Skip to main content
The console transport prints the DM ShoulderTap would send an expert to your terminal, and reads the reply from stdin — the same loop as real Slack, with no Slack app or credentials needed for a first look.
Prerequisites: Python 3.11 or newer. No Slack, no API keys, no LLM required — without an LLM configured, ShoulderTap passes the expert’s reply through verbatim instead of structuring it.
1

Install and initialize

Install the package and generate a starter config:
shtap init prompts for an organization name and writes shouldertap.yaml (config) and .env.example (secret placeholders) to the current directory.
2

Add an expert

Open the shouldertap.yaml that was just written and add an expert under the experts: section:
The id is a Slack user ID in production, but with the console transport any string works. The topics list is what routing matches a question’s topic against.
3

Start the engine

In your first terminal, run the server with the console transport:
This starts the engine, the HTTP API (default port 8776), and the approval UI. Leave it running — this is the terminal where the DM to Dana will appear.
4

Ask a question

In a second terminal, submit a question as a consumer:
Terminal 1 now prints the DM ShoulderTap would have sent Dana on Slack — the self-identification, why it’s asking, the question, and the opt-out. Type a reply there, for example:
Terminal 2 is now polling for an answer and will wait until a reviewer accepts it.
5

Review and accept

In a third terminal, see the pending proposal and accept it:
Terminal 2 then prints the accepted answer, attributed to Dana:
That’s the whole loop: a consumer asked, an expert answered on a transport, a human approved, and the answer came back attributed. In production you swap the console transport for Slack and point real agents at the HTTP API, MCP server, or SDK.

​
What’s next

Concepts

Understand requests, proposals, experts, consumers, kinds, and topics.

Configuration

Every shouldertap.yaml setting, defaults, and how secrets map to .env.

Connect Slack

Swap the console transport for a real Slack app.

Integrate an agent

Tap a human expert from your own agent via MCP, the SDK, or webhooks.