Skip to content

Agentic CLI

The Agentic CLI is the headless configuration experience: talk to TapPass.

The operator types intent — "deny the gmail.send tool for every agent in the customer-support project, then attach the GDPR compliance pack to all of them" — and an LLM-driven agent uses the TapPass control plane (via MCP server tools) to plan, confirm, and apply the changes.

This is the long-term ambition. UI today, CLI next, Agentic CLI later.

Surfaceterminal session (or chat panel) running an LLM-driven config loop
DrivesTapPass control plane via the MCP server tool surface
Authoperator session token (SSO) — agent inherits operator's permissions
Outputapplied changes + audit trail entries + a human-readable diff log
Statusfuture

It's not autocomplete on the CLI. It's a loop:

[intent] Operator: "Deny gmail.send for all customer-support agents,
then attach GDPR pack to those projects."
[plan] Agent: lists target agents and projects (via resource reads),
builds an ordered set of mutations
[confirm] Agent shows the plan as a diff. Operator confirms or amends.
[apply] Agent calls the MCP tools in order, surfacing failures.
[review] Agent summarizes what changed, links to audit trail entries.

The agent is bounded by the operator's RBAC scope and by Compliance pack constraints — it can't authorize destructive changes the operator alone couldn't authorize.

Three drivers:

  1. Headless future. The product vision treats UI as the on-ramp; long-term, configuration moves to CLI + agentic flows.
  2. Cross-project changes are high-leverage but tedious. "Apply this compliance pack to every project in the org" is a lot of clicks; one sentence to an agent does it.
  3. Self-documenting changes. The agent's plan + diff + summary become a natural change-log entry — better than what an operator typing CLI commands typically writes.

The agent is bounded by:

GuardrailEffect
Operator RBAC scopeAgent can't do anything the operator can't
Plan-then-apply gatingNo mutation without operator confirmation (configurable threshold)
Audit trailEvery action lands in audit, marked as agent-driven with operator + plan id
Compliance pack constraintsMutations that would violate an attached compliance pack are rejected
Loop guardRecursive / runaway agent loops detected and stopped
PersonaSurfaceWhat they do
OperatorTerminal tappass agenticOpen an agentic config session
OperatorAdmin UI → AI AssistantSame loop, in a chat panel inside the UI
AuditorAudit trailSee exactly which mutations the agent made on whose behalf, with the plan