# Decoding ML Join for content on designing, building, and shipping AI software. Learn AI engineering, end-to-end, from idea to production. Every Tuesday. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Deploying Parallel Remote Coding Agents with Decode DevFeed: [Deploying Parallel Remote Coding Agents with Decode]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-09-10T05:02:03Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [AI-assisted coding](), [Command-line interface](), [Serverless](), [Python]() Tags: [cli](), [coding-agents](), [modal](), [parallel]() ### AI overview This tutorial explains how to deploy the Decode coding-agent harness as remote background jobs. It covers moving from a TUI to a headless CLI, running jobs on Modal, and supporting parallel sessions across multiple projects. ### Source excerpt Run the harness remotely on Modal, triggered by your CLI, a webhook, or a nightly cron. ## Using Six Scoped Subagents to Manage Context Windows DevFeed: [Using Six Scoped Subagents to Manage Context Windows]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-09-01T05:00:29Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [context window](), [long-context](), [Artificial Intelligence](), [Code](), [coding](), [Claude](), [Claude Code](), [codex](), [LangChain](), [Python](), [Cloud]() Tags: [agent](), [agents](), [ai](), [claude](), [claude-code](), [cloud](), [codex](), [coding](), [coding-agents](), [context-engineering](), [context-window](), [langchain](), [python]() ### AI overview This tutorial explains how splitting research work among six parallel subagents can reduce context-window noise and limit the state returned to an orchestrator agent. It also covers designing subagent protocols, maintaining an agent registry, and running parallel agent workflows. ### Source excerpt The harness determines what your orchestrator agent never sees, not the model. ## Context Engineering for Coding Agents DevFeed: [Context Engineering for Coding Agents]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-08-25T05:01:37Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [context window](), [AI-assisted coding](), [coding](), [Claude](), [codex]() Tags: [agents](), [claude](), [codex](), [coding-agents](), [context](), [context-engineering](), [context-window](), [harness]() ### AI overview This tutorial explains context engineering for coding agents, focusing on memory, skills, LSP servers, compaction, and feedback loops. It presents these techniques as ways to keep an agent's context high-signal and improve coding-agent performance. ### Source excerpt The 4 harness components that keep your context window high-signal. ## From a Raw Shell to a Sandboxed Coding Agent DevFeed: [From a Raw Shell to a Sandboxed Coding Agent]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-08-18T11:02:59Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [AI-assisted coding](), [LangChain](), [Claude Code](), [Docker](), [computer-use](), [codex](), [Python](), [Open Source](), [Cloud]() Tags: [agents](), [ai](), [ai-evals](), [anthropic](), [claude](), [claude-code](), [cloud](), [codex](), [coding](), [coding-agents](), [computer-use](), [docker](), [guide](), [open-source](), [python](), [terminal]() ### AI overview A tutorial on isolating coding-agent tools inside local Docker or remote Modal sandboxes. It explains how to build a Python harness that safely executes commands and supports remote, parallel agent workflows. ### Source excerpt The guide to isolating your harness and safely executing its commands, locally or remotely. ## 11 Context-Engineering Tips for Using Coding Agents Efficiently DevFeed: [11 Context-Engineering Tips for Using Coding Agents Efficiently]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-08-04T11:04:10Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [AI-assisted coding](), [Large Language Model](), [Documentation](), [anthropic](), [codex](), [Obsidian]() Tags: [2026](), [anthropic](), [codex](), [coding-agents](), [context-engineering](), [docs](), [tokens](), [weekly]() ### AI overview The author shares 11 context- and harness-engineering techniques for using coding agents while controlling token use. The advice includes progressive disclosure, detailed planning with cheaper models handling execution, LLM wikis for project context, and subagents that return summaries. ### Source excerpt Context engineering techniques to avoid wasting tokens on what doesn't matter ## The Bare-Bones Coding Agent Loop DevFeed: [The Bare-Bones Coding Agent Loop]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-07-28T13:54:35Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Agent Harness](), [AI-assisted coding](), [Python](), [Shell](), [Text-based user interface]() Tags: [agent](), [agent-harness](), [coding](), [coding-agents](), [interfaces](), [python]() ### AI overview A lesson in an open-source course that explains how to build a bare-bones coding agent loop in Python. It covers decomposing goals into plans, executing them with tools, building a terminal user interface, and avoiding message-handling problems in the loop. ### Source excerpt One agent loop, 9 tools, and a terminal you can steer. ## Building a Coding Agent From Scratch DevFeed: [Building a Coding Agent From Scratch]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-07-22T11:04:24Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Agent Harness](), [AI-assisted coding](), [coding](), [LangChain](), [Claude Code](), [codex]() Tags: [agent-harness](), [ai](), [ai-agents](), [ai-evals](), [benchmarks](), [claude-code](), [codex](), [coding-agents](), [langchain]() ### AI overview This tutorial explains how to build a coding-agent harness from scratch in Python. It covers the agent loop, shell execution, context engineering, subagents, remote parallel agents, and evaluation workflows, using the project Decode as the practical example. ### Source excerpt Designing the harness around the model, from the agent loop to a remote swarm. ## How to Build Unified Agent Memory from Scratch DevFeed: [How to Build Unified Agent Memory from Scratch]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-07-14T05:01:54Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [AI Engineering](), [Claude Code](), [Graphs](), [LangChain](), [Large Language Model](), [Database](), [Model Context Protocol]() Tags: [agent](), [ai-engineering](), [claude-code](), [graph](), [graph-database](), [knowledge-graphs](), [langchain](), [llm](), [mcp]() ### AI overview A tutorial on building a unified agent memory layer from scratch using knowledge graphs, including ingestion, querying, and serving. It discusses trade-offs among vector databases, graph databases, temporality, versioning, MCP servers, CLIs, and skills, and explains why understanding the underlying memory layer matters. ### Source excerpt Ingest, query, and serve a unified memory from a single database. ## Building an LLM Wiki as Persistent Memory for AI Agents DevFeed: [Building an LLM Wiki as Persistent Memory for AI Agents]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-07-07T05:01:21Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Wiki](), [Large Language Model](), [Artificial Intelligence](), [AI research agents]() Tags: [agent](), [agents](), [ai](), [ai-agents](), [article](), [claude-code](), [codex](), [context](), [google](), [llm](), [memory](), [notes]() ### AI overview This tutorial describes building an AI Research OS that turns notes and web research into a queryable, maintainable LLM wiki. The wiki is designed to provide persistent memory for AI agents used in research, coding, and content creation. ### Source excerpt Turn dead notes into a living LLM wiki your AI agents can query, maintain, and grow ## From Harness Lock-In to Portable Context Layer DevFeed: [From Harness Lock-In to Portable Context Layer]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-06-30T08:20:17Z Content type: article Language: en Sources: [Decoding ML]() Topics: [Artificial Intelligence](), [MCP Server](), [Graphs](), [AI search](), [Notion](), [Obsidian](), [Google]() Tags: [ai](), [claude-code](), [code](), [knowledge-graph](), [mcp](), [memory](), [open-source](), [vector-search]() ### AI overview The article argues that users should keep their context layer separate from any AI harness. It proposes unified memory combining a filesystem, BM25 keyword search, semantic vector search, and a typed knowledge graph, exposed through an MCP server or skills so different models and harnesses can use it. ### Source excerpt Build a unified memory (knowledge graph or an LLM wiki) and serve it over MCP servers or skills, so any agent, open or closed, plugs in within minutes. ## How Evaluation-Driven Development (EDD) Works DevFeed: [How Evaluation-Driven Development (EDD) Works]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-06-23T08:57:02Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Development](), [AI Agent](), [Ground truth / benchmark quality](), [dataset]() Tags: [agent](), [ai](), [ai-evals](), [case-study](), [development](), [evaluation](), [experiment](), [saas](), [test](), [tests]() ### AI overview This case study explains Evaluation-Driven Development (EDD) for AI agents: measure a new feature, compare results before and after changes, and detect regressions before merging. It also discusses generating realistic test data when historical datasets, traces, or ground truth are unavailable. ### Source excerpt Turn every AI agent change into a measured experiment you compare before and after to detect regressions and measure performance. ## Build, Configure, or Use As-Is: The Agentic Harness DevFeed: [Build, Configure, or Use As-Is: The Agentic Harness]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-06-09T05:00:28Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Tool](), [AI Engineering](), [codex](), [Claude Code](), [Pydantic](), [TypeScript]() Tags: [agentic](), [agents](), [ai](), [ai-engineering](), [architecture](), [article](), [building](), [memory](), [permission](), [sandbox](), [sandboxes](), [tools]() ### AI overview This article explains the shared system design of agentic harnesses, covering tools, agent catalogs, subagents, skills, memory, sandboxes, and permissions. It argues that these harness components are increasingly standardized, while the main differentiation lies in the context and business layers built on top. ### Source excerpt A component-by-component teardown of an agentic harness, from tools and skills to memory, sandbox, and permissions. ## How to Keep Your AI Agent's Knowledge Graph Clean DevFeed: [How to Keep Your AI Agent's Knowledge Graph Clean]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-06-02T05:00:53Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Entity resolution](), [Graphs](), [AI Agent](), [data](), [Large Language Model](), [Neo4j]() Tags: [agent](), [ai-agent](), [code](), [knowledge-graph](), [llm](), [pipeline](), [rag](), [review]() ### AI overview This tutorial explains how to keep an AI agent's knowledge graph clean by separating entity resolution for naming from deduplication for identity. It presents a pipeline covering LLM extraction, embeddings, deduplication, and safety reviews to reduce incorrect merges as the graph grows. ### Source excerpt The resolution, deduplication, and review pipeline that keeps agent memory usable as it grows. ## How to Start a Knowledge-Graph Memory Layer with an Extendable Ontology DevFeed: [How to Start a Knowledge-Graph Memory Layer with an Extendable Ontology]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-05-26T05:00:51Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Graphs](), [Retrieval Augmented Generation (RAG)](), [data]() Tags: [ai-engineering](), [article](), [how-to](), [knowledge-graph](), [knowledge-graphs](), [rag](), [schema-design]() ### AI overview This tutorial explains how to begin building a knowledge-graph memory layer without designing a complete ontology upfront. It recommends a small, generic, extendable POLE+O model with Preferences and Facts, then extending it as domain-specific data reveals gaps. ### Source excerpt Start with a fixed, generic base and extend only when your data demands it. ## Inside Neo4j's Agent Memory DevFeed: [Inside Neo4j's Agent Memory]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-05-19T08:55:51Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Neo4j](), [Graphs](), [Artificial Intelligence](), [Retrieval Augmented Generation (RAG)]() Tags: [agent](), [ai](), [graph](), [knowledge-graph](), [memory](), [rag](), [retrieval-augmented-generation-rag]() ### AI overview The article presents Neo4j knowledge graphs as a model for durable agent memory. It argues that file-based logs and vector indexes lack identity and relationship tracking, while a structured graph can connect entities, preferences, and facts across a growing knowledge base. ### Source excerpt The knowledge-graph patterns that turn one-shot conversations into compounding intelligence. ## Squid: A Six-Agent Claude Code Setup for Agentic Coding DevFeed: [Squid: A Six-Agent Claude Code Setup for Agentic Coding]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-05-12T11:04:20Z Content type: article Language: en Sources: [Decoding ML]() Topics: [agentic-coding](), [Claude Code](), [Vibe coding](), [TypeScript](), [Model Context Protocol (MCP)](), [Text-based user interface]() Tags: [agentic-coding](), [ai-engineering](), [claude-code](), [interface](), [model-context-protocol-mcp](), [tools](), [typescript](), [vibe-coding]() ### AI overview The article presents Squid, an opinionated six-agent Claude Code setup for shipping software features through a structured, end-to-end engineering lifecycle. It contrasts this agentic-coding workflow with vibe coding and describes its use of specialized agents, MCP, skills, slash commands, and a TypeScript harness. ### Source excerpt My Claude Code agentic coding setup that ships features end-to-end ## Building Agentic GraphRAG Systems DevFeed: [Building Agentic GraphRAG Systems]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-05-05T05:01:08Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [Retrieval Augmented Generation (RAG)](), [data-modeling](), [MCP Server](), [AI Agent](), [context window]() Tags: [ai-agent](), [context-window](), [data-modeling](), [knowledge-graphs](), [langchain](), [latency](), [mcp-server](), [mongodb](), [rag]() ### AI overview The article explains agentic GraphRAG as a data-modeling problem involving knowledge graphs, ontologies, append-only data models, extraction modes, and hybrid retrieval. It describes exposing the resulting unified memory layer through an MCP server for AI agents. ### Source excerpt From knowledge graphs and ontologies to a unified memory as an MCP server for your AI agent. ## Weave CLI: A Case Study in Shipping Retrieval-Augmented Generation Systems DevFeed: [Weave CLI: A Case Study in Shipping Retrieval-Augmented Generation Systems]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-04-29T11:04:33Z Content type: article Language: en Sources: [Decoding ML]() Topics: [Retrieval Augmented Generation (RAG)](), [Command-line interface](), [Databases](), [Open Source]() Tags: [case-study](), [cli](), [databases](), [open-source](), [rag](), [vector-database]() ### AI overview An interview with Michael Maximilien examines the practical difficulties of building and evaluating RAG systems, including vector-database selection, embedding models, chunking, ingestion failures, and unreliable comparisons. Maximilien describes Weave CLI, an open-source command-line tool that unifies 11 vector databases into one workflow. ### Source excerpt You iterate. You evaluate. Weave CLI unifies 11 vector databases into one workflow. ## Ralph Loops Use Fresh Context and External Verification to Improve AI Agent Workflows DevFeed: [Ralph Loops Use Fresh Context and External Verification to Improve AI Agent Workflows]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-04-23T11:02:54Z Content type: article Language: en Sources: [Decoding ML]() Topics: [Artificial Intelligence](), [AI Engineering]() Tags: [agent-orchestration](), [agents](), [ai](), [ai-agents](), [ai-engineering](), [loops]() ### AI overview The article argues that replacing complex multi-agent systems with a writer-and-reviewer loop can simplify AI workflows. Ralph loops reset the conversation on each iteration, reload the specification, use filesystem and git for memory, and rely on objective signals such as tests or linters for verification. ### Source excerpt How one simple loop beats multi-agent orchestration and context rot in production. ## Building a Deep Research Agent Over Private Notes, Highlights, and Transcripts DevFeed: [Building a Deep Research Agent Over Private Notes, Highlights, and Transcripts]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-04-21T08:00:51Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [AI Engineering](), [Claude Code](), [Obsidian](), [Command-line interface](), [Markdown]() Tags: [agent](), [claude-code](), [cli](), [markdown](), [obsidian]() ### AI overview The article describes a deep-research agent built as three Claude Code skills that query private notes, reading highlights, and research transcripts through command-line interfaces. It uses multi-round query expansion, gap analysis, deduplication, re-ranking, and a filesystem-based wiki output rather than a vector database or RAG pipeline. ### Source excerpt A deep research agent over my notes, highlights, and transcripts, grounded in years of curated thinking, not the public web.