Oracle’s been moving quickly with its agentic finance capabilities, and the Payables Agent is one of the more practical outcomes so far. If you’re looking after accounts payable or running a shared services function, it’s worth taking a closer look at what it can do and what’s involved in getting up and running.
The Payables Agent is focused on the day-to-day reality of accounts payable, helping with invoice intake, compliance and control. It works to take invoices from wherever they come in and move them through to payment-ready with as little manual handling as possible. It sits alongside a wider set of Oracle AI agents across Payments, Expenses, Ledger and Customer Payments, each one aimed at a specific finance outcome.
At the heart of it is Document IO, which handles invoice ingestion across different channels and formats. It routes everything through a consistent process and flags anything that needs a closer look, so exceptions can be picked up and dealt with quickly.
Document IO works a bit differently to traditional approaches. It reads the whole invoice rather than picking out individual fields, then extracts and maps the information straight into the right attributes in Oracle Fusion. It can handle different formats, multi-page documents and multiple languages without needing templates set up for each supplier, and you don’t have to change how invoices are sent in, as your existing email channels can stay as they are.
The Streams UI gives you a single place to keep on top of everything, bringing together all your active invoice streams. You can quickly see what’s coming in, what’s already been processed, and what needs attention. Out of the box, there are two streams available. The first covers invoice image documents, handling supplier invoices sent by email in different formats, across multiple pages and languages. The second is partner e-invoice integration, which connects to e-invoices via Thomson Reuters. That one does require a commercial agreement with Thomson Reuters to get started.
Converged streams bring your existing channels into the same view as well, including bulk uploads and manual entry. It means you get a single, consistent way of seeing and managing every invoice type in one place.
For suppliers with a consistent invoice layout and high volumes, document training makes things even smoother. You set the format up once, the system extracts the data using GenAI, you check and save it, and that format is then recognised going forward. After that, every invoice in the same layout is processed automatically, without the need to retrain.
All of that is handled automatically in the background, with policy-driven validation, anomaly detection, PO matching, approval routing and budget checks applied to every invoice. A full audit trail is maintained throughout. Anything that needs attention is surfaced in the Invoice List UI, giving you a single place to manage invoices, handle exceptions and respond to queries. It means your team can focus their time where it really matters, rather than working through everything manually.
So, how do you get started? The Document IO Agent is already switched on by default, so there’s nothing you need to enable. From there, it’s really about setting up three key areas: where your invoices are received, how your streams are connected into the Streams UI, and, for higher-volume suppliers, putting a bit of time into training the system to recognise their invoice formats.
The best way to approach it is to take things in stages. Start with getting your invoice ingestion set up, then bring in converged streams and training, and finally test and refine at scale across different formats and volumes.
Stepping back, this is really about making day-to-day accounts payable that bit easier. A lot of the routine work is taken care of in the background, so your team can spend more time on the things that genuinely need their input. If you’re already using Oracle Fusion, it’s definitely worth exploring what this could look like in your own environment and where it might take the pressure off your team.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines
Over the bank holiday weekend, with the heat driving me indoors, I opened up my Fusion demo environment and decided to try building my first Oracle Agentic Application. Within a few minutes, it was up and running. That is not marketing spin, it is genuinely how quick and straightforward the experience was. It also gave me a good reason to sit down and share what I found.
Officially, the Agentic Application Builder does not arrive until Release 26C. However, if you are already familiar with AI Agent Studio and have access to a non production pod, there is more than enough available today to start building something meaningful and to get a feel for where this is going. Over the weekend, I put together two applications. The first used one of Oracle’s out of the box prompts, and the second was based on a custom prompt I created with support from Microsoft Copilot. Both came together quickly, which is really the point.
Before getting into what I built, it is worth being clear on how this fits together architecturally. AI Agent Studio, which is included within your Fusion Applications subscription, will introduce the Agentic Application Builder in Release 26C. It provides a low code way to create and extend agentic applications directly within Fusion. What makes it different is the starting point. Rather than beginning with code or a process diagram, you simply describe the business outcome you want to achieve, and the builder identifies the right agents, creates the initial structure, and connects to your enterprise data. It is also important to understand the licensing model. While you can explore, test, and build in non production environments without any additional cost, a separate licence is required to deploy and run these agentic applications in production. This means there is nothing to stop you getting hands on now and understanding the art of the possible before making any investment decisions.
Applications built in this way run natively within Fusion Applications, using your existing business objects and data, and operating under Fusion’s role based security. That is worth pausing on, because it means you are not creating something separate or bolting on additional functionality. These agents are working within the same security and access model your users already rely on in their day to day roles.
The builder brings applications together using reusable agent teams. These can be provided by Oracle, developed by partners, or created in house to suit your own needs. Each team is designed to handle a specific role, and the builder assembles them into a single application that works towards a common business outcome.
For my first build, I started with one of Oracle’s out of the box example applications. From selecting the template to having a working framework in front of me took only a few minutes. The App Builder presents a range of example agentic applications from the outset, giving you something tangible to work from straight away. You can select one, use it as a foundation, adapt it to your needs, and build from there. In my case, I chose the Talent Review and Insights application.
The steps are: go to AI Agent Studio, open the Apps tab, select Add, enter the name, code, and description for your agentic app, and navigate to the App Builder. Select one of the example apps and you’re looking at a working framework almost immediately.
That speed was the first thing that stood out to me. The framework clearly sets out the agent teams involved, the different sections of the application, and how everything fits together. You are not faced with a blank canvas. Instead, you can immediately see which published workflow agent teams are available to include, and the structure gives you a clear sense of how the application will operate before you have made any changes.
What really caught my attention was the quality of the insights it produced. This is not a static report. The agents actively draw on the data in your environment and present findings in a way that is designed to prompt action, not just provide information. For an HR practitioner used to working with standard Talent Review dashboards, the difference in how those insights are surfaced is immediately noticeable.
The second build is the one I found most interesting, and it was just as quick to put together. I used Microsoft Copilot to help shape a detailed natural language prompt, then passed that into the App Builder through the Ask Oracle interface to generate a completely custom agentic application from scratch.
The prompt set out an application designed for Payroll Administrators, bringing everything into a single workspace to monitor payroll activity and improve processing accuracy. The aim was to give payroll teams a clear, action focused view of exceptions, anomalies, and key changes that need investigation before payroll is finalised. In practice, that means removing the need for administrators to piece together that picture across multiple pages and reports.
The App Builder works through three clear phases: intent, assembly, and refinement. You start by describing the business objective in plain language, the builder then suggests the most relevant agents and proposes an initial structure, and from there you refine the application through layout changes, naming, and added detail before publishing. The whole journey, from a simple prompt to a structured application framework, moves quickly. If anything takes time, it is shaping the prompt itself rather than waiting for the builder to respond.
What I found is that the quality of the prompt makes a real difference to what the builder produces. The prompt I created with Copilot was clear about the user persona, the business context, and the type of information needed, focusing on a Payroll Administrator working in a pre finalisation scenario and looking for exceptions, anomalies, and priority changes. The application that came back reflected that level of clarity. In many ways, it is no different to working with any AI tool. The prompt is the critical part. The clearer and more specific you are, the more useful and relevant the outcome will be.
For those looking to get familiar with the structure ahead of 26C, an agentic application is built from three core elements: agent teams, communications, and actions. Agent teams sit at the heart of it. Only published workflow agent teams that have been enabled for use in applications are available to select, which helps ensure consistency and control over how these applications are put together.
Communications allow the application to send emails and messages using predefined templates. These templates can take the form of PowerPoint, PDF, email, or simple text. For email templates, the agent can be given the ability to suggest recipients, generate a subject line, and complete sections of the content. For PDF and PowerPoint templates, the agent can generate titles and populate the content, helping to streamline how information is produced and shared.
Actions define what happens as the application runs, including where human approval is needed along the way. The flow itself is straightforward. A widget or user interface element triggers a command, that command determines which action to run, and the action then executes its steps in sequence. There is a good level of flexibility in how those steps are defined. You can keep an action visible in the interface after it has run, navigate users to another application, send a command to an agent, refresh what the agent is showing, or switch the application context. Taken together, these steps allow you to shape how the application behaves and how users interact with it.
Once built and tested, you publish the app. Users can then access it from the AI Agents page, reached via Me > Quick Actions > Show More > AI Agent Studio > AI Agents.
I realise I am starting to sound a bit like an Oracle advert, so it is worth being honest about the experience. In its current pre release state, not everything behaves as you would expect from a finished product. Some agent team options are not yet fully populated, and there are limits to how far you can test the end to end flow in a sandbox without complete data. That is to be expected at this stage.
What is clear, though, is the direction of travel. The App Builder is designed to enable functional consultants and technically minded administrators to create agent driven applications without writing code, and to do so quickly. Starting with natural language removes much of the usual barrier, building from reusable agent teams means you are not starting from scratch each time, and the inclusion of example templates means you can have something up and running in the time it takes to make a coffee. For organisations investing in the Fusion Agentic Apps Platform, this is where a great deal of tailored capability is likely to be developed over the coming releases.
If you have access to a non prod pod and want to get ahead of 26C, it is well worth spending some time in AI Agent Studio now. The core concepts you will be working with, including agent teams, sections, communications, and actions, are already in place and align with what will be available in the full release.
I will share a more detailed walkthrough once 26C is live and the full feature set is available. In the meantime, if you are interested in where this is heading, it is worth taking a look at my earlier write up on AI Agent Studio and what it means for Oracle Fusion HCM.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines
Oracle has been making a clear and increasingly consistent argument over the past few months: enterprise software has reached the limits of what a system of record can do. I’ve written before about the introduction of Agentic Applications at AI World London, and about the specific HCM applications that were announced alongside them. But there’s a broader story here that I haven’t fully explored yet, and it’s one that I think matters for every Fusion customer, not just those focused on HCM.
This post draws on the “Reinventing How Work Works” webinar, which stepped back from individual applications and made the architectural and commercial case for why the shift to agentic is happening, what it actually looks like in practice, and where Oracle is taking this next. If you’re trying to build internal momentum for agentic adoption, or if you’re trying to explain to a leadership team why this is different from previous AI announcements, this is the post to share.
The framing that Oracle used throughout this webinar is, I think, one of the clearest explanations of what has actually changed. Traditional enterprise systems, including Fusion as it has historically operated, are systems of record. They follow fixed rules, capture what happened, retrieve information when asked, and complete transactions. They document the business. What they don’t do is run the business.
Agentic Applications represent a move to what Oracle calls systems of outcomes. Rather than waiting for a person to interpret data and decide what to do next, a system of outcomes works toward objectives, makes things happen, solves problems, and achieves results. The underlying system of record doesn’t go away. The data, governance, approval hierarchies, role-based access control, and audit history are still there, and in Oracle’s case, they’re still the source of truth for every transaction. What changes is the layer operating on top of that foundation.
This architecture diagram is worth studying if you haven’t seen it. Agentic Applications sit in a new composable layer above the existing ERP, HCM, and CX transactional applications. That layer is powered by teams of AI agents coordinated through Oracle AI Agent Studio, drawing on the full enterprise data model, security model, and process history that already exists in Fusion. Beneath all of this, Oracle Cloud Infrastructure (OCI) provides the AI data platform, and a range of large language models (LLMs), including those from OpenAI, Cohere, Meta, Anthropic, xAI, and Google, are available depending on the task and preference.
Every Fusion Agentic Application is built around four core dynamic areas. Understanding these is useful when you’re evaluating a specific application or explaining the concept to stakeholders.
The first is the Advisor, which is the “Ask Oracle” conversational interface. This is where a user can ask natural language questions and get contextual, data-aware responses rather than navigating to a report. The second is the Information Summary, which provides an intelligent, prioritised view of what’s happening right now in that area of the business, surfaced automatically rather than requiring the user to run queries. The third is Priority Actions, a curated queue of recommended next steps that the agents have identified based on current conditions, risk signals, and business objectives. The fourth is Communications, which handles notifications, responses, and outbound actions within the appropriate governance boundaries.
These four areas appear consistently across all 22 applications, which is deliberate. Oracle’s position is that once a user understands the structure in one application, they can navigate any other agentic application without relearning the interface.
One of the most practically useful concepts introduced in this webinar is what Oracle calls the Autonomy Dial. It’s a spectrum with three positions, and it addresses one of the most common concerns I hear from customers and consultants: how much control do we give up?
At the “Human in the Loop” end, the agent assists and a person decides. The agent drafts, recommends, and prepares; the human reviews and approves. This builds trust, improves speed and consistency, and keeps people firmly in control. The business impact is described as immediate productivity gains.
In the middle is “Human in the Lead”, where the agent executes and a person monitors. The agent handles routine work and manages to policy; a person steps in for genuine exceptions. This scales output without adding headcount and frees teams for higher-value work. The impact here is scaled operations.
At the “Autonomous Execution” end, the agent drives and a person owns. End-to-end execution happens within policy, continuous real-time optimisation takes place, and human involvement is reserved for true exceptions. The impact is described as business transformation.
What I find compelling about this model is that it isn’t prescriptive. Oracle isn’t saying every organisation should start at one end or aim for the other. Each position on the dial represents a valid operating model depending on the process, the risk tolerance, and the maturity of the organisation. A payroll close process might comfortably sit at Human in the Lead. A workforce scheduling decision for a critical shift might warrant Human in the Loop until confidence is established. A high-volume procurement matching task might be a good candidate for Autonomous Execution relatively quickly.
My earlier posts covered the eight HCM applications in detail. The full announcement of 22 applications in releases 26B / 26C spans ERP/SCM, HCM, and CX, and it’s worth understanding the breadth of this, because it signals how Oracle is positioning agentic across the entire Fusion suite rather than as an HCM-specific capability.
On the ERP and SCM side, the applications include Design-to-Source Workspace, Product Readiness Workspace, Production Shift Operations Workspace, Sales Order Command Centre, Batch Process Manufacturing Workspace, Logistics Execution Command Centre, Maintenance Operations Workspace, Warehouse Operations Workspace, Cost Accounting Close Workspace, Sourcing Command Centre, Collectors Workspace, and Security Command Centre.
The Design-to-Source Workspace is a useful example of the transformation logic. Previously, product design and bill of materials work happened in separate systems. Sourcing relied on items entered manually. Negotiation delays accumulated when information was missing or unresolved. With the agentic application, product specifications translate automatically into qualified supplier lists, bills of materials are generated directly from CAD files, at-risk negotiations are flagged automatically, and bids are evaluated across cost, lead time, quality, and risk in a single view. The outcome is faster time to market and improved sourcing cycle times.
On the CX side, three applications have been announced: Cross-Sell Program Workspace, Contract Compliance Workspace, and Sales Command Centre. For CX teams, the Sales Command Centre in particular brings together the kind of deal health monitoring, risk flagging, and next-step recommendation that previously required significant manual analysis across multiple reports.
I’ve written in detail about Oracle AI Agent Studio in previous posts, but the webinar highlighted several new capabilities that are worth calling out specifically, because some of them genuinely change what’s possible for teams building custom agentic applications.
The most significant new addition is the Agentic App Builder, which is released in 26C. This is what Oracle describes as a “no-code agentic brain”: you describe your objective in natural language, the system explains and builds the workflow, generates agents and the underlying code automatically, and allows you to diagnose and fix issues in real time. In the demo, a user types a description of a sales opportunity health and risk management app, and within moments a structured agentic application is assembled from reusable agents, with a Deal Summary Agent, a Risk Agent, a Customer Insights Agent, and a Process Agent already in place and connected. It’s a significant step forward from the existing builder experience.
Alongside this, several other capabilities have been marked as new in the current release: Workflow Orchestration, Content Intelligence, Contextual Memory, Multi-Modal support, an Agent ROI Dashboard, and enhanced Security, Auditability, and Governance controls. Contextual Memory is worth paying attention to particularly, because it allows agents to retain information across interactions, which is what enables genuinely personalised, continuous support rather than stateless responses to each individual query.
The studio now also supports full interoperability through MCP (Model Context Protocol) and A2A (Agent-to-Agent) protocols, which means agents built in Fusion can exchange context with agents or tools running outside the Fusion estate, provided the appropriate governance controls are in place.
One thing the webinar made very clear is that Oracle isn’t building this alone. The Fusion AI ecosystem now includes 73,400 certified builders, 10,000 developers actively building agents, and over 100 pre-built agent templates in the AI Agent Marketplace, which is now open to all partners for submissions. Open standard support includes native MCP integration across connectors and an agent-to-agent registry within Oracle AI Agent Studio itself.
For customers, this matters because it means the pool of available agents and expertise is growing rapidly. You don’t need to build everything from scratch, and you don’t need to rely solely on Oracle to extend the platform. The open partner submission model for the marketplace is a meaningful shift, and it’s one that will accelerate the availability of domain-specific and industry-specific agents over the coming months.
The summary that Oracle closed with is a useful way to frame internal conversations: Fusion is moving from systems of record to systems of outcomes. Agentic Applications get work done. Oracle AI Agent Studio lets you build, deploy, and scale agents specific to your organisation. OCI AI Advantage runs it all securely at scale.
What I’d encourage any Fusion customer to take from this is that the window to start is now. The pricing model has already been simplified significantly (covered in my earlier post), the tooling to build and extend has matured substantially, and the evidence base from production deployments is solid. Starting with one application in one process area, positioned at Human in the Loop on the autonomy dial, is a low-risk, high-value entry point that builds organisational confidence while delivering measurable results.
If you’re thinking about where to start or how to make the case internally, I’m happy to talk it through. In the meantime, why not check out my earlier post on the HCM-specific Agentic Applications announced at AI World London? You can find it here. And if you missed the original announcement post covering the architecture, the maturity model, and the updated pricing, that’s a useful starting point too, and you can find it here.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines
I’ve written quite a bit recently about Oracle AI Agent Studio and what it can do at a high level, and those posts have led to some really valuable conversations. A question that keeps coming up, though, is a very practical one: “This all sounds great, but how does it actually fit into the rest of my technology landscape?” Closely followed by, “How do I build something that’s reliable and production‑ready, rather than just impressive in a demo?” This post is my attempt to answer both, drawing on the training content from the AI World partner sessions, which goes into a level of detail that genuinely changes how you think about building with AI Agent Studio, particularly when it comes to integration, robustness and real‑world use. I should say up front that this series is a little more technical than my usual blogs, but it feels important to share, because this is the detail that turns AI from an interesting idea into something you can confidently run and scale.
One announcement I haven’t covered yet is the invokeAsync REST API, introduced in 26A, which allows external applications to programmatically call published Agent Teams in Fusion, and this is a significant step forward for organisations where Fusion sits alongside other enterprise systems. It means those systems can now trigger Fusion AI agents directly, without a user ever needing to open the chat interface. The process works in two stages: an external application sends a POST request to the invoke endpoint, passing either a user prompt or structured data, and because AI agents may need time to reason or retrieve information, the call returns a job ID rather than an immediate response. That job ID is then used to poll a separate status endpoint, which returns the final output along with useful metadata such as status, conversation ID, trace ID and timing information. For development and testing, adding ?invocationMode=ADMIN to the status endpoint provides detailed debug output, including the full node execution trace, which is invaluable when you are building and troubleshooting. Authentication follows the standard OAuth 2.0 bearer token approach used across Fusion APIs, so if you are already familiar with OCI IAM and IDCS, there is nothing fundamentally new to configure.
For those looking for a more standardised integration approach, Oracle also introduced support for the A2A, or Agent‑to‑Agent, protocol in 26A. A2A allows a client to discover agents through a well‑known metadata endpoint, often referred to as the agent card, initiate a task by sending a message, and then poll for the result using the same job ID pattern. The agents search endpoint makes it possible to query for published agents by name, which is particularly useful when you are building orchestration layers that need to dynamically discover and delegate work to specialist agents. The agent card itself returns the agent’s capabilities and supported methods in a structured format, making it much easier to establish interoperability between Fusion agents and third‑party systems without relying on custom, point‑to‑point integrations.
The relationship between Fusion and the outside world does not just work in one direction. In 26A, Oracle introduced Data Source Applications within the Credentials tab of AI Agent Studio, allowing administrators to configure OAuth connections to non‑Fusion systems such as EPM Cloud, WMS, or any external application with a compatible identity provider. Once a Data Source Application is set up with the base URL, IDCS URL, client ID, scope and key pair, it becomes available as a selectable source when creating a Business Object using the resource type “Other Data Source Application”. This makes it much easier for AI agents to securely reach out to external systems, bringing data back into Fusion in a controlled and repeatable way rather than relying on custom or hard‑coded integrations.
At runtime, when a Business Object function within a workflow needs to call an external system, the platform simply uses the saved configuration to obtain an OAuth token and invoke the target API behind the scenes. From the workflow designer’s point of view, it behaves exactly like any other Business Object node, with no additional complexity to manage. This opens up some genuinely powerful patterns, such as an HCM Workflow Agent that validates a job requisition in Fusion, checks headcount or budget in EPM, and then writes the outcome back to a Fusion record, all within a single, governed automation that remains transparent, secure and easy to maintain.
This blog is the first in a short series of four, where I will walk through some of the latest and most important functionality in Oracle AI Agent Studio introduced in 26A. In this opening post, I’ve focused on how agents connect to the wider enterprise landscape, because integration, reliability and governance are what ultimately determine whether AI delivers real value. In the next blogs, I’ll build on this foundation and explore other new capabilities in more detail, looking at how they work in practice and how you can apply them confidently in real‑world scenarios.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines
At the AI World London HCM Partner Summit, Oracle unveiled 22 new Agentic Applications across the Fusion suite, including eight designed specifically for HCM Cloud. One of the standout additions is the Workforce Operations Command Centre, which brings scheduling, time, and absence management into one coordinated hub. It highlights real‑time risks, helps managers make confident coverage decisions, and streamlines day‑to‑day operations. During the demo, we saw a live priority queue flagging shift conflicts and timecard issues by severity, with simple one‑click options to approve, reassign, or review — making it far easier to stay ahead of workforce challenges.
Oracle has also introduced a series of new workspaces designed to streamline everyday manager and employee tasks. The Hiring Workspace for Store Managers brings candidate details, interview scheduling, and urgent hiring requests together to support faster decisions, while the Manager Concierge Workspace unifies compensation, performance, talent, and absence insights with simple, policy‑backed actions. The Team Learning Workspace helps managers stay ahead of compliance risks and focus on development priorities, and the Career Advancement Command Centre connects employees to suitable roles, required skills, and training. Alongside this, the My Help Workspace offers a clear view of open requests and relevant knowledge articles, and Contracts Intelligent Counsel, also known as Agentic Compliance, provides continuous, autonomous monitoring of contract terms and policy changes to reduce compliance overhead.
Oracle also unveiled Oracle Manager Edge, a new personal AI coach designed to give managers practical, data‑driven guidance directly within Touchpoints, with suggested actions seamlessly linked to Oracle Team Touchpoints. Although it isn’t an Agentic Application, it will be available through the AI Agent Studio once released, offering organisations an accessible way to bring personalised, context‑aware coaching into everyday management without additional complexity.
Oracle also confirmed six dedicated Payroll Agents designed to cut manual effort and improve payroll accuracy. The Payslip Analyst, already live in 25D, helps employees resolve payslip queries and has been shown to reduce inquiry costs by up to 70 per cent with a rapid ROI. The Compliance Update Agent (26C) converts legislative changes into proactive configuration updates, removing up to 90 per cent of the manual workload. The Court Order Processing Assistant (26A) fully automates garnishment intake, while the Tax Calculation Statement Agent (26C), currently specific to the US and California, explains the detailed tax logic behind each payroll run. The W‑4 Compliance Agent (26B) automates US tax‑form completion, and the Pay Run Agent (26C) provides real‑time summaries and flags exceptions, reducing manual review efforts by as much as 70 per cent. For UK and global payroll teams, the Payslip Analyst and Compliance Update Agent are the most relevant today, with the remaining agents focused on US‑specific requirements.
As Oracle continues to expand its portfolio of Agentic and AI‑driven capabilities, the direction is clear: more guidance, more automation, and less friction across everyday HR and payroll operations. For organisations already using Fusion, these new applications offer a practical way to improve decision‑making, strengthen compliance, and deliver a smoother experience for managers and employees alike. And with more innovation on the horizon, now is an ideal time to explore how these tools can support your roadmap and help your teams work smarter, not harder.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines.
After sharing my initial thoughts on the Oracle AI World announcements earlier this week, I’ve since taken a closer look at what sits behind the headlines. The announcements focused on what Oracle is delivering, but what really interests me now is the how. That is where things get genuinely exciting for those of us who will be hands-on, building and configuring these new capabilities.
One thing that really helped me make sense of Oracle’s approach was the clear distinction between workflow agents and hierarchical agents. They serve very different purposes, and treating them as interchangeable would quickly lead to the wrong outcomes. Workflow Agents follow policy‑bound orchestration with contextual reasoning and are designed for predictability, auditability and stable SLAs, making them ideal for things like payroll deductions, purchase requisitions or leave approvals where governance and consistency are essential. Hierarchical Agents work differently, using LLM‑led decomposition with specialist sub‑agents, which makes them a better fit for open‑ended problems with many possible paths where multi‑domain reasoning matters more than repeatability. Oracle has intentionally designed the two to complement each other, with Workflow Agents providing the structure by defining stages, approvals, retries and SLAs, while Hierarchical Agents take on the heavier analytical or generative work within specific steps. The result is a balanced model that preserves governance while still giving teams the flexibility to tackle more complex reasoning tasks.
Oracle has outlined seven composable design patterns for building Workflow Agents, each suited to a different type of process. Chaining uses sequential intelligence to pass enriched context from one step to the next, which works well for extract‑validate‑decide‑act processes. Parallel execution allows multiple branches to run at the same time and then consolidates their outputs into a single decision, making it a strong fit for compliance or risk scenarios. Switch flows use context‑aware decisioning to route work based on intent, profile, state and policy; for example, an employee updating deductions after a new baby can trigger both Benefits and Payroll updates automatically with no handoff. Iteration supports adaptive refinement by recalculating until constraints are met, which suits planning and scheduling tasks. Looping introduces self‑correction, such as regenerating and revalidating an invoice when OCR results do not match. RAG‑assisted Reasoning retrieves the right policy information before applying thresholds or routing logic. Finally, timer‑based execution triggers actions on a schedule, such as checking invoice status and notifying the accounts payable owner before an SLA is at risk.
The Workflow Agent canvas in AI Agent Studio groups its building blocks into four areas that shape how an automation behaves. AI nodes include LLM, Agent, Workflow and the RAG Document Tool. Data nodes cover things like the Document Processor, Business Object Function, External REST, Tool and the Vector DB Reader or Writer. Logic nodes provide Code and Set Variables, while the Workflow Control nodes handle governance through Human Approval, If Condition, For Loop, While Loop, Switch, Run in Parallel, Wait and Return. At workflow level, the Triggers tab supports Webhook, Email and Schedule triggers, and the Error Handling section lets you notify recipients by email if a workflow reaches a permanent failure, using context expressions such as $context.$workflow.$traceId. For image-related tasks, the Vision LLM node is the correct choice, although it is classed as a premium tool and comes with associated pricing considerations.
METRO, Oracle’s monitoring layer for Measurement, Evaluation and Testing for Real‑time Observability, gives teams a clear view of what their Workflow Agents are doing across inbound emails, approvals and scheduled runs. From the 26C release, it will also surface AI Unit consumption, which becomes increasingly important as organisations scale their use of agents and need tighter visibility and cost control.
Pricing has been a major consideration for customers exploring AI Agents, and the new structure aims to simplify things through the introduction of AI Units, or AUs. Oracle is expected to publish the full details in April or May, but the core concept is that an AU costs roughly $0.01 and is calculated as: AU consumption = CEILING((Input Tokens + Output Tokens) / 10,000) × Action Value Factor. The Action Value Factor varies depending on the action type and the LLM tier being used. General actions such as Q&A, approvals and reasoning have a 0x factor on the Basic LLM, while Premium and Bring Your Own apply higher factors. Artifact creation and audio generation sit in higher tiers again, with video generation marked as coming soon. Every Fusion customer receives 20,000 AUs per month at no charge, pooled across all pillars with unused units rolling over to the end of the contract term. Additional AUs are available in $1,000 increments.
What I find most compelling about this architecture is that it’s built for the realities of enterprise work rather than an idealised version of it. The self‑correction loops, governance controls, evaluation framework and hybrid agent pattern all acknowledge that real business processes can be messy and that auditability is essential. The 22 new agentic applications arriving in 26B across ERP, HCM, SCM and CX give us a clear benchmark for what good looks like in practice. If you’re interested in exploring how Workflow Agents could support your organisation’s processes, now is a great time to start that conversation.
In the meantime, why not check out my earlier post covering the Oracle AI World announcements? You can find it here.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines
I’m writing this from Oracle AI World in London today, where Oracle has just unveiled its new Agentic Applications for Oracle Fusion Cloud. It’s genuinely one of the biggest announcements we’ve seen in quite some time. These aren’t early ideas or future promises, they’re real applications, with names, availability details, defined process areas and clear outcomes for customers. Here’s a quick look at what matters and why it’s worth paying attention to.
Oracle’s message today is pretty clear: traditional enterprise systems may hold vast amounts of information, but they don’t genuinely understand it. They capture data, store it, and generate reports, but it’s always been down to people to interpret what’s happening and drive the next step. Agentic Applications change that. They bring reasoning, context awareness and prioritisation into the flow of work, acting within your existing governance and security boundaries without needing constant, step‑by‑step direction.
In this updated architecture, Oracle positions Agentic Applications in a new, composable layer above the existing Fusion transactional systems, ERP, HCM and CX. Beneath that, they can tap into a broad set of LLMs from OpenAI, Cohere, Meta, Anthropic, xAI and Google. At the centre is Oracle AI Agent Studio, which provides the development and configuration layer that connects everything together. Oracle also introduced a helpful maturity model: GenAI Assisted, delivering around a 5–10% productivity uplift; Agent Optimised, offering 10–30% efficiency gains; and Agent Re‑invented, where processes are re‑designed around autonomous agents and Oracle is seeing improvements of 40% or more in operational agility.
Oracle was also keen to emphasise that not all AI in Fusion is created equal. There’s a spectrum that runs from AI Workflows, logic‑driven automation using LLM nodes, loops and if/then conditions, through to Workflow Agents, which introduce real‑time reasoning and greater autonomy. Above that sit AI Agents, which are goal‑based, specialised and able to operate more independently, and AI Agent Teams, where a lead agent coordinates several specialist agents working together. Each step up the ladder trades a little predictability for far greater capability. For anyone who’s spent years configuring Oracle, the workflow layer will feel familiar, but the agentic layers above it represent genuinely new behaviour.
Oracle also announced a set of new capabilities today, including an Agentic App Builder, interoperability through MCP (Model Context Protocol) and A2A (Agent‑to‑Agent) protocols, Contextual Memory, Content Intelligence, multi‑modal support, an Agent ROI Dashboard, and a full suite of security, audit and governance controls. The standout is the Agentic App Builder: you simply describe your objective in natural language and the system assembles reusable agents and workflows into a composable agentic application.
One final announcement that will please a lot of customers: Oracle has simplified its agent pricing. The old split between Seeded Agents (Oracle‑built) and Custom Agents has been removed. If you use Oracle’s standard LLMs, every agent, irrelevant of who has built it, is now free. Premium third‑party LLMs such as OpenAI or Anthropic come with a straightforward consumption‑based charge. Every Fusion customer also receives a monthly allocation of 20,000 AI Units (AUs), with unused units rolling over until the end of the contract term. For organisations that have held back on AI because of cost uncertainty, that barrier has effectively disappeared.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines
AI is everywhere at the moment, there’s really no getting away from it, but not all AI is created equal. Plenty of platforms promise co‑pilots, assistants and automation, yet very few can actually take action inside core business systems. That’s why Oracle’s approach with AI Agent Studio for Fusion Applications really stands out.
Most enterprise AI tools today act as co‑pilots: brilliant for drafting content or answering questions, but far less capable when it comes to genuine process automation. Oracle has taken a different approach. Its AI agents are embedded directly within Fusion Applications, giving them the power to:
Understand business data in real time
Make decisions with full context
Write back into transactional systems securely
Automate tasks end‑to‑end without relying on extra tools
This isn’t AI “bolted on”, it’s AI woven right into the core of the application. And yes, I realise I’m starting to sound like an Oracle salesperson, but the difference between Oracle and other providers is hard to ignore. The image below highlights just how significant that gap is, comparing what Oracle delivers with five other major service providers.
Across the market, vendors are running into the same familiar obstacles:
Added AI costs. Whether it’s Copilot capacity, ServiceNow’s AI tiers or Salesforce Flex Credits, AI is frequently positioned as an optional extra rather than something included as standard.
Co‑pilots, not agents. Microsoft, Salesforce, Workday and others are excellent at generating content and offering recommendations, but they seldom deliver true autonomous action within transactional systems.
Fragmented platforms. Many providers depend on several data models, clouds and integration layers. Their AI often relies on separate analytics environments or copied data, which strips away workflow context and makes automation far more difficult.
You may have already come across Oracle’s One Platform, and this is where Oracle really pulls ahead of the pack. Oracle keeps things refreshingly straightforward: Fusion Applications, data and AI all sit within a single, unified ecosystem. That brings three key advantages:
Embedded intelligence — agents work directly inside the applications employees use every day.
A unified security and data model — consistent governance and safer, more reliable automation.
True write‑back — agents can update transactions natively, without middleware or separate AI clouds getting in the way.
So you might be wondering, “That all sounds impressive, but what does it actually mean for me?” At its core, agentic AI is about cutting down manual effort, improving accuracy and boosting operational efficiency. Oracle’s embedded approach ensures that automation is reliable, properly governed and able to scale as your business does. Crucially, it isn’t stitched together from multiple products. With Oracle, AI is built in, a fundamental part of the system that runs your business, not an optional extra layered on top. It marks a shift from AI that simply talks, to AI that genuinely delivers.
Please note all screenshots are the property of Oracle and are used according to their Copyright Guidelines
Have you heard about METRO? METRO is the embedded measurement and observability framework within Oracle AI Agent Studio. It stands for:
Oracle have introduced METRO as part of release 25D. It is a brand-new set of monitoring and evaluation tools built right into Oracle AI Agent Studio. Think of METRO as your control centre for AI agents in production. It gives you everything you need to keep an eye on accuracy, compliance, performance, costs, latency and even token usage. In short, it helps you make sure your agents are doing exactly what you expect, without any surprises.
The world of AI agents isn’t straightforward, responses can vary, workflows aren’t always predictable, and traditional checks don’t always work. That’s where METRO steps in. It’s designed for this new reality, offering smart ways to check semantic correctness, track detailed performance metrics and keep guardrails in place against risks like prompt injection. Whether you’re running complex multi-agent setups or more structured workflows, METRO makes it easier to stay on top of quality and reliability.
One of the best parts? The dashboard. It gives you a clear view of key stats like latency, error rates, token counts and correctness scores. And if you want to dig deeper, you can trace every single step an agent took, from LLM calls to tools used and outputs generated. This level of detail means you can troubleshoot quickly and optimise performance without the guesswork.
METRO also helps with testing, using the industry-standard LLM-as-a-Judge approach to score responses and provide feedback you can act on. Combine that with new features in 25D, like deterministic workflow agents and support for models such as GPT‑5 mini, and you’ve got flexibility to build agents for any scenario.
METRO isn’t just another feature, it’s a game-changer for anyone looking to manage AI agents with confidence. By combining deep insights, flexible evaluation tools and full traceability, it gives you everything you need to keep your AI ecosystem running smoothly. And with the added power of new models and workflow options in 25D, you’ve got all the tools to innovate faster and smarter. The future of AI governance starts here and METRO makes it simple!
K8 Mead 