Learning Machine: Hands-on Insights on Agentic Coding, Codex, and Multi-Agent Systems

LinkCoreyResource

Corey's blog 'Learning Machine' shares practical experiments, configuration tips, and conference notes focusing on AI agents, Codex CLI, Claude Code, and engineering workflows.

Key points

  1. Codex CLI sandbox management: Allowing agents to commit by modifying .git access in workspace-write, alongside notes on Codex 0.144.4 deprecating local model_context_window overrides for GPT-5.4.
  2. Practical agentic coding: Resolving a Rust memory leak in the Handy speech-to-text app using Claude Code without prior Rust knowledge.
  3. Output formats for agents: Examining Thariq Shihipar's argument regarding HTML output efficiency over Markdown in Claude Code workflows.
  4. Conference takeaways from AI Engineer Europe: Insights on multi-agent failure points from Databricks and shortcomings in LLM evaluators from Agenta AI.

Why it matters

The blog documents grounded, real-world development experiences with modern AI agent tools, highlighting actual failure modes, sandbox restrictions, and tooling decisions.

Analysis

Corey's posts focus on direct problem-solving and actionable technical nuances. By covering specific error responses, breaking configuration changes across tool versions, and engineering lessons from industry talks, the blog serves as a useful reference for developers implementing autonomous agent workflows.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:EveryInc/compound-engineering-plugin

    Compound Engineering: 33-Skill Plugin for AI Coding Agents

    Compound Engineering is an open-source plugin for AI coding agents designed to structure development workflows and systematically preserve learned context. It runs on 14 platforms, including Claude Code, Cursor, and Codex.

    24.9kstarsTypeScript

    AI & LLMs· Tool

  • Link:IndyDevDan

    Tactical Agentic Coding: Moving Beyond In-the-Loop AI Assistance

    Tactical Agentic Coding (TAC), created by IndyDevDan, is a training framework focused on advancing from basic interactive AI coding to fully autonomous agentic engineering. Rather than remaining 'in the loop' via conversational prompting, software engineers are trained to combine deterministic code with non-deterministic agents like Claude Code to orchestrate self-correcting development pipelines.

    AI & LLMs· Resource

  • Repository:openai/codex

    OpenAI Codex CLI: Local Terminal Coding Agent Built in Rust

    Codex CLI is an open-source, lightweight coding agent developed by OpenAI that runs locally in your terminal. Written in Rust, it connects directly to ChatGPT plans or standard API keys.

    121.7kstarsRust

    AI & LLMs· Tool

  • X post:Luna Tech

    OpenAI Workshop: Building Agentic Systems with Codex

    Luna Tech highlights a one-hour OpenAI workshop demonstrating how to build agentic systems with Codex from scratch, covering subagents, prompt patterns, persistent goals, and automated loops.

    4kbookmarks151.7kviews

    AI & LLMs· Resource

  • Article:Anthropic

    Effective Context Engineering for AI Agents: Managing the Attention Budget

    Anthropic details the shift from prompt engineering to holistic context engineering for autonomous AI agents. Because language models operate within finite attention budgets dictated by transformer architectures, developers must carefully curate tokens and adopt just-in-time retrieval strategies.

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.