Slack agent workflows

Bring agent workflows closer to where operators work

Dekaplane supports Slack-oriented ChatOps patterns while keeping agent actions governed by the self-hosted control plane.

Slack is often where operational questions start. The challenge is connecting those conversations to safe tools, deterministic workflows, model routing, and visibility.

Dekaplane treats Slack-style agent workflows as part of the governed platform rather than a disconnected automation channel.

From chat request to controlled workflow

A Slack agent workflow should have clear limits: which models are used, which tools are available, and how each step is tracked. Dekaplane centralizes those decisions.

  • Admin-selected model routes
  • Approved tool inventory
  • Workflow state and trace events
  • Platform-level review of behavior

Where MCP fits

MCP integrations make tools discoverable and manageable as part of the platform. For Slack-oriented workflows, that means agents can act through approved capabilities instead of arbitrary external calls.

  • Tool discovery through MCP
  • Tool enablement through the control plane
  • Policy boundaries around execution
  • Traceable tool calls

What this enables

The goal is not to turn chat into an unchecked automation surface. The goal is to let operators ask for help, trigger approved workflows, and inspect the result when something needs review.

  • Faster operational interaction
  • Clearer accountability
  • Less manual glue code
  • More trustworthy agent behavior

Related reading

Explore adjacent product areas

Current release

Start with the free self-hosted package

Dekaplane is currently available as a Free single-tenant self-hosted release with portal-based downloads, license materials, and installation guidance.