https://getagenttools.com/blog/ Field notes from running AI agents on real business workflows. en Fri, 23 Oct 2026 14:07:48 GMT https://getagenttools.com/blog/opencode-dangerously-skip-permissions/ https://getagenttools.com/blog/opencode-dangerously-skip-permissions/ Fri, 23 Oct 2026 00:00:00 GMT opencode accepts --dangerously-skip-permissions as a hidden alias for --auto. What it approves, what deny rules still block, and the permission config in opencode.json. https://getagenttools.com/blog/codex-dangerously-skip-permissions/ https://getagenttools.com/blog/codex-dangerously-skip-permissions/ Tue, 20 Oct 2026 00:00:00 GMT Codex has no --dangerously-skip-permissions. Use --dangerously-bypass-approvals-and-sandbox, or -a never with a sandbox. Plus approval_policy, sandbox_mode and --approve-for-me. https://getagenttools.com/blog/ga4-consent-mode/ https://getagenttools.com/blog/ga4-consent-mode/ Sat, 17 Oct 2026 00:00:00 GMT GA4 consent mode explained: basic vs advanced, what each sends before the click, and a store where Search Console counted clicks on days GA4 counted nothing. https://getagenttools.com/blog/rag-vs-fine-tuning/ https://getagenttools.com/blog/rag-vs-fine-tuning/ Sun, 11 Oct 2026 00:00:00 GMT Choose RAG or fine-tuning by the failure you need to fix: missing facts, inconsistent behavior, or both. Includes a decision worksheet and a local retrieval fixture. https://getagenttools.com/blog/n8n-error-handling/ https://getagenttools.com/blog/n8n-error-handling/ Sat, 10 Oct 2026 00:00:00 GMT Use n8n error workflows, node error outputs and bounded retries. A local receipt model shows why a timeout can repeat an action that already succeeded. https://getagenttools.com/blog/claude-code-sandbox/ https://getagenttools.com/blog/claude-code-sandbox/ Fri, 09 Oct 2026 00:00:00 GMT Configure the Claude Code sandbox, probe file and network restrictions, and check retries, excluded commands and tools that run outside its boundary. https://getagenttools.com/blog/claude-code-channels/ https://getagenttools.com/blog/claude-code-channels/ Thu, 08 Oct 2026 00:00:00 GMT Understand Claude Code Channels, sender allowlists, session lifetime and permission relay. Use a local test plan before connecting an external chat platform. https://getagenttools.com/blog/ai-agent-cost/ https://getagenttools.com/blog/ai-agent-cost/ Wed, 07 Oct 2026 00:00:00 GMT Calculate AI agent cost with tokens, tools, retries, failed tasks and operator time. A synthetic ledger shows what cost per successful task includes. https://getagenttools.com/blog/claude-code-checkpoints/ https://getagenttools.com/blog/claude-code-checkpoints/ Tue, 06 Oct 2026 00:00:00 GMT Choose code, conversation or both in Claude Code rewind, check shell and subagent limits, and keep Git and external recovery separate from checkpoints. https://getagenttools.com/blog/claude-code-worktrees/ https://getagenttools.com/blog/claude-code-worktrees/ Mon, 05 Oct 2026 00:00:00 GMT Use Claude Code worktrees for parallel tasks, choose the right base, handle dependencies, review each branch, merge changes and clean up safely. https://getagenttools.com/blog/claude-code-plugins/ https://getagenttools.com/blog/claude-code-plugins/ Sun, 04 Oct 2026 00:00:00 GMT Choose a Claude Code plugin scope, inspect its components and context cost, diagnose loading, then update, disable or remove the correct installation. https://getagenttools.com/blog/codex-skills/ https://getagenttools.com/blog/codex-skills/ Sat, 03 Oct 2026 00:00:00 GMT Build a small Codex skill with SKILL.md, choose its local scope, check discovery, and test explicit invocation without assuming tool access. https://getagenttools.com/blog/gpt-6-1-sol-dots-codex-plans/ https://getagenttools.com/blog/gpt-6-1-sol-dots-codex-plans/ Tue, 29 Sep 2026 00:00:00 GMT GPT-6.1 Sol is here. Check dots access, ChatGPT Pro prices, Codex usage limits and the difference between faster modes and billing multipliers. https://getagenttools.com/blog/claude-sonnet-5-5/ https://getagenttools.com/blog/claude-sonnet-5-5/ Mon, 28 Sep 2026 00:00:00 GMT Claude Sonnet 5.5 keeps Sonnet 5 token prices. Check speed claims, API changes, and progress updates your agent interface could stop showing after migration. https://getagenttools.com/blog/own-your-intelligence/ https://getagenttools.com/blog/own-your-intelligence/ Fri, 25 Sep 2026 00:00:00 GMT Harrison Chase's own-your-intelligence framework, checked question by question against my own AI agent stack, with honest yes, no, and partial answers. https://getagenttools.com/blog/ai-code-review-agents/ https://getagenttools.com/blog/ai-code-review-agents/ Thu, 24 Sep 2026 00:00:00 GMT How to use AI agents for code review without losing control: specialized reviewer agents, a CI loop, fail-closed auto-merge gates, and verifying real behavior. https://getagenttools.com/blog/prompt-caching-explained/ https://getagenttools.com/blog/prompt-caching-explained/ Wed, 23 Sep 2026 00:00:00 GMT How prompt caching actually works under the hood, what is worth caching, when it does nothing for your bill, and the one-line check I run before turning it on. https://getagenttools.com/blog/ai-technical-debt/ https://getagenttools.com/blog/ai-technical-debt/ Tue, 22 Sep 2026 00:00:00 GMT AI technical debt breaks into four types: data, model, prompt, and organizational. Here's what each looks like in practice, plus a self-audit checklist. https://getagenttools.com/blog/opus-5-5-gpt-6-sol-luna/ https://getagenttools.com/blog/opus-5-5-gpt-6-sol-luna/ Tue, 22 Sep 2026 00:00:00 GMT Opus 5.5, GPT-6 Sol and Luna launched September 22, 2026. Compare API IDs, token prices, Work and Codex availability, and migration checks for agent builders. https://getagenttools.com/blog/smart-zone-dumb-zone/ https://getagenttools.com/blog/smart-zone-dumb-zone/ Mon, 21 Sep 2026 00:00:00 GMT Context rot explained: why a large context window does not stop an agent from getting worse mid-session, plus how to spot the dumb zone and four ways out. https://getagenttools.com/blog/agents-md-is-not-your-documentation/ https://getagenttools.com/blog/agents-md-is-not-your-documentation/ Sun, 20 Sep 2026 00:00:00 GMT AGENTS.md and CLAUDE.md files bloat when every fix gets appended to them. A router-first structure, plus what OpenWiki automates, keeps the entry file small. https://getagenttools.com/blog/google-merchant-center-feed/ https://getagenttools.com/blog/google-merchant-center-feed/ Sat, 19 Sep 2026 00:00:00 GMT Google Merchant Center feed audit: what a 548,575-item feed had wrong (empty MPN, constant availability, missing images) and which fixes actually moved. https://getagenttools.com/blog/claude-resume/ https://getagenttools.com/blog/claude-resume/ Fri, 18 Sep 2026 00:00:00 GMT claude --resume from the Claude Code docs: when to resume, when to /clear, what a resumed session restores and what it drops, from 215 transcripts on disk. https://getagenttools.com/blog/dangerously-skip-permissions/ https://getagenttools.com/blog/dangerously-skip-permissions/ Wed, 16 Sep 2026 00:00:00 GMT --dangerously-skip-permissions: what it skips, what deny rules and hooks still block, and the matching switch in Codex, opencode, Cursor, Copilot and Gemini CLI. https://getagenttools.com/blog/claude-p-headless/ https://getagenttools.com/blog/claude-p-headless/ Sun, 13 Sep 2026 00:00:00 GMT claude -p runs Claude Code with no terminal: prompt in, result out, JSON with cost and session ID. The flags my automations use and what --bare changes. https://getagenttools.com/blog/what-is-an-agent-harness/ https://getagenttools.com/blog/what-is-an-agent-harness/ Sat, 12 Sep 2026 00:00:00 GMT What is an agent harness: every piece of code around the model, the loop, the tools, the approvals and the log. Examples, harness vs agent, and the one I run. https://getagenttools.com/blog/claude-code-context-window/ https://getagenttools.com/blog/claude-code-context-window/ Fri, 11 Sep 2026 00:00:00 GMT Claude Code context window explained from the docs: what loads at startup, what /context shows, when auto-compaction runs, what survives, and the rules I keep. https://getagenttools.com/blog/what-is-function-calling/ https://getagenttools.com/blog/what-is-function-calling/ Thu, 10 Sep 2026 00:00:00 GMT What is function calling: the model picks a tool and writes the arguments, your code runs it and sends the result back. The loop, the cost, and MCP. https://getagenttools.com/blog/claude-code-memory/ https://getagenttools.com/blog/claude-code-memory/ Wed, 09 Sep 2026 00:00:00 GMT Claude Code memory has two parts: CLAUDE.md you write and auto memory Claude writes. Where each lives, the 200-line and 25 KB limits, and my 538 memory files. https://getagenttools.com/blog/what-is-a-system-prompt/ https://getagenttools.com/blog/what-is-a-system-prompt/ Tue, 08 Sep 2026 00:00:00 GMT What is a system prompt: the instructions an application loads before your message, what they can and cannot enforce, and how Claude Code builds its own. https://getagenttools.com/blog/claude-code-subagents/ https://getagenttools.com/blog/claude-code-subagents/ Mon, 07 Sep 2026 00:00:00 GMT Claude Code subagents run a task in their own context window and return a summary. What the docs guarantee, the two agent files I run, and one leaked .env file. https://getagenttools.com/blog/what-are-ai-guardrails/ https://getagenttools.com/blog/what-are-ai-guardrails/ Sun, 06 Sep 2026 00:00:00 GMT What AI guardrails are in operator terms: input filters, output checks and action gates, why the third one is the one agents need, and the three layers I run. https://getagenttools.com/blog/claude-chrome/ https://getagenttools.com/blog/claude-chrome/ Sat, 05 Sep 2026 00:00:00 GMT Field notes on claude --chrome, the flag that hands Claude Code your logged-in browser: 27 screenshot timeouts, clicks that miss, and the gates I use. https://getagenttools.com/blog/chatgpt-ads/ https://getagenttools.com/blog/chatgpt-ads/ Fri, 04 Sep 2026 00:00:00 GMT ChatGPT Ads: a US test in February, self-serve in 52 countries by September. What Ads Manager Beta gives you: bids, context hints, Pixel and Conversions API. https://getagenttools.com/blog/what-is-rag/ https://getagenttools.com/blog/what-is-rag/ Fri, 04 Sep 2026 00:00:00 GMT What is RAG in AI, in plain terms: fetch relevant text from a source you chose, put it in the prompt, then generate. How it works, RAG vs MCP, where it fails. https://getagenttools.com/blog/pretooluse-hook/ https://getagenttools.com/blog/pretooluse-hook/ Thu, 03 Sep 2026 00:00:00 GMT Before a tool call runs, a PreToolUse hook in Claude Code can deny it or ask me. My 79-line production guardrail, the ssh case rules miss, and its limits. https://getagenttools.com/blog/what-is-an-ai-agent/ https://getagenttools.com/blog/what-is-an-ai-agent/ Wed, 02 Sep 2026 00:00:00 GMT A plain definition of what an AI agent is: a language model that picks tools inside a loop, with a stop condition and a human on the gates that matter. https://getagenttools.com/blog/statusline-claude-code/ https://getagenttools.com/blog/statusline-claude-code/ Tue, 01 Sep 2026 00:00:00 GMT The statusLine setting runs a script on every update. My claude code statusline reads only stdin: median 41 ms, replacing a tool that took 13-20 s a render. https://getagenttools.com/blog/ai-agent-architecture-diagram/ https://getagenttools.com/blog/ai-agent-architecture-diagram/ Mon, 31 Aug 2026 00:00:00 GMT A practical AI agent architecture diagram with six layers for goals, orchestration, context, models, tools, policy, and production observability in practice. https://getagenttools.com/blog/llm-evaluation/ https://getagenttools.com/blog/llm-evaluation/ Sun, 30 Aug 2026 00:00:00 GMT A practical LLM evaluation method using representative test cases, deterministic checks, human review, calibrated model judges, and release gates that work. https://getagenttools.com/blog/ai-agent-examples/ https://getagenttools.com/blog/ai-agent-examples/ Sat, 29 Aug 2026 00:00:00 GMT Seven practical AI agent examples with their inputs, tools, stop conditions, human approval gates, and the failures each design must handle in production. https://getagenttools.com/blog/what-is-a-prompt-in-ai/ https://getagenttools.com/blog/what-is-a-prompt-in-ai/ Fri, 28 Aug 2026 00:00:00 GMT A plain explanation of AI prompts, their main parts, prompt roles, practical examples, common mistakes, and how to test whether a prompt works in practice. https://getagenttools.com/blog/mcp-server-security/ https://getagenttools.com/blog/mcp-server-security/ Thu, 27 Aug 2026 00:00:00 GMT A practical MCP server security checklist covering trust boundaries, credentials, token handling, approvals, sessions, sandboxing, and logs for AI agents. https://getagenttools.com/blog/what-is-an-ai-context-window/ https://getagenttools.com/blog/what-is-an-ai-context-window/ Wed, 26 Aug 2026 00:00:00 GMT What is a context window in AI? Learn what fits inside it, how it differs from memory, why long context still fails, and how agents manage it in practice. https://getagenttools.com/blog/ai-agent-deployment/ https://getagenttools.com/blog/ai-agent-deployment/ Tue, 25 Aug 2026 00:00:00 GMT AI agent deployment needs more than a working prompt. Use this practical path through sandbox, staging, canary release, monitoring, rollback, and approval. https://getagenttools.com/blog/what-is-ai-hallucination/ https://getagenttools.com/blog/what-is-ai-hallucination/ Mon, 24 Aug 2026 00:00:00 GMT What is an AI hallucination: a fluent, confident output that is not true. Why next-token prediction makes them inevitable, and which defenses work. https://getagenttools.com/blog/ai-time-dividend-tests/ https://getagenttools.com/blog/ai-time-dividend-tests/ Sun, 23 Aug 2026 00:00:00 GMT Agents write code many times faster. Robert C. Martin says spend the saved time on testing rigor. Field notes on what that looks like when you actually do it. https://getagenttools.com/blog/what-is-a-token/ https://getagenttools.com/blog/what-is-a-token/ Sat, 22 Aug 2026 00:00:00 GMT What is a token in AI: the chunk a model reads and writes text in. Roughly three-quarters of a word, and the unit behind every context limit and every invoice. https://getagenttools.com/blog/ai-agent-monitoring/ https://getagenttools.com/blog/ai-agent-monitoring/ Fri, 21 Aug 2026 00:00:00 GMT AI agent monitoring is not server monitoring. Field notes from running a 36-probe cockpit over an agent fleet: traces, review queues, judges, decision stamps. https://getagenttools.com/blog/slack-code-channels/ https://getagenttools.com/blog/slack-code-channels/ Fri, 21 Aug 2026 00:00:00 GMT Slack Code gives coding agents their own channels with diffs, previews and a self-archiving log. What it changes for permissions, prompts and who can build. https://getagenttools.com/blog/what-is-an-llm/ https://getagenttools.com/blog/what-is-an-llm/ Thu, 20 Aug 2026 00:00:00 GMT What is an LLM: a model trained on text to predict the next token, and the engine under chatbots and agents. How it works in practice and what people get wrong. https://getagenttools.com/blog/disable-model-invocation/ https://getagenttools.com/blog/disable-model-invocation/ Wed, 19 Aug 2026 00:00:00 GMT One frontmatter line decides if Claude can run a skill on its own. disable-model-invocation on 55 real skills, 0 flagged then 8, plus Copilot, Cursor, Codex. https://getagenttools.com/blog/what-is-ai/ https://getagenttools.com/blog/what-is-ai/ Tue, 18 Aug 2026 00:00:00 GMT What is AI, in plain language: software that handles judgment calls, learned from data instead of programmed. What the term covers, and the myths around it. https://getagenttools.com/blog/claude-md-audit/ https://getagenttools.com/blog/claude-md-audit/ Mon, 17 Aug 2026 00:00:00 GMT Anthropic cut over 80% of Claude Code's system prompt. The new CLAUDE.md best practices, tested against a real 482-line config and its 26 loudest rules. https://getagenttools.com/blog/production-ready-ai-agents/ https://getagenttools.com/blog/production-ready-ai-agents/ Fri, 14 Aug 2026 00:00:00 GMT A production-readiness checklist for AI agents: 12 gates across access, actions, failure and operations, each with a failure mode and a pass or stop test. https://getagenttools.com/blog/deepseek-harness/ https://getagenttools.com/blog/deepseek-harness/ Thu, 13 Aug 2026 00:00:00 GMT DeepSeek Harness ships under MIT with every capability as a plugin. What the docs let you swap, what they will not, and the tools left switched off. https://getagenttools.com/blog/build-your-own-mcp-server/ https://getagenttools.com/blog/build-your-own-mcp-server/ Tue, 11 Aug 2026 00:00:00 GMT When an MCP server integration is worth writing yourself, what it takes, and why tool descriptions cost more thought than code. Notes from two servers I run. https://getagenttools.com/blog/remote-mcp-servers/ https://getagenttools.com/blog/remote-mcp-servers/ Tue, 11 Aug 2026 00:00:00 GMT Hosted and public MCP servers move the credential, the failure mode and the trust boundary off your machine. What I run, what broke today, what I check first. https://getagenttools.com/blog/mcp-server-database/ https://getagenttools.com/blog/mcp-server-database/ Mon, 10 Aug 2026 00:00:00 GMT An MCP server for your database gives an agent live SQL in minutes. Field notes on schema cost, read-only roles, and why my write path never goes through MCP. https://getagenttools.com/blog/mcp-server-for-ai-agents/ https://getagenttools.com/blog/mcp-server-for-ai-agents/ Mon, 10 Aug 2026 00:00:00 GMT An MCP server for AI agents is judged differently than one for chat: tool count, description quality, error text, blast radius, and the check I run first. https://getagenttools.com/blog/mcp-servers-list/ https://getagenttools.com/blog/mcp-servers-list/ Mon, 10 Aug 2026 00:00:00 GMT An MCP servers list is only useful if it is short. The eight I keep connected, what earns a place, what gets one removed, and why directories do not help. https://getagenttools.com/blog/what-is-an-mcp-server-in-ai/ https://getagenttools.com/blog/what-is-an-mcp-server-in-ai/ Mon, 10 Aug 2026 00:00:00 GMT What is an MCP server in AI: host, client and server explained, both transports, and a plain answer to where your data ends up when an agent calls a tool. https://getagenttools.com/blog/muse-code-agent-harness/ https://getagenttools.com/blog/muse-code-agent-harness/ Thu, 06 Aug 2026 00:00:00 GMT Agent harness design notes on Meta's Muse Code launch: an append-only event log, background agents that outlive the task, and an approval gate as a skill. https://getagenttools.com/blog/field-notes/ https://getagenttools.com/blog/field-notes/ Sun, 26 Jul 2026 00:00:00 GMT Why this blog only covers agent tools that carry real production work, and how the verdicts get decided.