Tag: Power FX

Exam AB-410: Intelligent Applications Builder Associate

Time for another exam post (I’ll actually be doing 2 posts around new exams this week), this time around building ‘AI Applications’. This is another one of the new ‘AB series’ of exams, which are replacing the older ‘PL series’ of exams. This exam specifically replaces the PL-200 exam, though there’s no mention of the ‘Functional Consultant’ title any longer.

This time, it’s around building intelligent applications. What struck me in the first instance is that it DOESN’T cover using AI to build applications – there’s nothing in it (well, for me at least) that looked at using Copilot or any other AI capabilities within Power Platform to build out components (whether applications or automations). The exam information does mention using AI, but the exam questions (at least the ones I got) didn’t cover it at all. This does feel a bit strange, given how Microsoft keep going on about using AI for building, but given that Copilot for building canvas apps has been deprecated (as an example), I guess that this is following the same trend.

The official description of the proposed exam candidate is:

As a candidate for this Microsoft Certification, you’re a professional who builds AI-powered solutions in Microsoft Power Platform by using Microsoft Copilot, natural language prompts, and low-code tools. You create apps, data models, and flows that connect to agents, AI models and prompts, and visualizations to enrich these experiences.

In this role, your responsibilities include:

  • Developing Dataverse data models, model-driven apps, and canvas apps.
  • Integrating agents and Copilot features into canvas apps, model-driven apps, and Power Pages sites.
  • Creating cloud flows and business logic.

You collaborate with:

  • Environment and security administrators for policies, roles, identity, and authentication.
  • Governance teams on responsible AI principles, application lifecycle management (ALM), solutions, pipelines, and monitoring.
  • Agent developers, solution architects, and other app builders for business solution building.
  • Business stakeholders to gather requirements, iterate business solutions, and promote user adoption.

The overall information for the exam can be found at Microsoft Certified: Intelligent Applications Builder Associate, and there is an official Learning Path available for it.

There is a LOT of different stuff in this exam, but I like it – it shows the breadth of knowledge (& experience) that’s needed in order to build out what’s needed for applications. Canvas apps were somewhat lightweight (at least for me), but I’m absolutely LOVING the focus & usage on Business Process Flows and Business Rules. Yes they’ve been around for a loooong time, and there’s nothing cool, sexy or new about them, but they’re absolutely essential to the ways of working with data & records!

As I’ve posted before around my exam experiences, it’s not permitted to share any of the exam questions. This is in the rules/acceptance for taking the exam. I’ve therefore put an overview of the sorts of questions that came up during my exam. (Note: exams are composed from question banks, so there could be many things that weren’t included in my exam, but could be included for someone else!). It’s also in beta at the moment, which means that things can obviously change for when it comes out of beta.

I’ve tried to group things as best together as I feel (in my recollection), to make it easier to revise:

  • Environments
    • Environment types
    • When to use different types of environments
  • Dataverse
    • Table relationships
    • Record deletion rules, including how they can affect child records
    • Executing logic on record forms – client side vs server side, what is used for each
    • Executing synchronous behaviour – what this is, what can be used for it
    • Different options for validation logic, how they work, and when to use
    • Adding icons for tables
    • Creating/configuring forms
    • Creating/configuring views
    • Custom pages – what they are, when they should be used
    • Column options – what they are, how/when to use. Covering items such as rollups, formula, autonumbering, etc
  • Business rules
    • What they are, and when to use
    • Different types of actions
    • Business required vs Business recommended
    • Scope options – what each one means, and how they actually work/affect data
  • Approvals
    • What they are
    • How to configure, including different types of approvals
  • Business process flows
    • When to use
    • What the different components are (eg steps, stages etc)
    • How to configure
    • Triggering Power Automate flows
    • Usage of them on existing records vs new records
  • Power Automate
    • Trigger types – differences between them, when to use
    • Handing connections
    • Handling time-outs/retries
    • Handling/configuring Run After behaviour
    • Concurrency – what is it, when to use, how to configure
    • Connecting to AI Builder
    • Conditions – what they are, how/when to use
    • Branching logic – what this is, how/when to use
  • Canvas Apps
    • Triggering record submission and saving
    • Triggering Power Automate flows
    • Configuring properties for buttons (different formula types)
    • PCF controls – what they are, what they’re used for, creating them, reusability
    • Power FX commands – selecting right syntax to be used for code examples, managing retries, managing errors
    • Variable types – what they’re used for, differences between them
    • Collections – what they’re used for, how to use them
    • Optimising data loading – how to do this, what to consider, what to use
  • Integrations
    • Connecting to Microsoft components (inside and outside of Power Platform)
    • Connecting to custom API’s
    • Connecting to external API’s
  • Security
    • Security roles
    • Security teams & access teams
    • Entra ID security groups
    • Giving access to applications
    • Checking user access rights
    • Dataverse record ownership – different types of record ownership, differences between them, how to set up/configure
    • Restricting access to tables, views & forms
    • Hierarchy security – different options available, differences between them and when to use them
  • Auditing
    • Global level
    • Table level
    • Row level
    • Retention settings
    • Change tracking – enabling it, when it should be used
  • Application Lifecycle Management (ALM)
    • What solutions are used for
    • Unmanaged vs managed solutions
    • Exporting & importing solutions between environments
    • Adding components to solutions (new vs existing components, and how to do this)
  • AI
    • Using AI to summarise records – how to set up, configure and use it
    • Using AI Builder – capabilities, how to set it up & use it, how to call it from different component types, how to use outputs
    • How to update AI Builder prompts

I hope that this is helpful for anyone who’s thinking of taking it – good luck, and please do drop a comment below to let me know how you found it!

I’d also be interested in your thoughts/opinions around the direction that Microsoft has taken for this!

Exam AB-620: Design and build integrated AI agent solutions in Copilot Studio

We seem to be on a roll here over the last month or so with new exams being released (& its not over yet!). With all of the emphasis on AI & agents, I decided to go take the new Copilot Studio exam to see what it would be like.

Given that I have a decently passing familiarity with Copilot Studio (as I use it for projects, and actually do get hands on with it quite a bit of the time), I felt that I’d be in a good place to handle it without any revision. Obviously this could have been a bold move, and it’s up to everyone to make their own decisions about how much to revise (or not revise)!.

Copilot Studio has moved on from when it first came onto the scene (and for those who remember, it used to be called Power Virtual Agent, or PVA). Nowadays it supports coding within it, but it also can serve as the front end for other Microsoft AI capabilities, such as Microsoft Foundry models.

This is also the first time that it’s been featured for its own exam – previously it got rolled into other exams (such as the PL-100, PL-200, etc), where it was just one of the components being covered (and covered in a lightweight manner, at that). With the focus from Microsoft now heavily on it though, it’s now taken a step forward into the spotlight by itself.

The official description of the proposed exam candidate is:

As a candidate for this Microsoft Certification, you’re a professional developer or advanced builder who builds, extends, and integrates custom agents for enterprise-grade solutions. You typically work as an IT application developer, consultant, or independent software vendor (ISV) partner focused on creating scalable AI solutions for organizations or customers.

For this exam, you should be familiar with Power Fx, Microsoft Dataverse, Microsoft Power Platform environments and components, Microsoft 365 Copilot, Microsoft Foundry, and adaptive cards.

You need intermediate knowledge of generative AI concepts, including models, orchestration, retrieval-augmented generation (RAG), Model Context Protocol (MCP), Agent2Agent (A2A) protocol, and more. You should also have experience with prompt engineering and with REST APIs and integration patterns. Additionally, you need experience configuring agents with basic knowledge sources, instructions, tools, and topics in Microsoft Copilot Studio.

As a developer who works in Copilot Studio, you:

  • Integrate agents with Microsoft Foundry.
  • Integrate agents with Model Context Protocol (MCP) servers.
  • Integrate agents with custom connectors.
  • Integrate agents with APIs.
  • Integrate agents with Microsoft Fabric.
  • Automate tasks with computer use.
  • Integrate agents with connectors.

You create:

  • Multi-agent solutions.
  • Agents with enterprise knowledge sources (such as ServiceNow, SAP, and others).
  • Advanced agent topics and tools.
  • Computer-using agents.
  • Agents that perform advanced actions via APIs.

You collaborate with Microsoft 365 administrators, Microsoft Power Platform administrators, Microsoft Copilot administrators, Copilot Studio agent builders, Copilot Studio administrators, Foundry administrators, agentic AI business solutions architects, and Copilot Studio architects.

The overall information for the exam can be found at Microsoft Certified: AI Agent Builder Associate, and there is an official Learning Path available for it.

As I’ve posted before around my exam experiences, it’s not permitted to share any of the exam questions. This is in the rules/acceptance for taking the exam. I’ve therefore put an overview of the sorts of questions that came up during my exam. (Note: exams are composed from question banks, so there could be many things that weren’t included in my exam, but could be included for someone else!). It’s also in beta at the moment, which means that things can obviously change for when it comes out of beta.

I’ll freely admit that there was a LOT more focus on MCP capabilities than I had expected there to be, but I guess that again this is natural, given how Microsoft is moving at the moment.

I’ve tried to group things as best together as I feel (in my recollection), to make it easier to revise.

  • Copilot Studio
    • Component/node types. What they are, how/when to use them
    • Using topic variables
    • Timeouts
    • Concurrency
    • Sensitive data & Using type ‘secret’ – what this does and why to use
    • Generative answers – how they work, limitations, what to know, how to configure & ground them
    • Computer Use
    • Connecting with Microsoft Graph
    • Connecting to other agents – how to do this, how to configure, what to use
  • Connector types
    • Standard connectors (ie connectors provided by Copilot Studio). When to use them, limitations
    • Custom connectors – what these are, why you’d use them
  • Security
    • Authentication types (API, OAuth 2)
    • Query delegation
    • DLP policies
  • MCP servers
    • What they are
    • Connecting to them
    • Security with MCP servers
    • Authentication types
    • Usage of AI with MCP servers
  • Azure AI Search
    • Connecting to knowledge index
    • Configurations
    • Security
  • Solution Types
    • Default vs Unmanaged vs Managed
    • Environment variables
    • Creating solution
  • Application Lifecycle Management (ALM)
    • What this is, and why it’s needed
    • What approaches can be used, why to use them
    • What’s needed to set up ALM
  • Monitoring & Troubleshooting
    • Reporting on deployed agents
    • Evaluating usage of deployed agents
    • Identifying issues & errors
    • Stopping runs

I hope that this is helpful for anyone who’s thinking of taking it – good luck, and please do drop a comment below to let me know how you found it! I’d also be interested in your thoughts/opinions around the direction that Microsoft has taken for this!