​

Glossary

A reference guide to the terminology used throughout CogniAgent. If you’re new to workflow automation or AI agents, start here.

​

Core Concepts

​

Application

A container that holds one or more workflows. Think of it as a project folder. Applications let you organize related automations together and manage them as a unit. Example: An “Order Management” application might contain workflows for order confirmation, shipping updates, and returns processing.

​

Workflow

A sequence of connected nodes that automates a process. Workflows start with a trigger and include actions and logic nodes that execute in order. Example: A workflow that starts when a customer submits a form, uses AI to categorize the request, and routes it to the appropriate team.

​

Node

A single step in a workflow. Nodes are the building blocks you connect together. There are three types:

• Triggers — Start the workflow
• Actions — Perform tasks
• Logic — Control the flow

​

Execution

A single run of a workflow. When a trigger fires, it creates an execution that moves through each node in sequence. You can view execution history to see what happened.

---

​

Trigger Types

​

Start Trigger

The simplest trigger. Runs the workflow when you click the Run button manually. Good for testing or workflows you want to run on-demand.

​

Scheduled Trigger

Runs the workflow on a time-based schedule. Can be set to hourly, daily, weekly, or custom intervals using cron expressions. Example: Run a report every Monday at 9 AM.

​

App Trigger

Starts the workflow when something happens in a connected application. Requires an integration to be set up first. Example: When a new row is added to a Google Sheet, when an email arrives in Gmail.

​

Webhook

Starts the workflow when an external system sends an HTTP request to a unique URL. Useful for connecting with systems that support webhooks. Example: When Stripe sends a payment notification, when a form service submits data.

​

AI Lookout

Uses AI to monitor a condition and triggers when that condition is met. More flexible than rule-based triggers. Example: Trigger when an email appears urgent based on its content, not just keywords.

---

​

Action Types

​

Ask AI

Sends a prompt to an AI model and returns the response. Use this for text generation, summarization, classification, or any task where you need AI intelligence.

​

App Action

Performs an action in a connected application. Requires an integration to be set up. Example: Send an email via Gmail, create a row in Google Sheets, post a message to Slack.

​

Call AI Agent

Invokes an autonomous AI agent that can perform multi-step tasks independently. Agents can use tools, make decisions, and complete complex objectives.

​

Ask a Person

Orchestrates multi-turn conversations with humans across multiple channels. Uses skillsets to collect structured data through natural dialogue. The person can respond through email, Slack, SMS, web chat, or other connected channels.

​

Execute Code

Runs custom JavaScript or Python code. For advanced users who need logic that isn’t available through standard nodes.

​

HTTP Request

Makes a web request to any URL. Use this to integrate with APIs that don’t have a dedicated CogniAgent integration.

​

Update Variable

Sets or updates a variable value that persists across the workflow execution or the entire application.

​

Read File

Extracts content from uploaded files. Supports PDFs, documents, spreadsheets, and images.

---

​

Logic Types

​

Condition

Branches the workflow based on a true/false condition. If the condition is true, one path executes. If false, another path executes. Example: If order total is greater than $100, apply free shipping. Otherwise, calculate shipping cost.

​

Multi-Condition (Switch)

Branches the workflow based on multiple conditions. Like a condition node but with more than two paths. Example: Route support tickets to different teams based on category: billing, technical, or general.

​

Loop

Repeats a set of nodes for each item in a list. Useful for processing multiple records. Example: For each row in a spreadsheet, send a personalized email.

​

Pause

Stops the workflow for a specified duration before continuing. Example: Wait 24 hours before sending a follow-up email.

​

Wait and Combine

Waits for multiple parallel branches to complete before continuing. Used when you’ve split a workflow and need to merge the results.

---

​

Data Concepts

​

Variable

A named value that stores data during workflow execution. Variables can be set by nodes and referenced by other nodes. Types:

• Runtime variables — Exist only during a single execution
• Application variables — Persist across executions

​

Variable Reference

The syntax for accessing data from other nodes: {{node_name.field_name}} Example: {{ask_ai_1.response}} gets the response from an Ask AI node named “ask_ai_1”.

---

​

Integration Concepts

​

Integration

A connection to an external service (Gmail, Slack, Shopify, etc.). Integrations require authentication and enable App Triggers and App Actions. CogniAgent supports 2,700+ integrations through Pipedream and built-in connectors. Learn more →

​

Pipedream

CogniAgent’s primary integration platform, providing access to 2,700+ pre-built app connections. Handles authentication, rate limiting, and API updates automatically.

​

MCP (Model Context Protocol)

A standard protocol for connecting AI models to external tools and data sources. CogniAgent supports MCP integrations for enhanced AI agent capabilities.

---

​

AI Concepts

​

AI Agent

An autonomous AI system that can perform multi-step tasks, use tools, and make decisions. Unlike simple AI prompts, agents can take actions and adapt based on results.

​

Human-in-the-Loop

A workflow pattern where automation pauses to get human input or approval before continuing. Ensures humans stay in control of important decisions. Example: AI drafts a response, but a human reviews and approves before sending.

​

Prompt

The text instruction sent to an AI model. Good prompts are clear, specific, and include relevant context.

---

​

Conversational AI Concepts

​

Skillset

A conversational AI agent that collects specific information through natural dialogue. Skillsets turn traditional forms into conversations — instead of filling out fields, users talk to an AI that guides them through providing information. Example: A “Lead Qualification” skillset collects company size, budget, and timeline through conversation rather than a form. Learn more →

​

Skillset Engine

The system that powers CogniAgent’s conversational AI capabilities. It manages conversation flow, decides how to respond to each message, tracks collected data, and handles edge cases like clarification requests and human escalation.

​

Conversation Tool

One of nine actions the Skillset Engine uses to manage dialogue:

• Accept answer — Save valid response, move to next question
• Reject answer — Ask for clarification
• Skip field — Skip optional field
• Update field — Change a previous answer
• Mark unknown — User doesn’t know the answer
• Confirm complete — Verify all data before finishing
• Transfer to human — Escalate to human agent
• End conversation — Wrap up the conversation
• Search knowledge — Look up information in the knowledge base

​

Form Field

A piece of information that a skillset collects. Each field has an ID, name, description, data type, and whether it’s required. The AI asks about fields conversationally rather than presenting them as a form.

​

Guardrails

Safety systems built into the Skillset Engine that protect conversations:

• Content safety checks
• Automatic escalation when users are frustrated
• Limits on clarification attempts
• Topic boundaries to keep conversations focused

​

Channel

A communication platform where conversations happen. CogniAgent supports:

• Email — Gmail, Microsoft Outlook
• Messaging — Slack, Microsoft Teams
• SMS — Text messages via Twilio
• WhatsApp — WhatsApp Business
• Web Widget — Embedded chat on your website

Conversations can span multiple channels — users can start on web chat and continue via email. Learn more →

---

​

Architecture Concepts

​

EDAA

Event-Driven Agentic Architecture — CogniAgent’s workflow orchestration system. EDAA manages how workflows execute, coordinates between different services, and handles actions triggered by conversations.

---

​

Execution States