Stacklumen runs AI agents inside Slack that can ship real changes to client sites through our internal tooling. This page sets out exactly how that works: what the agents do, who directs them, how requests flow, and the policies that keep every change safe, reviewed, and accountable.
These terms apply in every Slack channel where Stacklumen agents operate — our internal workspace and the shared channels we run with clients and partners.
You never talk to an agent. You talk to us — in plain language, in your shared channel — and we run the agentic work internally.
Describe the change you want in your shared channel — plain language is perfect — and tag @iainfeeney so it enters the queue.
Stacklumen crafts, scopes, and runs the agent instruction internally. Prompt systems are proprietary and never client-operated.
The agent performs the change through internal tooling under staff direction, with review before anything ships.
We confirm what changed, where, and when it published — in the same thread.
Tagging @iainfeeney is the entire workflow. Clients never operate agents directly — every agentic change is authored, executed, and reviewed by Stacklumen.
Agentic tooling is internal by design. Restricting who can direct the agents is what makes agent-shipped changes safe enough to offer at all.
Agent-operated channels are still your channels. Here’s what gets processed, what doesn’t belong in Slack, and how retention works.
Agents make us faster; they don’t replace judgment. Staff review sits between agent output and anything that reaches production.
A few hard lines. They protect your site, your data, and every other client who shares the workspace with us.
We may update these terms as agent capabilities evolve — the live version of this page always governs. Material changes are announced in shared channels. Questions: support@stacklumen.com.
Describe what you want in your shared Slack channel and tag @iainfeeney — we’ll take it from prompt to published. No agent wrangling required.
