AI Agents & Automation: RAG, Workflows & Guides

If you put several sites in one repository and place a CLAUDE.md or AGENTS.md in each site's folder, those rules aren't guaranteed to be read before work begins. Claude Code loads a CLAUDE.md below the launch directory when Claude reads, writes or edits a file in that folder, while Codex reads only the AGENTS.md files from the project root down to the launch directory, once at the start of each run. This article compares, item by item, how both tools load these files and how to check whether they were loaded (/context shows only what was loaded at startup), then covers a check that stops the release if anything outside the assigned folder changes, and tool settings that block writes. It also shows how to tell similarly named repositories apart by remote URL and root commit, and commands that show only environment variable names (checked November 1, 2026).

"Codex won't go parallel unless you tell it to" is true, with conditions: the Codex app, CLI and IDE extension spawn subagents when you ask directly, or when AGENTS.md or a skill instructs delegation (Ultra in ChatGPT Work also delegates on its own judgment). Claude Code delegates on its own based on the request and each subagent's description. Using the official OpenAI and Anthropic documentation (checked October 26, 2026), this article compares what triggers parallel work, five things to put in your instructions, ready-to-use example prompts, [agents] in Codex's config.toml and the TOML files in .codex/agents/, Claude Code's .claude/agents/ and environment variables, commands such as /subagents, /tasks, /subtask, /batch and /worktree, tasks that suit parallel work and tasks that don't, and the impact on usage limits, and it also shares lessons this site learned from running subagents in parallel.

Claude Duet is Anthropic's app in which Claude works as a proactive agent, sending a morning briefing and periodic check-ins and carrying out tasks in the cloud. Based on Anthropic's announcement and help documentation (checked October 22, 2026), this article covers the Make and Tasks tabs and over 6,000 connectors; who can use it and pricing (invitation-only Pro and Max in the US, no extra charge, limits shared with Claude, and a limit reset through November 30); the approval safeguards before sending, paying, signing, or deleting; current limitations; availability outside the US; and how it differs from ChatGPT's dot.

Claude's Max, Ultra, and Team plans come with credits you can use on the Claude API every month ($100 on Max, $200 on Ultra, and up to $500 in total on Team depending on the number of seats). However, you don't receive them until you link a Claude Console organization on the claude.ai billing page, and unused credits don't roll over. This article is based on my record of the screens when I claimed the credits on a Max 20x (now Ultra) plan on October 10, 2026, and on the official documentation, help articles, and terms, which I checked in the original on the same day. It explains where the credits can be used (the API, Message Batches, Managed Agents, the Agent SDK, the Playground, and claude -p run with an API key) and where they can't (interactive Claude Code, extra usage in the apps, Bedrock, and more); that linking partway through a cycle still gave me the full amount, expiring about three weeks later; that you can't change the linked organization yourself and an organization can receive only one plan's credits; the order credits are used in and auto-reload; how keeping ANTHROPIC_API_KEY set permanently switches Claude Code to API billing; ways to use the credits up and spend limits; and key points from the terms, such as the credits not being transferable or sellable.

Check a ChatGPT scheduled task in three stages: registration, run, and notification. Plan-specific reservation limits, setup steps, editing, stopping, and notification troubleshooting are explained with diagrams and tables. Also covers differences from Codex PC schedules and dot, usage allowances, and project file and shared link limits.

Compare Codex Remote and Cloud by where work runs, PC sleep behavior, phone access, development environments, and usage allowances. Learn the conditions for the connected PC, Cloud setup and unsupported features, Handoff limits, and how Work Cloud and dot differ. Also see what to check when a connection fails.

Use Codex /goal to keep a completion condition across investigation, fixes, and verification. This guide separates desktop and CLI operations, gives example requests, and covers pausing, resuming, clearing, and reasons work stops partway. It also explains how token budgets differ from pricing and what evidence to check in a completion report.

Claude Tag is an Anthropic feature that lets you hand Claude research, document writing, recurring reports, and even draft GitHub pull requests just by typing @Claude in a Slack channel (announced June 23, 2026, in public beta). Only Team and Enterprise organizations can use it; on personal Pro and Max plans, the prompt may appear on claude.ai, but clicking it leads nowhere. I confirmed this is by design using the actual screen from clicking it on a personal Max plan and the matching row in the official troubleshooting page. This article lays out, from the original text of the official docs as of October 4, 2026, a decision flow for whether you can use it, how coworkers without a Claude seat can still ask in channels, where each kind of work is billed (the monthly limit options, and the 7-day, $50, 50-session limits on DMs from members without a connected account), how to ask in channels, DMs, and group DMs, channel memory, scheduled runs and channel monitoring with Routines, switching models, connecting tools with Access bundles and dedicated Claude accounts, the PR flow on GitHub and GitLab and two-person approval, how guests and Slack Connect are handled, data retention and deletion, common snags and commands, and how it differs from the earlier Claude in Slack, Cowork, and Claude Code.

Claude Code's /doctor prompt-audit (/checkup prompt-audit is the same) has Claude read CLAUDE.md, CLAUDE.local.md, AGENTS.md, and the rules, skills, commands, and subagents under .claude/, look for prompting written for older models, references to files or commands that don't exist, and instructions that contradict each other, and return a report with proposed diffs. Nothing changes until you ask, and it requires v2.1.283 or later. Based on the official docs and CHANGELOG as of October 3, 2026 and the audit guide bundled with Claude Code, this article covers how to run it and narrow it with a path, what it counts as stale (over-strong wording, missing paths, conflicts between files, and more), its rule against deleting context and prohibitions that exist for a reason, the six fields of the report and how to read confidence levels, and how it differs from /doctor, /claude-api prompt-audit, and the terminal claude doctor command. It also shares what happened when we ran it on this site's instruction files (7 of 9 findings applied, including a real drift where we forgot to rewrite an explanation after adding a rule) and caveats such as usage allowance, run-to-run variation, and the effort of checking findings before applying them.

Claude Code's /code-review is a bundled skill that reads your commits ahead of upstream plus uncommitted changes (or a PR, branch, or path you pass), hunts for correctness bugs, and reports them. /review is an alias, the review runs as a background subagent, and its cost counts toward your normal usage. This article covers how to pass a target, how to choose between low (only high-confidence findings) and medium to max (wider coverage, but you need to sort the results), the rule that leaving out the level reuses the last level you typed, the caveat that --fix edits made in the background can't be undone with /rewind, and where --comment posts on GitHub and GitLab. It also explains ultra, where multiple agents in the cloud return only verified findings (about 15 to 25 minutes; 3 one-time free runs on Pro and Max, then typically $5 to $25 per run in usage credits), and how /code-review differs from /simplify, /security-review, the GitHub App's Code Review, and claude-code-action, based on the original text of the official documentation and CHANGELOG as of October 2, 2026 (the level descriptions as of October 14). Finally, it shares the results of running /code-review high once on the code for this site's AI image checker tool (9 of 10 findings were real bugs, all fixed) and the downsides, including usage, the work of checking findings, and how to undo --fix.

ChatGPT dot is a continuous AI agent that keeps working on tasks between conversations, included at no extra charge with Pro. In our to-do app test, dot handled generating the app and adding undo, but screen checks were completed in Codex. The article covers pricing, usage limits, memory and permissions, delegation to Codex, and how to stop work, so you can decide how to split work between dot and Codex.

ChatGPT Pro comes in three tiers: 100, 200 and 500. Since October 29, 2026, the Work and Codex allowances are 10, 20 and 50 times Plus (calculated by this site), and the official monthly prices are $100, $200 and $500, so two 100 subscriptions and one 200 cost the same and give the same total allowance; local-currency prices vary by country or region. The article also explains how speed settings use up allowance, how and when to use banked reset passes, and how they differ from credits.