Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.zgi.cn/llms.txt

Use this file to discover all available pages before exploring further.

What is an agent?

The agent is the smallest delivery unit of ZGI and is the AI application that users ultimately publish, call and integrate. An agent is composed of workflow + model + knowledge base + prompt words, and provides conversational or workflow-style AI capabilities to the outside world.

Two types of agents

TypeDescriptionTypical Scenario
Conversational AgentTalk directly to users and answer questions based on knowledge base and modelsCustomer service, Q&A, consultation
Workflow AgentPerform multi-step tasks according to preset workflowsContract review, report generation, data analysis

Agent life cycle

Create

Select the agent type and configure basic information: name, icon, description, permission scope (visible only to yourself/visible to the team/visible to the organization). The system automatically generates a unique identifier and initializes the workflow draft.

Arrangement

Drag and drop nodes on the visual canvas to build a business process. Supports multiple node types such as model nodes, knowledge base nodes, database nodes, HTTP nodes, code nodes, conditional branches, loops, iterations, etc.

Debugging

Enter test data in the debugging area, and the system displays the execution status and results of each node in real time through SSE. Drafts are automatically saved every 30 seconds to avoid losing edits.

Publish

Publish it as an accessible web application (agent landing page) with one click, or generate an API Key for external system calls. A version number is automatically generated for each release, which can be traced and rolled back.

Operation and maintenance

View running logs, token consumption, number of calls, exception rate and other running data. Supports configuring API Key’s quota limit, expiration time, and IP whitelist.

Workflow node type

ZGI provides a wealth of built-in nodes to cover most business process orchestration needs:
NodeFunctionTypical usage
Start NodeDefine workflow input parametersReceive user input or API request parameters
LLM NodeCall large models for inferenceText generation, analysis, translation, classification
Knowledge Base NodeRetrieve information from the knowledge baseQ&A, term query, answer with citation
Database NodeQuery structured dataContract ledger, project records, data statistics
NL2SQL nodeNatural language to SQLBusiness personnel do not need to write SQL to query the database
Conditional branchSelect execution path based on variable valueRisk level classification, type judgment
Code NodeRun Python/JS custom logicData processing, format conversion
HTTP nodeCall external APIConnect with CRM, ERP, OA and other systems
Iteration nodeBatch processing of array dataContract review one by one, data processing one by one
Loop NodeRepeat execution according to conditionsRetry logic, iterative optimization
End NodeOutput the final resultReturn JSON, text or trigger subsequent actions

Trigger method

Trigger methodDescriptionTypical scenarios
User conversationWorkflow triggered when user sends messageCustomer service Q&A, intelligent assistant
API callsTriggered via REST APISystem integration, automated processes
Scheduled tasksRegular execution according to Cron expressionPeriodic reports, data synchronization
File uploadAutomatically triggered when user uploads a fileAutomatic review of contract upload, automatic document storage
WebhookReceive external system callback triggersOA approval, CRM events, ERP changes

Variables and context

Variables are the core mechanism for transferring data between nodes. ZGI supports a three-layer variable system:
Variable typesScopeTypical uses
Environment variablesGlobalAPI Key, model configuration and other sensitive information
Session variablesSingle conversationContextual memory, user preferences
Node variablesTransfer between nodesThe output of the previous step is used as the input of the next step

Core Features

  • SSE streaming execution — push the execution status and results of each node in real time, and the front end can display the progress
  • Draft AutoSave — Automatically saves workflow drafts every 30 seconds to prevent lost edits
  • Version Management — Automatically generate a version number for each release, traceable and rollable
  • YAML template — Agent configuration can be exported to YAML for reuse across teams and environments
  • API Key Quota — Generate a dedicated API Key for each agent, supporting daily/monthly quota, expiration time, and IP whitelist
  • Asset prevention from accidental deletion — Checking mechanism prevents accidental deletion of running agents; employees can be handed over with one click when they leave.