Learn

Every developer's agent on your team works a different way, and the shared instructions file grows until nobody reads it. In nine lessons you give the team one way of working, built by asking Claude Code: a short AGENTS.md that routes to your standards and docs, a locked review list, a hook, one bug-fix workflow, and three loops that keep it small. Lesson 9 checks your own repo for the certificate.

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.

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.

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.

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.

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.

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.

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.

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.