Docent

Docent is a third-party tool by Transluce for summarizing, clustering, and searching over agent transcripts. It is not part of Control Tower; see the Docent repo and Docent docs for support and documentation. Control Tower can run it as an optional local service and provides a CLI for managing collections, uploading evaluation data, and sharing collections with collaborators.

Local Service

Docent is not started by default. To include it:

docker compose --profile docent up -d

Docent runs entirely locally with its own PostgreSQL database. Accounts are created on first sign-up and stored there.


Frontend	http://localhost:3001
API	http://localhost:8888
Backed by	PostgreSQL (port 5432), Redis (port 6379)
DB credentials	`docent_user` / `docent_password` (database: `docent_db`)

To get started, go to http://localhost:3001 and create an account. To do it from the command line instead:

Sign up: curl -X POST http://localhost:8888/rest/signup -H 'Content-Type: application/json' -d '{"email":"you@example.com","password":"pass"}'
Log in: curl -X POST http://localhost:8888/rest/login -H 'Content-Type: application/json' -d '{"email":"you@example.com","password":"pass"}'
Create an API key and manage collections at http://localhost:3001

Local Environment Variables

Add these to your main .env. They have no defaults, and ct docent commands fail with an error naming any that are missing.

DOCENT_SERVER_URL=http://localhost:8888
DOCENT_WEB_URL=http://localhost:3001
DOCENT_API_KEY=<your-api-key-after-signup>

For Docent's LLM features, copy .env.docent.example to .env.docent and add your API keys. Only that file is passed to the Docent containers:

cp .env.docent.example .env.docent
# Add your ANTHROPIC_API_KEY and/or OPENAI_API_KEY

Installation

Install the CLI's dependencies:

uv sync --extra docent

Quick Start

Set the Docent environment variables in your .env.
Create a collection:
```
ct docent create --name "My Evals"
```
Upload evaluation logs:
```
ct docent upload logs/my_eval.eval
```

Add a collaborator:

ct docent collaborator-add colleague@example.com

Commands

Run ct docent --help for the collection, upload, and sharing commands and their options. Collaborators added with collaborator-add get read access, and make-public prints the public dashboard URL.

Interactive Collection Selection

Every command that operates on a collection prompts you to pick one if you don't pass a collection ID. Pass the ID to skip the prompt, for example when scripting.

Select a collection:
  1. Linux Evals (ID: abc123) - Evaluation runs for Linux tasks
  2. Agent Tests (ID: def456)
  3. Production Runs (ID: ghi789) - Weekly production evaluations
Select option (1-3):