Skip to main content
Guide · How-to

Your first session

Launch the workspace, run an agent, read the numbers. What you'll see and how to interpret it.

Step 1

Open the workspace

senkani

Or open SenkaniApp from /Applications if you dragged it there. A single empty canvas appears.

Step 2

Open three panes

⌘K → type "Terminal" → Enter. ⌘K → "Analytics". ⌘K → "Agent Timeline". Three panes side by side.

Step 3

Start the agent

In the Terminal pane:

claude

Claude Code starts; MCP handshake happens automatically (you can confirm via the "MCP connected" indicator in the status bar).

Step 4

Ask for something real

Ask the agent to do something that involves reading your project:

> Find the function that handles order pagination.

Watch the Agent Timeline pane fill with tool calls (senkani_searchsenkani_fetch → possibly senkani_read). Each line shows the tool, target, and compression ratio.

Step 5

Read the Analytics pane

  • Tokens saved — bytes that would have been sent to the LLM but weren't.
  • Cost saved — tokens × model rate (from the pane's model preset).
  • Compliance rate — fraction of tool calls that went through Senkani vs the agent's built-ins. High is good.
  • Per-feature breakdown — F / C / S / I / T contributions.

What "good" looks like

If compliance is low

The agent is bypassing senkani tools. Run senkani doctor to check registration; make sure the MCP server entry in ~/.claude/settings.json is present; make sure you launched claude inside a Senkani-managed Terminal pane (the one the app opened, not a random shell).

Next

Budget setup →