RevoEngine Documentation

Tools and skills solve different parts of an AI task:

A tool performs an operation: search, read, compare, validate, execute, write, or call an attached plugin.
A skill is focused guidance for how to solve a class of problems with the available tools.
A plugin adds tenant-specific tools, skills, MCP servers, or a package of related capabilities.

A skill never grants permission by itself. Identity, policy, target access, and approval requirements still determine whether an operation can execute.

Platform-aware capability families

Exact availability depends on the current identity, target, Agent or thread configuration, and instance policy.

Capability	What it does	Typical safety
Reference search	Finds authorized components, endpoints, databases, storage entries, Agents, jobs, and other platform objects	Read-only
Describe	Loads the current contract and allowed next operations for an exact target	Read-only
Snapshot history, get, and diff	Reads historical versions and compares changes	Read-only
Code search and describe	Finds implementation references and loads exact runtime or library declarations	Read-only
Dependency graph	Shows relationships and likely blast radius	Read-only
Operations investigation	Reads job history, logs, webhooks, events, and correlated failures	Read-only
Safe code execution	Runs bounded validation, calculation, or debug probes	Execute, restricted
Platform apply	Performs an admitted Platform API read or mutation against an exact contract	Approval depends on operation
Storage	Reads or writes managed files within an authorized scope	Reads are safe; writes depend on scope and policy
Public web research	Searches and loads current public information when enabled	External read
Plugins and integrations	Invokes an attached, governed business or external capability	Determined by the operation and plugin policy
Collaboration	Requests clarification, delivers an approved message, or hands work to an eligible Agent	Identity, target, and action policy apply
Durable knowledge	Saves concise reusable context within an allowed memory scope	Memory ownership and policy apply

These families describe product capabilities, not unconditional permissions or a guarantee that every capability is available in every thread.

Breadth without overclaiming

RevoEngine can combine model reasoning with live, authorized application context, execution evidence, generated runtime types, persistent workspace artifacts, controlled web research, and instance-specific plugins. This makes it broad for the lifecycle of a RevoEngine application: design, build, debug, operate, and improve. It is not positioned as a universal, unrestricted computer operator. It deliberately does not bypass tenant roles, Secret masking, target ACLs, deployment state, or review controls. The right measure of its strength is the quality of a verified outcome in the permitted scope—not the size of a capability catalog.

Reference tokens

The Assistant uses stable references to keep a name tied to the correct platform object and, where needed, a specific version. In the UI these appear as readable pills rather than raw identifiers. References support safer follow-ups:

Compare this component with its previous version and list affected endpoints.

Use the endpoint we discussed above, but inspect the currently active component version before proposing a fix.

Versioned references are especially useful for audit, rollback analysis, and changes made while a thread is still open.

Skill libraries

Skills provide reviewed guidance for recurring work without changing the underlying permission model. Organizations can use built-in and approved plugin skills to standardize how work is scoped, validated, documented, and handed off. Skill areas can include:

Application architecture

Components, dependencies, low-code review, shared libraries, and schema evolution.

Data

Database configuration, row reads, controlled mutations, and query patterns.

Endpoints and runtime

Endpoint contracts, validation, execution, and managed runtime behavior.

Automation and operations

Jobs, schedules, events, webhooks, execution history, and incident investigation.

Storage and identity

Files, upload flows, secrets, users, groups, roles, and preferences.

Agent capabilities

Plugin creation, tool composition, handoffs, memory, and workspace-aware execution.

Authorization and approval

Before an operation executes, RevoEngine evaluates:

Is the capability enabled for this runtime and instance?
Is it permitted for the current thread or Agent?
Can the current identity access the target?
Is the call read-only, write-capable, destructive, executable, or external?
Does the capability or plugin policy require approval?
Are the arguments valid for the current operation contract?

Read-only work can normally proceed without approval. A capability category alone does not determine safety: a bounded validation may be allowed while code that attempts a side effect is blocked or requires review.

Activity and artifacts

The execution timeline can show relevant operations, approval requests, results, and retained artifacts. RevoEngine applies masking, access control, and retention policy to this evidence. Secrets and private platform implementation are not included in normal shared-thread output.

Ask for capability-aware work

You usually do not need to name an implementation-specific operation. State the outcome and evidence requirement:

Find the exact endpoint, inspect its active component, and show the dependency impact. Do not make changes.

Validate the proposed query with a bounded read. Do not export the database.

Use the attached CRM plugin to read the account. Ask for approval before any external update.

Plugins

Add governed tenant-specific and external capabilities.

Approvals and plans

Control when tools pause before side effects.

​Platform-aware capability families

​Breadth without overclaiming

​Reference tokens

​Skill libraries