AI agents that work inside your management system
af-cli gives AI agents access to AmpliFlow. This is our research preview
of how agents can do the groundwork in your management system: gather input, identify
gaps in risk registers, draft updates. You review and decide.
We use it internally every day. Now we want to know what you think.
af-cli A CLI and an agent skill
af-cli is two things. A command-line tool that gives access to AmpliFlow
from the terminal: projects, tasks, risks, deviations, goals, checklists. And a
skill that AI agents can use directly.
Running OpenClaw?
af-cli works as a drop-in skill. Running opencode? You get both a plugin and a
subagent. It also works with Claude Code and other agents that can run
commands in the terminal.
Everything the agent creates is automatically marked as AI-generated, in line with the EU AI Act. You always know what came from a person and what came from the agent.
AmpliFlow projects as shared memory
The quality manager works in AmpliFlow. The agent works in the terminal. Same project, same tasks, same data.
People in AmpliFlow
You create tasks, write comments, and make decisions in the interface you already know. Nothing new to learn.
The agent in the terminal
Your IT person starts the agent once. It picks up tasks, works through them, and reports back. You see the results directly in AmpliFlow.
Workflows on demand
"Go through the management review and see what is missing." "Create a risk register from our ISO 27001 gap analysis." Describe what you need done. The agent plans and executes.
The same things you do in AmpliFlow
The agent has access to the full system. You describe what you want done. It reads, reasons, and acts.
Risk management
Read through all risks, spot which ones are missing probability and consequence scores, identify what your processes don't cover, create new risks and link them to the right actions.
Deviations and improvements
Go through open deviations, flag which ones have been sitting idle too long, propose root causes, create improvement items and follow up to make sure actions actually happen.
Project tasks
Pick up tasks, work through them, leave comments on what's been done and what remains, mark them complete. All while you're doing something else.
Goals and follow-up
Read your goals, see which ones haven't been updated in a while, fill in results from the latest period, and flag goals at risk of being missed.
Checklists and processes
Go through checklists that haven't been run on schedule, create new checklist instances, document results, and escalate deviations right away.
Management review
Collect input from across the system, risks, deviations, goals, audits, and produce a structured decision package ready for management to review.
NIS2 risk review in 42 seconds
One example of what an agent can do: read 9 tasks and 5 existing risks, identify 5 gaps against NIS2 requirements, and register them when you say "Do it".
What do you think?
af-cli is free for all AmpliFlow customers and we use it ourselves every day.
This is not a finished product. It is a research preview.
We want to know what you would use it for, what is missing, and what does not matter.