Fusion AI

Glossary

63 terms. Each links to the lesson that teaches it.

Platform & tooling

Oracle AI Agent Studio

25B

Fusion's low-code builder for agents, workflow agents, agent teams, tools, topics, business objects and agentic apps. Included with Fusion, runs in each pod and inherits Fusion security.

Lesson

Fusion AI Studio (CLI)

26C

Oracle's pro-code tooling: a CLI skill that gives coding assistants Fusion context, plus a VS Code extension. Artifacts live as files in Git; fetch, validate, test and save drafts from code.

Lesson

ATLAS

Aug 2026

Agentic Testing and Lifecycle Automation Suite in Fusion AI Studio. Records live runs and replays them as workflow, conversation and app tests with path assertions and an LLM judge.

Lesson

Oracle AI Agent Marketplace

Oct 2025

Where partners publish agents and agentic apps for Fusion customers, approved by Oracle per quarterly release.

Seeded agents and apps

Agents, workflows, policies and apps Oracle ships with ORA_ codes. Duplicate and extend them; never edit in place, so quarterly updates still apply.

Pod and promotion

Each environment (dev, test, prod) is a pod. Artifacts move by export, import and publish, and imports carry no secrets.

Lesson

Workflow agents

Workflow agent

25D

An agent built as a graph of typed nodes, saved as a .wf file. Deterministic steps do the volume and rules; model steps do the judgement. The default unit of build.

Lesson

Agent team

25C

A supervisor classifies the request and routes it to worker agents, typically a read-only query agent and a separate execution agent that holds the write tools.

Lesson

Node

One workflow step: AGENT, LLM, CODE, CONDITION, SWITCH, PARALLEL, LOOP, WHILE, WAIT, HUMAN, POLICY, WORKFLOW and tool nodes. Display names must be unique.

Lesson

AGENT node

A model that reasons over instructions, topics and tool schemas, calls tools and loops (up to maxInteractions, 1 to 20) until it can answer. Use it only when tools are attached.

Lesson

LLM node

One prompt in, one answer out, no tools. Cheaper and more predictable than an AGENT node: summaries, classification, drafting.

Lesson

CODE node

Sandboxed JavaScript that filters, joins, calculates and caps rows. Reports 0 tokens; output lands at $output.result. The most-used node type in production workflows.

Lesson

CONDITION and SWITCH

Deterministic routing. CONDITION has true and false outcomes; SWITCH has one outcome per case, and its fallback branch is labelled default.

Lesson

$context

Everything a node can read: $nodes (other nodes' outputs), $variables, $system, $app, $triggers, $user, $error. Written as {{$context.$nodes.X.$output}} in inputs and prompts.

Lesson

WORKFLOW node (child)

Runs another published workflow as a step. A failed child leaves no output; a child that pauses on HUMAN pauses the parent.

Lesson

errorNodeId

The node a run jumps to when this node fails. The handler reads $context.$error.$errorMessage. Failure is never an edge.

Lesson

Triggers, rules & people

Trigger

What starts a workflow: REST (chat, apps, API), SCHEDULE (as a service account), EMAIL (an inbound mailbox), EVENTS/signals, or CAPABILITY (Fusion Claw).

Lesson

Signals

26C

Events one workflow publishes and others subscribe to, with retries and backoff. Fusion business events still arrive through Oracle Integration.

Lesson

Topic

A reusable set of business rules and instructions carried into an agent's context on every call.

Policy Store and policy

A policy is generated from an SOP document: an LLM writes deterministic JavaScript functions with the rules as literals, plus test cases. Templates lock names and return shapes.

Lesson

POLICY node

Runs a policy function with no LLM call: same input, same decision. Oracle's AP Payment Exceptions Advisor uses 12 of them.

Lesson

HUMAN node

Pauses a run for a person over CHAT, EMAIL or APPROVAL_PROCESS (26C). Its only edge is success, and a timeout takes it too, with $output = TIMEDOUT.

Lesson

Approval process

26C

A Fusion approval definition AI Studio workflows can route to: rules on payload attributes, approvers by user, management hierarchy or representative, notified by email, SMS, push or bell.

Lesson

Confirmation gate

practitioner pattern

A graph pattern: CODE classifies the reply and a CONDITION lets only a real confirmation reach the execute agent. A prompt-only "confirm first" failed 3 runs in 4.

Lesson

Tools & data

Tool

A capability an agent can call, described by a schema the model reads. Every attached tool's schema rides in context on every call.

Lesson

Business object (BO)

A Fusion REST resource registered in AI Agent Studio, such as purchaseOrders, workOrders or invoices, with fields, child resources and actions.

Lesson

Business Object tool

Reads and writes business objects over Fusion REST as the signed-in user, so Fusion roles and data security decide the rows.

Lesson

REST tool

Calls a service outside the pod over HTTPS: Oracle Integration, ORDS, OTM, third parties. Runs as the stored credential, not the user.

Lesson

MCP tool

26A

Connects to an MCP server, lists its tools (tools/list) and calls one (tools/call). One MCP tool brings the whole server's tool set into context.

Lesson

Document tool (RAG)

Retrieves relevant chunks of uploaded playbooks and policies, so answers follow your own rules.

Lesson

Connectors

26C

Content connectors bring SharePoint files and crawled sites into retrieval; client connectors put agents into Teams and Slack.

Utility tools

Email, deep link, user session, calculator and web search tools, plus the seeded multi-file processor for attachments.

Agentic apps

Agentic application

A Fusion workspace where several workflow agents share context around one process: panels, priority actions, a summary, communications and chat.

Lesson

Panel

A tile backed by a workflow agent and rendered at the InitDisplay stage, from <oraInfoDisplay> widget blocks. Bare JSON shows as raw text.

Lesson

App stage

Why the app called the workflow, in $context.$app.$OraMessageHint: InitDisplay, InitActions, Summary, Query, InvokeAction, InitCommunications and more.

Lesson

Priority actions

Ranked <oraInsight> actions built at InitActions from panels that set includeInActions; clicking one runs ora.Invoke("actionN", …).

Lesson

Ask box (queryAgent)

Chat inside the app. The Ask box and every action click go to the app's single queryAgent, running its published version; a panel's own chat goes to that panel's workflow.

Lesson

App context

Runtime values in $OraAppContext, such as a plant or business unit, that every panel reads, so users can switch organisation without a second app.

Lesson

Agent API (invokeAsync)

25C

The older way to call an agent from outside Fusion: POST invokeAsync returns a job id, then poll its status until COMPLETE or ERROR. Oracle is replacing it with A2A, so build new callers on A2A.

Lesson

Fusion Claw & Companion

Fusion Claw

26D

Oracle's outcome engine inside agentic apps. A frontier model plans from the app's goals and capabilities, deterministic compute executes across Fusion data, and it re-plans until the outcome is reached.

Lesson

Outcome

26D

A goal set in the app's Priorities panel with a mode. Research returns a plan and changes nothing; Full Auto executes, inside your approvals. Outcomes can repeat.

Lesson

Autonomy settings

26D

Set in App Settings once autonomous outcomes are enabled: goals, skills, capabilities, additional agents and example outcomes.

Lesson

Capability

26D

A workflow agent declared as something Claw may plan with, under Settings › Triggers › Capabilities in the workflow builder.

Lesson

Operating envelope and Trust Harness

26D

The envelope sets the data, processes, roles, permissions and limits; the Trust Harness checks every proposed action against it before it touches Fusion.

Lesson

Outcome Receipt

26D

The audit record of every Claw run: what was asked, what was done, which actions were governed and what was handed off.

Lesson

Fusion Companion

AI World 2026

One layer that understands a user's goal and selects the right Fusion capability: an agentic app with Claw, an agent, or a business action. Context and authority travel with the work.

Lesson

Fusion Agentic Home

AI World 2026

The Fusion-native front door to Companion, with Work, Research and Full Auto modes, and # to insert business objects.

Lesson

Governance, quality & cost

Role-based access

Every interactive call carries the running user's Fusion token, so the agent is bound by that user's roles and data security. Fusion makes the final authorisation decision.

Lesson

Credentials

26C

The Credentials tab: bring-your-own model keys, email accounts (inbound or approver) and storage for chat uploads. REST and MCP auth is set on each tool.

Lesson

Guardrails

26A

Scans of requests and responses for prompt injection, toxic content and personal data, inside Oracle's defense-in-depth.

Lesson

METRO

25D

Monitoring (or Metrics), Evaluation, Tracing, Reporting and Observability: the Monitoring and Evaluation tab. Errors, latency, tokens, AI Units and a trace of every run.

Lesson

Evaluation (LLM as a judge)

25D

Scores answers from an evaluation set against reference answers for correctness, groundedness and relevance, with a score and an explanation.

Lesson

AI Units (AU)

Oracle's meter. Premium models: 5 AU per started 10K tokens per node. Basic: 0. A generated document: 10 or 20. 1 AU lists at USD 0.01.

Lesson

Premium, Basic and BYO models

Premium: OpenAI models on a zero-retention endpoint outside Oracle. Basic: GPT-OSS-120B on OCI, data stays in Oracle Cloud. BYO: your key and endpoint, metered at multipliers.

Lesson

The wider Oracle stack

Oracle Integration AI agents

OIC 25.10

Agents built in an Oracle Integration project's AI tab, using registered integrations as their tools. Arrived in OIC 25.10 with projects as MCP servers and human-in-the-loop.

Lesson

OIC project as an MCP server

OIC 25.10

An Oracle Integration project exposed at /mcp-server/v1/projects/<project>/mcp: tools/list returns its registered integrations, tools/call runs one, as the OAuth client rather than the user.

Lesson

A2A (Agent2Agent)

26C

An open protocol for agents to discover and call each other: an agent card describes an agent, and work moves as tasks and messages. Fusion exposes published agents through what Oracle calls a pragmatic subset of it, for other agents and for apps and integrations, as it replaces invokeAsync.

Lesson

FSCR

AI World 2026

Fusion Setup and Configuration Registry: a public Oracle repository of 1,124 skills that let a coding agent map requirements to setup tasks, build a run book and load setup data after approval. Sample code, not a supported product.

Lesson

Oracle AI Success Navigator

AI World 2026

Oracle's implementation platform (formerly Cloud Success Navigator). Its agents cover discovery, design, configuration (built on FSCR), testing, integration and innovation.

Lesson

Visual Builder (VBCS)

8 Oct 2026

From 8 Oct 2026, customers without a Visual Builder instance can no longer provision one. Existing instances continue, with no end-of-life date; Visual Builder Studio for extending Fusion pages is unaffected.

Lesson

APEX AI Agents

APEX 26.1

In APEX 26.1 (GA May 2026), AI Agents with AI Tools and tool guardrails, natural-language page creation and APEXlang application files. APEX connects to a model you choose; it ships none.

Lesson

Oracle AI Data Platform

GA Oct 2025

An open lakehouse with a governed catalog (supporting A2A and MCP), an Agent Hub and one workbench for data and AI teams. Fusion Data Intelligence data is available in it.

Lesson

Private Agent Factory

Mar 2026

Oracle AI Database 26ai's no-code agent builder that runs as a container next to your data, in the cloud or on-premises, with prebuilt data agents, MCP tools and A2A.

Lesson

Independent course, not an Oracle product. Based on Oracle documentation, release notes and hands-on builds; check Oracle's documentation for your release.