Real Value Acceleration Program home

What can you build?

Design a new AI application or add a capability to an existing system.

What the creator can design

Bring the first task you want users to complete in a new or existing application. AI Agent Creator helps define that journey and its architecture. It may recommend a platform agent, custom application, explicit workflow, or a model call with a defined task.

The plugin designs the solution but does not implement or certify it. These examples are not customer results or deployment templates.

Application families

The products shown are examples. Discovery must verify product fit, connections, availability, and release status.

Knowledge assistants

Help users find permitted information and cite its source. Define source ownership, permissions, freshness, and what happens when evidence conflicts or is missing. A fixed lookup may not need an agent loop.

Example options
Azure AI SearchSearch and retrieval for an application-owned assistant.
Microsoft Copilot StudioA platform-managed agent grounded in configured knowledge sources.
Answer with authorized evidence The assistant searches sources the user may access. It cites evidence in its answer and reports missing or conflicting evidence. Ask a question Search permitted sourcesApply the user's permissions Answer with citations
If evidence is missing or conflicting, say so. Retrieval alone does not require an agent loop.

Agents that use business tools

Investigate a task and prepare or perform approved operations. Define read-only access, approval boundaries, authorization, and retry behavior that prevents duplicate business actions.

Example options
Azure Logic AppsConnector-based business workflows.
Foundry Agent ServiceAn agent that selects configured tools. Enforce business authorization separately.
Propose an action before approval The assistant investigates a maintenance request and proposes a work order. A manager approves or rejects it before any operation. The system must authorize the operation before acting. Receive a request Investigate with allowed tools Propose a work order Manager reviews the proposalApprove or reject
The system must authorize each operation and prevent retries from repeating it. Proposing an action does not authorize it.

Document and media processing

Turn incoming material into structured results. Define the output schema, review threshold, correction path, and downstream handoff. This may be a fixed pipeline with no conversational interface.

Example options
Azure Document IntelligencePrebuilt or custom extraction models for known document types.
Azure Content UnderstandingAnalyzers for unstructured documents or mixed-media inputs.
Turn a document into a reviewed record The pipeline classifies a document and extracts its fields. A reviewer checks uncertain fields before the pipeline publishes the record. Receive a document Classify it and extract fields Review uncertain fieldsApply the agreed threshold Publish the structured record
The output must match the agreed schema. Send reviewer corrections to the downstream system.

Voice and audiovisual experiences

Use speech or audiovisual presentation when the task requires it. Define interruptions, corrections, exit paths, privacy, and accessibility. An avatar or generated video alone does not require an agent.

Example options
Azure SpeechCompose speech recognition and synthesis with your application logic.
Voice Live APIA speech-to-speech API within Azure Speech, rather than a separate product.
Confirm actions separately from voice replies The assistant interprets speech and responds by voice. Consequential actions require a separate confirmation step. Listen to the user Interpret the request Respond by voice Confirm before taking action
The dashed path shows where consequential actions need confirmation. Let users interrupt the assistant or correct what it understood.

Background workflows

Respond to events or process jobs without a chat interface. Define who owns job state, how work resumes, which branches stay fixed, and when investigation stops.

Example options
Azure Logic AppsConnector-based workflows with explicit steps.
Azure Functions with Durable FunctionsCode-defined workflows with persisted state and recovery.
Save job state while waiting for approval An event starts a job that gathers evidence. The job saves its state while it waits for approval. It resumes only after approval. An event starts a job Gather evidence Wait for the owner's approvalSave the job's state Resume after approval
The job can wait without an open chat. Stop the proposed action if the owner rejects it. Define how the job recovers from failures.

Coordinated specialist agents

Split responsibilities only when one agent cannot meet the requirement reliably. Define handoffs, access boundaries, shared state, conflict handling, and failure behavior. Coordination adds overhead. Microsoft's orchestration guidance recommends the lowest complexity that meets the requirement.

Example options
Foundry Agent ServiceA managed agent runtime. Verify support for the selected coordination pattern.
Microsoft Agent FrameworkCode-defined orchestration. Choose hosting separately, including Foundry when appropriate.
Coordinate specialists with separate permissions A coordinator assigns work to specialists with separate permissions. It checks their results before submitting a proposal for approval. Coordinate the task InvestigatorRead evidence Action agentPropose work Check and submit the proposal
This example gives each specialist separate tools and permissions. The coordinator must resolve conflicting results. Consequential actions need approval.

Capabilities you can combine

Families can overlap. Add persistent memory, multiple agents, or personalization only when the journey needs them. Define ownership, permissions, provenance, expiry, and deletion.

Choose an architecture during discovery

You do not need to choose a platform before discovery. Bring the outcome and existing constraints. The creator compares existing capabilities with custom execution against the first journey's requirements. Microsoft's technology planning guidance starts by checking whether a ready-to-use solution meets the need.

Choose the user channel separately from the runtime. Keep knowledge access and permission to perform actions distinct. The architecture review must verify product fit and proposed connections, and name owners for unresolved checks.

Describe your first journey

Tell the creator who will use the application and what their first task is:

/ai-agent-creator Design a maintenance assistant for property managers. Help them investigate
resident requests and prepare a work order for approval. Reuse our existing
identity and service system. Compare an agent with a simpler workflow before
recommending the architecture.

Set up your application workspace, then bring your own idea. If you are extending a system, prepare its context.

Review and approve the architecture package before starting a separate implementation session. Architecture approval does not authorize implementation or deployment.