Converso

Create Workflow

Parse SDK TypeScript and create a new published workflow. `code` is TypeScript source using `@dograh/sdk`. The workflow name comes from `new Workflow({ name: "..." })` — it is required. Example code: import { Workflow } from "@dograh/sdk"; import { startCall, endCall } from "@dograh/sdk/typed"; const wf = new Workflow({ name: "lead_qualification" }); const greeting = wf.addTyped(startCall({ name: "Greeting", prompt: "Hi!" })); const done = wf.addTyped(endCall({ name: "

Create Tool

Create a reusable tool the agent can invoke during calls. The request schema is the same `CreateToolRequest` used by the REST API and generated SDKs. Use it to create HTTP API, end-call, transfer-call, calculator, or MCP-server tools. For authenticated HTTP or MCP tools, reference an existing `credential_uuid` from `list_credentials`; users create credential secrets in the UI, and this flow only stores the UUID reference. For MCP tools, the server best-effort discovers the remote tool catalog a

Get Node Type

Fetch the authoring schema for a node type: each property's name, type, default, requiredness, enum options, validation bounds, and LLM-readable description, plus worked examples and graph constraints. UI-only metadata (display labels, placeholders, conditional visibility rules, renderer hints) is intentionally omitted — set only the fields you need. Use the property `description`/`llm_hint` and the `examples` list to understand semantics; types alone are not enough.

Get Workflow

Fetch a single agent by id, projected into the SDK code view. Output shape: {"id": int, "name": str, "status": str, "version": "draft" | "published" | "legacy", "version_number": int | None, "code": "<TS source>"}

Get Workflow Code

Return the workflow as SDK TypeScript code the LLM can edit. Output shape: {"code": "<TS source>", "workflow_id": int, "version": "draft" | "published" | "legacy"} The LLM edits `code`, then calls `save_workflow(workflow_id, code)`.

List Credentials

List external credentials available for webhook auth and pre-call fetch. Returns each credential's `credential_uuid` (use this in node `credential_uuid` / `pre_call_fetch_credential_uuid` properties), `name`, `description`, and `credential_type`.

List Documents

List knowledge-base documents the agent can reference during a call. Returns each document's `document_uuid` (use this in node `document_uuids` properties), `filename`, and `processing_status`.

List Node Types

List every available node type with a brief summary. Use this first to discover what nodes exist, then call `get_node_type` for the full schema of any node you intend to use. Returns: A dict with `spec_version` (pin against this in any generated workflow code) and `node_types` (list of {name, display_name, description, category}).

List Recordings

List pre-recorded audio files available for greetings and edge transition speech. Returns each recording's `recording_id` (use this in `greeting_recording_id` / `transition_speech_recording_id` properties), `transcript`, and TTS metadata. Pass `workflow_id` to filter to one workflow's recordings.

List Tools

List tools the agent can invoke during a call. Returns each tool's `tool_uuid` (use this in node `tool_uuids` properties), `name`, `description`, and `category`. Pass `status=None` to include archived tools.

List Workflows

List agents (workflows) in the caller's organization. Returns id, name, status, and created_at for each agent. Use `get_workflow` to fetch a single agent's current SDK view and metadata. Defaults to active agents; pass `status="archived"` to list archived agents, or `status=None` to list all.

Save Workflow

Parse SDK TypeScript and save the resulting workflow as a draft. `code` is TypeScript source using `@dograh/sdk`. Fetch the current code first via `get_workflow_code(workflow_id)`, edit it, then pass the full updated source here. Example code: import { Workflow } from "@dograh/sdk"; import { startCall, endCall } from "@dograh/sdk/typed"; const wf = new Workflow({ name: "lead_qualification" }); const greeting = wf.addTyped(startCall({ name: "Greeting", prompt: "Hi!" })); co

Get Voice Prompting Guide

Fetch staged voice-prompting guidance for authoring Dograh workflows. Call this BEFORE composing or revising any prompt field on a node. The guide is the authoritative source for prompt-authoring craft (global guidelines, turn-taking, tool calls, success criteria, guardrails); product-mechanics questions (how a node type works at runtime) belong in `search_docs` / `read_doc`.

List Docs

Browse the Dograh docs hierarchy before reading a page in full. ``path`` addresses navigation sections exposed by this tool. Page paths returned by ``search_docs`` and ``read_doc`` are the published docs routes instead, for example ``voice-agent/tools/mcp-tool``.

Read Doc

Read one docs page after you have narrowed to a likely match.

Search Docs

Search the Dograh documentation and return a lean ranked shortlist. Use this first for keyword or acronym lookup. Once the right page looks likely, call ``read_doc(path)`` instead of reasoning from summaries alone.