OVERVIEW

Verdaca docs

This documentation covers Verdaca's deliberation platform — how it is architected, how to run your first session, and how to extend it with custom agents and adapter substrates. It is written for practitioners: consultants, engineers, and technical leads who need to understand the system well enough to configure and deploy it.

ADVISORY

Start with the Conceptual model before touching configuration — the two-axis pluggability diagram is the key to understanding every other section.

What's in these docs

Overview (this page) — What Verdaca is and how these docs are organized.
Getting started — Installation, first session, and the four-step channel onboarding flow.
Channels & onboarding — Drive Verdaca from Microsoft Teams or Slack through one gateway, behind an auth-first spine. See Getting started for the flow and Conceptual model for the front door.
Conceptual model — Two-axis architecture, the auth-first front door, the deliberation loop, and kernel responsibilities.
Agent catalog — Available personas, capabilities, and how to load them.
Build your own agent — Define a custom persona and bind it to a session.
Workflow recipes — Pre-built deliberation patterns ready to run or adapt.
Output review — Scoring, audit trails, and custom rubrics.

Quick start

Three lines to run a deliberation session. Install the package, initialize a Studio, and pass a workflow name.

# Install Verdaca
pip install verdaca

# Initialise a session
from verdaca import Studio
session = Studio.create()
result  = session.run("[workflow-placeholder]")

Architecture at a glance

Verdaca is organized on two independent axes: swap the agent personas horizontally, swap the substrate adapters vertically. Neither axis requires changing the other.

Every request reaches the kernel through one channel-neutral gateway, after an auth-first spine of four checks — signature, identity, replay, and budget. See the front door in the conceptual model.