Guides

A guide is a one-page answer that settles one practical question about building or running AI agents, such as what graph engineering is and when a team should use it. Neomanex writes each guide, shows when it was last updated and publishes a plain-text copy that AI assistants can quote.

Guide

Intermediate · 13 min · Updated Oct 12, 2026

Playwright MCP Acceptance Testing: Agents Run the Journeys
Agent-driven acceptance testing is a verification loop where an AI agent drives each user journey in a real browser and reports pass or fail against frozen acceptance criteria. We run acceptance testing with Playwright MCP on ConvOps: the agent that tests never fixes, and a failure goes back to the build until the whole run passes again.

Read guide

Guide

Intermediate · 27 min · Updated Oct 12, 2026

Build a Self-Improving AI System: Workflows, Memory, Gates
A self-improving AI system is a repository of standards, a memory store and gated workflows that turn each finished job's lessons into rules the next job reads. It learns in six layers, from memory to a pipeline that reviews the whole system. We run ours on ConvOps.

Read guide

Guide

Beginner · 30 min · Updated Oct 10, 2026

Claude Code Deleted My Files? The Layer That Stops It
A Claude Code delete guard is four layers that stop an agent deleting your files: an approval prompt, a deny rule, a PreToolUse hook and work that is committed and pushed. ConvOps adds isolated runs and a sign-off before merge for the runs nobody watches.

Read guide

Guide

Beginner · 10 min · Updated Oct 10, 2026

CLAUDE.md Too Long? What to Cut and Where It Goes
A CLAUDE.md is too long when it carries lines the agent would not get wrong without them. Neomanex fixes it with an audit: test every line, keep what prevents a mistake, and move the rest to a docs page, skill, folder rule, ConvOps workflow or hook, for CLAUDE.md and AGENTS.md alike.

Read guide

Guide

Beginner · 9 min · Updated Oct 12, 2026

How We Run Our Company With AI Agents on Workflows That Remember
Running a company with AI agents means every job runs on a written workflow, not a chat: its first step recalls what was decided before, a person signs off where it matters, and the job keeps what is worth remembering. We run ours on ConvOps, where our tasks, workflows and memories live.

Read guide

Guide

Intermediate · 14 min · Updated Oct 12, 2026

Self-Healing Website AI Agent: Heal What It Can Verify
A self-healing website AI agent is a scheduled loop that reads a site the way a reader gets it, files each defect as a bug, and has an agent in an isolated environment repair what it can rewrite and re-check, holding the rest for a person. ConvOps runs the weekly sweep, the bug pool and the per-bug heal.

Read guide

Guide

Intermediate · 12 min · Updated Oct 10, 2026

SEO + GEO Experiments With Claude Code and a Control Group
The SEO experiments loop is an agent loop that turns every SEO fix into a pre-registered experiment with a randomised control group. ConvOps schedules each run, Claude Code makes the change, a human merges it, and a script judges it against untouched pages at day 15 and day 31.

Read guide

Guide

Intermediate · 8 min · Updated Oct 10, 2026

What Is Graph Engineering? An 8-Line CLAUDE.md
Graph engineering is designing an AI agent system as a graph: nodes do the work, edges decide what runs next, and state travels between them. Our take: the graph replaces the instructions file, so a CLAUDE.md can shrink to 8 lines while the process and the rules live in workflows and standards.

Read guide

Questions about these guides

What is on this page and how do I choose?

This page lists every guide Neomanex has published, newest first. Each guide answers one question about building or running AI agents. Each card shows the level, the reading time and the date of the last update. Start with the guide whose title matches the question you have today. Pick a beginner guide if agents are new to you, and an advanced guide if you already run agents in production.

Who are the Neomanex guides for?

Neomanex writes the guides for people who build and run AI agents at work, such as developers, product managers and team leads. Each guide answers one practical question on a single page. The reader leaves with one decision or one change to apply to their own agents. Reading a guide needs no account and no payment.

How is a guide different from a course?

A Neomanex guide is one page that answers one question, and anyone can read it in a few minutes without signing in. A course is a sequence of lessons with quizzes, and tracking your progress through it needs an account. When a course covers the same topic in depth, the guide page links to that course after the guide text.

How do I know a guide is still current?

Check the date on the guide card, or in the facts panel beside the guide text. Neomanex shows the date each guide was published and, after any later change, the date of the last update. Some guides also show a last verified date and a note on what changed. A guide with no update date has not changed since it was published.

Which languages are the guides in?

Neomanex writes each guide in English and can translate it into Spanish, Portuguese, French and German. When a guide has a translation in the language you browse in, the guide page shows it. When it has none yet, the page shows the English text with a notice that says so. The steps and the questions of a guide are translated together with its text.

What is llms.txt, and can an AI assistant read these guides?

llms.txt is a plain-text file at the root of a website that lists the pages an AI assistant should read. The Neomanex llms.txt lists every published guide with links to the page and to its markdown copy. Each guide also has a plain markdown copy at its address with .md added at the end, and this list of guides has one at /learn/guides.md. An assistant can quote a guide from that copy without loading the web page.