Agents
How agents work in Fruxon — anatomy, lifecycle, and the building blocks
An agent in Fruxon is a configured AI workflow with everything attached: prompts, steps, tools, knowledge, AI providers, memory, and revision history. Agents range from a single LLM call to multi-step orchestrators that branch, loop, call sub-agents, and escalate to humans.
Anatomy of an agent
| Piece | What it is |
|---|---|
| Flow | The graph of steps you build in Studio. |
| Parameters | Typed inputs the agent accepts at run time. |
| AI Providers | Which LLMs the steps use. Mix freely across steps. |
| Tools | What the agent can do — call APIs, query DBs, run code, hand off to sub-agents. |
| Knowledge Base | Documents and data sources retrieved at runtime. |
| Memory | Persistent facts the agent reads and writes. |
| Connectors | Channels (Slack, Teams, etc.) that can deliver the agent. |
| Revisions | Immutable snapshots — every save is recorded. |
| Budgets | Monthly cost caps and alert thresholds. |
The agent lifecycle
- Create — name, type, description.
- Build — design the flow in Studio.
- Equip — wire AI providers, tools, knowledge, memory.
- Test — run interactively with sample inputs (Testing).
- Evaluate — score candidate revisions against a golden dataset (Evaluations).
- Deploy — promote a revision to production (Versioning).
- Connect — add API callers, connectors, or sub-agent callers.
- Operate — watch traces, review conversations, manage costs.
Agent types
The type field is a label that helps organize agents and provides sensible defaults — it doesn't restrict capability. Pick whichever fits.
- Chat — multi-turn conversational agents (support, Q&A, copilots).
- Summarization — turn long content into briefings or digests.
- Recommendation — score, rank, or suggest based on inputs.
- Analyzer — process data and generate insights.
- Other — anything else.
Any type can have any tools, any flow shape, and any number of steps. Type is metadata, not a runtime gate.
What's in this section
Agent Studio
The visual canvas where every agent is built.
Creating Agents
Step-by-step walkthrough of a fresh agent.
AI Providers
Connect OpenAI, Anthropic, Google, Bedrock, and more.
Tools & Skills
Give agents abilities — APIs, sub-agents, code, memory.
Sub-agents
Compose agents as reusable building blocks.
Memory
Persistent facts across conversations.
Sessions
Multi-turn state and context-window management.
Copilot
The in-Studio AI assistant that helps you build agents.
Testing
Iterate quickly with the built-in test runner.
Cost & Budgets
Per-agent budgets, thresholds, and pricing visibility.