Core Concepts
Agent
Agent
An autonomous AI worker that executes your business workflows. Agents understand natural language instructions, process documents, and complete tasks automatically.Example: A Quote Generation Agent that creates customized quotes based on customer requirements.
Worksheet
Worksheet
A full-featured spreadsheet where your agent reads input data and writes output. Worksheets are powered by SpreadJS and support all standard Excel features (formulas, charts, formatting, etc.).Example: A price list where your agent looks up product prices and writes generated quotes.
Sources
Sources
Documents, files, and links that provide context to your agents. Sources help agents make informed decisions by giving them access to company policies, examples, and reference materials.Example: Uploading past quote PDFs so your agent can match your formatting style.
Run
Run
A single execution of your agent’s workflow. Each time your agent performs its task, that’s a run. Runs have a status (Running, Completed, Failed, Needs Review) and include detailed logs.Example: When your Quote Generation Agent processes 10 customer requests, that’s one run.
Workspace
Workspace
A container for your team’s agents, worksheets, sources, and integrations. Workspaces can be personal (individual use) or organizational (team collaboration).Example: “Acme Corp Sales” workspace containing all quote generation and CRM automation agents.
Integration
Integration
A connection to an external service that your agent can interact with. Integrations enable agents to send emails, update CRMs, post to Slack, query databases, and more.Example: Gmail integration allowing your agent to send quotes via email.
Trigger
Trigger
The mechanism that activates your agent. Triggers can be time-based (schedule), event-based (webhook, new data), manual (click Run button), or API-based (programmatic).Example: “Run every day at 9 AM” or “Run when a new row is added to the worksheet.”
Technical Terms
RAG (Retrieval-Augmented Generation)
RAG (Retrieval-Augmented Generation)
A technique where the AI retrieves relevant information from your documents before generating a response. This allows agents to reference specific pages, sections, and data points from your sources.How it works:
- Your documents are indexed when uploaded
- When the agent runs, it searches for relevant sections
- Retrieved content is used to inform the agent’s decisions
- The agent cites specific sources and page numbers
Bounding Box Citation
Bounding Box Citation
The exact location within a PDF where information was found. Bounding boxes show the specific paragraph, table, or section the agent referenced, highlighted with a rectangular box.Why it matters: You can verify the agent didn’t hallucinate by seeing exactly what it read.
OCR (Optical Character Recognition)
OCR (Optical Character Recognition)
Technology that extracts text from images and scanned PDFs. Decisional automatically applies OCR to scanned documents so agents can read them.Best practices:
- Use 300 DPI or higher for scans
- Ensure good contrast (black text on white background)
- Avoid skewed or rotated pages
SpreadJS
SpreadJS
The professional-grade spreadsheet engine powering Decisional worksheets. SpreadJS provides full Excel compatibility including formulas, charts, conditional formatting, and more.
Agentic Reasoning
Agentic Reasoning
The ability of AI agents to think through problems, handle edge cases, and adapt to new situations - not just follow rigid rules. Agentic reasoning allows Decisional agents to handle complex workflows that traditional automation can’t.Example: If a product is out of stock, the agent suggests alternatives instead of failing.
Semantic Search
Semantic Search
Search based on meaning, not just keywords. When your agent searches sources, it finds conceptually relevant information even if exact words don’t match.Example: Searching for “price” will also find “cost”, “fee”, “rate”, etc.
Workflow Terms
Input Data
Input Data
The data your agent receives to process. This typically comes from worksheet rows, API calls, email triggers, or form submissions.Example: Customer name, product, and quantity from a “Quote Requests” spreadsheet.
Output Data
Output Data
The results your agent produces. This is written to worksheets, sent via integrations (email, Slack), or returned via API.Example: Generated quote with calculated prices, discounts, and total.
Instructions
Instructions
Natural language description of what your agent should do. Instructions are written like you’re training a new team member.Example:
Human-in-the-Loop
Human-in-the-Loop
A workflow pattern where the agent pauses for manual review before proceeding. Useful for high-stakes decisions.Example: “If quote exceeds $50,000, flag for manager approval before sending.”
Batch Processing
Batch Processing
Processing multiple items in a single run. Agents can process entire worksheets or lists of items efficiently.Example: Generate 100 quotes from 100 customer requests in one run.
Error Handling
Error Handling
How your agent responds to problems. Good agents log errors, continue processing remaining items, and notify you of issues.Example: If one invoice fails to process, log it to an “Errors” sheet and continue with the rest.
Data & Storage Terms
Sheet
Sheet
A single tab within a worksheet (workbook). You can have multiple sheets for organizing data (e.g., “Requests”, “Outputs”, “Errors”, “Reference Data”).
Cell
Cell
A single box in a spreadsheet, identified by column letter and row number (e.g., A1, B5, Z100).
Formula
Formula
An Excel-style calculation (e.g.,
=SUM(A1:A10), =VLOOKUP(B2, Prices!A:B, 2, FALSE)). Agents understand and respect formulas.Named Range
Named Range
A friendly name for a group of cells (e.g., “CustomerNames” for cells B2:B100). Makes formulas more readable.
Data Validation
Data Validation
Rules that constrain what can be entered in cells (e.g., dropdown lists, number ranges, date ranges). Helps ensure data quality.
Conditional Formatting
Conditional Formatting
Automatic cell formatting based on values (e.g., highlight cells red if value > 1000). Useful for visual alerts.
Integration & API Terms
OAuth
OAuth
A secure authorization method used by integrations. When you connect Gmail, HubSpot, etc., you’re using OAuth to grant Decisional permission to access those services on your behalf.
Webhook
Webhook
A callback URL that triggers your agent when an external event occurs. Webhooks enable real-time automation.Example: When a form is submitted on your website, it sends a webhook to trigger your agent.
API (Application Programming Interface)
API (Application Programming Interface)
A way for software to talk to other software. Decisional provides an API for programmatic access, and agents can call external APIs.
API Key
API Key
A secret token that authenticates API requests. Keep your API keys secure - they grant full access to your workspace.
Endpoint
Endpoint
A specific API URL that performs an action (e.g.,
/agents/create, /runs/list). Each endpoint has a specific purpose.REST API
REST API
A standard way of building APIs using HTTP methods (GET, POST, PUT, DELETE). Decisional’s API is RESTful.
Status & States
Running
Running
The agent is currently executing. You can see real-time progress in the run logs.
Completed
Completed
The agent finished successfully. All outputs have been written and actions taken.
Failed
Failed
The agent encountered an error and couldn’t complete. Check the run logs for details.
Needs Review
Needs Review
The agent is waiting for human approval before proceeding (human-in-the-loop pattern).
Pending
Pending
The item is waiting to be processed (e.g., a worksheet row with Status = “Pending”).
Indexed
Indexed
A source has been processed and is ready for the agent to search. Sources must be indexed before agents can use them.
Processing
Processing
A source is currently being indexed. Wait for this to complete before running your agent.
Roles & Permissions
Owner
Owner
The workspace creator. Has full control including billing, deleting workspace, and managing all resources. Each workspace has exactly one owner.
Admin
Admin
Can manage all agents, invite team members, and configure integrations. Cannot access billing or delete workspace.
Editor
Editor
Can create, edit, and run agents. Cannot invite team members or delete workspace.
Viewer
Viewer
Read-only access. Can view agents and worksheets, run agents, but cannot create or edit anything.
File Formats
CSV (Comma-Separated Values)
CSV (Comma-Separated Values)
Simple text format where each line is a row and commas separate columns. No formatting, formulas, or multiple sheets.When to use: Basic data export/import, no formatting needed
XLSX (Excel Workbook)
XLSX (Excel Workbook)
Modern Excel format supporting multiple sheets, formulas, charts, formatting, and more.When to use: Full-featured spreadsheets with formulas and formatting
XLS (Legacy Excel)
XLS (Legacy Excel)
Older Excel format (pre-2007). Still supported but XLSX is preferred.
PDF (Portable Document Format)
PDF (Portable Document Format)
Static document format. Decisional can extract text and data from PDFs using RAG and OCR.Best for: Contracts, invoices, reports, policies
DOCX (Word Document)
DOCX (Word Document)
Microsoft Word format. Good for policies, procedures, and template documents.
Quick Reference
| Term | Category | Definition |
|---|---|---|
| Agent | Core | Autonomous AI worker |
| Worksheet | Core | Spreadsheet data layer |
| Source | Core | Context document/file |
| Run | Core | Single execution |
| RAG | Technical | Retrieval-Augmented Generation |
| OCR | Technical | Optical Character Recognition |
| Trigger | Workflow | What activates the agent |
| Integration | API | Connected external service |
| Owner | Role | Full workspace control |
| Indexed | Status | Source ready to use |