Projects

What is a Project?

A Project is a complete, deployable AI system in Triform. It's a repository that holds all the components (Agents, Flows, Actions) needed to accomplish a specific goal.

Project structure

Projects contain:

Actions — Python functions for deterministic logicAgents — LLM-powered components with toolsFlows — Orchestration graphs connecting componentsSub-Projects — Nested Projects for modularityVariables — Configuration accessible to all componentsTriggers — What starts executions

Example structure:

Project: Customer Support System├── Flows│   ├── ticket_triage│   └── response_generation├── Agents│   ├── sentiment_analyzer│   └── response_writer├── Actions│   ├── fetch_ticket│   ├── update_status│   └── send_notification└── Project Variables    ├── API_KEYS    └── CONFIG

Creating Projects

Via UI

1. Click Home in Top Bar
2. Click New Project
3. Name it and add a description
4. Click Create

Via Triton

Ask: "Create a new Project for processing customer feedback"

Triton will create the structure, ask clarifying questions, and suggest initial components.

Working with Projects

Opening and navigating

1. Navigate to Home
2. Click your Project to open on Canvas
3. Double-click nodes to drill into Flows, Agents, or Actions
4. Use breadcrumbs at top to track your location

Building in a Project

Via Triton:

• "Add a validation Flow to this Project"
• "Create an Action that calls the Stripe API"

Via UI:

• Right-click Canvas → Add Node
• Choose component type, configure, and connect

Project lifecycle

1. Design — Plan inputs, outputs, and data flow2. Build — Create Actions, configure Agents, build Flows3. Integrate — Wire components together4. Test — Validate with sample payloads5. Deploy — Push to staging, then production6. Monitor — Track execution success rate and performance7. Iterate — Add features and optimize

Common patterns

Request-Response API

Input → Validate → Process → Format → Output

Use case: API endpoints, data transformations

Multi-stage pipeline

Input → Extract → Transform → Load → Output

Use case: ETL, data processing, content generation

Agent with tools

Input (query) → Agent (with tools) → Output (response)  Tools: search_database, call_api, send_email

Use case: Conversational interfaces, decision support

Parallel processing

Input → Split → [Process A, B, C] → Merge → Output

Use case: High-volume processing, independent tasks

Best practices

Single responsibility — Each Project should have one clear purpose

Self-contained — Minimize dependencies on other Projects

Well-documented — Clear descriptions for all components

Tested — Save example payloads for regression testing

Monitored — Track success rates and performance

Project scope guidelines

Too small ❌Project: "Uppercase a string" → Should be an Action

Just right ✅Project: "User Onboarding" → Includes validation, account creation, welcome email, setup

Too large ❌Project: "Entire Customer Platform" → Split into multiple Projects: Support, Billing, Notifications

Rule of thumb: If you can't explain what the Project does in one sentence, it's too large.

Troubleshooting

Project won't deployCheck all components are configured, Project Variables are set, no circular dependencies

Execution fails in Project but components work individuallyCheck connections, field mappings, and data flow

Project is slowProfile execution, identify bottlenecks, add parallel processing or caching

Can't find my ProjectCheck filters, search by name, verify you're in the right Organization

Next steps

See Agents, Flows, Actions, and Build a New Project.