reshaped into something quite different.

Read More

Every company sitting on a data warehouse wants the same thing: let anyone ask questions in plain English and get reliable answers. OpenAI published how they built their internal data agent, and the open-source community responded fast. Here’s a quick summary of three projects pushing this forward.

Read More

This post brings together everything we’ve learned about applying agentic AI to financial services. From role-based prompting through multi-agent coordination, we’ve covered the complete spectrum of techniques for building intelligent financial systems. Here’s the comprehensive overview with production patterns.

Read More

When multiple agents operate simultaneously on trading operations, they must share a consistent understanding of the world state. This post explores the coordination patterns that make multi-agent trading systems reliable: persistent state management, conflict resolution, and multi-agent RAG for comprehensive analysis.

Read More