Specialized AI Track • UiSAI • Professional Level C E R T I F I C A T I O N G U I D E UiSAI Certification Guide: UiPath Specialized AI Professional Syllabus, sample questions and a study plan for the UiPath-SAIv1 exam All 141 objectives from the UiSAI syllabus under their sixteen topic headings, with an objective-count chart, the exam fact sheet checked against UiPath’s August 2025 exam description, how Document Understanding, Communications Mining and AI Center split the paper, the 18-hour Academy learning plan, a five-step route to exam day, and ten real sample questions with a full answer key. 60 QUESTIONS 180 MINUTES 70% PASSING SCORE $300 EXAM FEE 17 EXAM SECTIONS Prepared by CertFun • www.certfun.com www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 1 CERTIFICATION GUIDE Contents Click any line to jump straight to that section. The same eight entries appear in your PDF reader’s bookmark pane. SECTION 01 Exam Overview 2 SECTION 02 What the Current Exam Description Says 3 SECTION 03 What This Exam Actually Tests 3 SECTION 04 The Exam Sections and Every Objective 4 SECTION 05 What the Credential Is Worth 11 SECTION 06 Getting Certified, Step by Step 12 SECTION 07 UiSAI Sample Questions 12 SECTION 08 Where to Go Next 15 www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 2 SECTION 01 Exam Overview The UiSAI UiPath Specialized AI Professional exam is UiPath’s professional-level credential for intelligent document processing and unstructured-communication AI: Document Understanding, Communications Mining and AI Center. It is a 180-minute exam with a 70% pass mark, booked through Pearson VUE. The facts below come from CertFun’s UiSAI exam syllabus and from UiPath’s own exam description document (version 1.5, August 2025); where the two overlap they agree. Certification UiPath Certified Professional Specialized AI Professional Exam code UiSAI (UiPath exam number UiPath-SAIv1) Certification track UiPath Certified Professional - Developer / Specialized AI Track Level Professional Number of questions 60 (CertFun syllabus; the UiPath exam description does not state a count) Exam duration 180 minutes Passing score 70% Exam fee USD 300 per attempt Prerequisite None Product versions Document Understanding, Studio, AI Center, Orchestrator 2024.10; Communications Mining 2024.20 Exam sections 17 listed, no official weightings published Delivery Pearson VUE - test centre or OnVUE online proctoring Validity 3 years Exam description Version 1.5, August 2025 Two lines in that table need a caveat. The 60 questions appears on CertFun’s syllabus page; UiPath’s exam description gives the duration, pass mark, fee and validity but not a question count, so treat 60 as the published convention rather than a UiPath statement. On that basis the paper allows three minutes a question and a pass needs about 42 correct answers - our arithmetic, not UiPath’s. And UiPath publishes no percentage weightings for its 17 sections, which is why Section 04 charts the number of published objectives under each topic heading instead and says so. The prerequisite line is genuinely “none,” but the minimally qualified candidate UiPath describes has completed automation projects that analyse complex communications with Communications Mining and process unstructured or semi-structured documents with Document Understanding, has finished the recommended Academy training, and has delivered at least one Communications Mining project www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 3 Re-read the official UiPath certification page the week you book: UiPath’s programme is moving quickly, and the page currently leads with a new agentic certification. SECTION 02 What the Current Exam Description Says The exam has been revised twice since it launched. In June 2024 UiPath announced on its forum that the Specialized AI Professional exam would be updated to align with product version 2023.10 , alongside the launch of a new Specialized AI Associate certification. The exam description now in force is version 1.5, dated August 2025 , and it moves the product list on again: Document Understanding, Studio, AI Center, Action Center, Assistant, Robots and Orchestrator at 2024.10 , and Communications Mining at 2024.20 The content shows the generative turn. Document Understanding now opens with the DocPath LLM , the AI Trust Layer and the Document Understanding API; Studio objectives ask about prompts and the limits of the Generative Classifier and Generative Extractor ; and Communications Mining adds generative annotation and generative extraction in Model Training, Discover and Explore. A whole heading, “Updates from product version 2023.xx and later,” lists twenty changes, from Document Manager updates and field-level business rules to FedRAMP, Exchange attachments and the new dataset creation flow. The fee also moved: a UiPath Forum fee update post from January 2025 records the rise to USD 300 per attempt , the figure the exam description now prints. Version facts to carry into revision Exam description V1.5, dated August 2025; exam number UiPath-SAIv1. Products at 2024.10, except Communications Mining at 2024.20. Academy plan: “Automation Developer - Specialized AI Professional Training (v2024.10)”. Generative classifier, extractor, annotation and extraction are all in scope. SECTION 03 What This Exam Actually Tests UiPath’s own summary is that the certification “focuses on assessing knowledge and skills in constructing and deploying intelligent robots with cognitive capability encompassing AI, ML, and NLP,” and the certification page adds that it “validates the ability to build automated processes that combine intelligent document processing and unstructured communication analysis.” Read the 141 objectives together and the weight is plain: the six Communications Mining headings hold 60 of them, the four Document Understanding headings 21, and AI Center 20 on its own. Communications Mining is where candidates from a pure RPA background are thinnest. Refine and Maintain alone has 22 objectives: precision and recall, Model Rating and its Performance, Coverage and Balance factors, Mean Average Precision on the Validation page, the blue, amber and red label indicators, Check Label and Missed Label, and concept drift. Explore adds Shuffle, Teach Label and Low Confidence; Taxonomy Design asks you to tell analytics from automation taxonomies. Around that sit Analytics and Monitoring (Reports, Trends, Segments, Threads, Alert Center) and Automation and Model Management (streams, thresholds, pinned model versions and the Dispatcher Framework). www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 4 The sample questions on CertFun’s UiSAI sample questions page show the register: five of the ten are Communications Mining, four are Document Understanding and one is AI Center. Two are long scenarios - a mortgage-processing team balancing automation rate against human verification, and a telecoms rollout with inconsistent regional metadata - so expect to read a paragraph before you reach the question. Who UiPath wrote this exam for Automation developers on Document Understanding and Communications Mining projects. Automation architects, solution designers and solution architects in those projects. Process automation architects and similar technical roles. Advanced Automation Developers aiming at AI-powered, production-level automations. This is a hands-on exam written as multiple choice . UiPath’s hands-on list asks for end-to-end process development, code reviews, hypercare, maintenance, project specifications, fixing production bugs and adding features to existing Document Understanding processes. If you have not yet trained an extractor, run a Communications Mining model through Discover, Explore and Refine, and deployed an ML skill on the UiPath platform, the objectives will read as vocabulary rather than things you have done. SECTION 04 The Exam Sections and Every Objective UiPath lists 17 exam sections but publishes its task statements under 16 topic headings : “UiPath Document Understanding Process Template” is named as a section with no separate task list, and its tasks sit under the Document Understanding Framework heading. UiPath does not publish weightings, so the chart counts the 141 published objectives under each heading as a proxy for where the marks sit. Communications Mining - Refine and Maintain leads with 22; AI Center and the 2023.xx updates have 20 each. 1 Document Understanding 4 objectives 2 DU Framework 4 objectives 3 Studio - DU Activities 10 objectives 4 Implementation Methodology - DU 3 objectives 5 AI Center 20 objectives 6 CM - Model Training 8 objectives 7 CM - Taxonomy Design 6 objectives 8 CM - Setup 6 objectives 9 CM - Discover 7 objectives 10 CM - Explore 11 objectives 11 CM - Refine and Maintain 22 objectives 12 Analytics and Monitoring 8 objectives 13 Automation and Model Management 9 objectives 14 Updates from 2023.xx and later 20 objectives 15 Advanced Developer 1 objective 16 Automation Developer 2 objectives www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 5 Number of published objectives per topic heading, counted from the CertFun syllabus page and UiPath’s exam description. DU = Document Understanding, CM = Communications Mining. UiPath gives no percentage weightings. Every objective follows in the wording of the CertFun syllabus page, cross-checked line for line against UiPath’s exam description; the two match. Source quirks are kept rather than corrected: “Cross Tennant,” the Dispatcher Framework and Quotas pages appearing under two headings, and the one-line Advanced Developer heading, which UiPath leaves as a bare placeholder. Read the list as a checklist: if you cannot do the task named in a line, it is a study item. 1. UiPath Document Understanding — 4 objectives • Utilize the Document Understanding API. • Utilize the DocPath LLM. • Describe the AI Trust Layer. • Describe the Cross Tennant functionalities. 2. UiPath Document Understanding Framework — 4 objectives • Build POCs and automation components for DU template (but not a robust and complete DU process) • Utilize the DU Process template to build a complete automation solution. • Utilize the business rules to validate the extracted data. • Use Action Center to incorporate human in the loop for end-to-end processes. 3. UiPath Studio - Document Understanding Activities — 10 objectives • Explain what a Document Object Model is in the context of Document Understanding. • Select an appropriate OCR engine for your digitization use case. • Analyze what kind of classifier/extractor is the most suitable for the automation project. • Use UiPath Orchestrator or Action Apps to configure human validation steps. • Train the Classifiers and Extractors used to improve their performance. • Build the first model and test it out for labeling and types. • Evaluate the model. • Utilize the following Taxonomy features: Validator notes and business rules. • Utilize the Document Object Model in the context of Document Understanding. • Explain building prompts and the limitations for the Generative Classifier and the Generative Extractor. www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 6 4. UiPath Implementation Methodology - Document Understanding specific — 3 objectives • Gather and analyze data about the documents in scope (document types, fields extracted, pages per documents). • Gather and analyze data about languages in scope and OCR engine of choice. • Integrate exception handling within the automation solution. 5. UiPath AI Center — 20 objectives • Distinguish between AI,ML,NLP,DL,Computer vision. • Distinguish between supervised, unsupervised and reinforcement learning. • Describe how AI Center works. • List the user personas who can access and use AI Center. • List the types of ML models in AI Center. • Describe the various ways to deploy and install AI Center. • List the example of out-of-the box ML Packages application. • Define the AI Center User Interface elements. • Manage projects in AI Center (Create, edit, delete). • Manage datasets in AI Center (Create, upload, edit, delete, make the dataset public). • Manage data labels in AI Center (Create a data labeling instance, configure). • Build ML Packages in AI Center. • Manage ML Packages in AI Center (Upload ML Package, import, view ML Package details, version control of ML Packages). • Use Out-of-the-box ML Packages from AI Center. • Manage the Pipelines available in AI Center (Create, schedule pipelines, edit scheduled pipelines, remove pipelines). • Describe how to retrain a model by sending feedback from the process to the model. • Create ML skills. • Update ML Skills in new ML Packages (Upload ML Package, import, view ML Package details, version control of ML Packages). • Describe the steps to make an ML skill public. • Describe the types of events captured in the ML logs. www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 7 6. UiPath Communications Mining - Model Training — 8 objectives • Describe the golden rules of label training. • Describe the golden rules for general fields training. • Using the train tab • Generative annotation (cluster suggestions, assisted labelling) • Generative extraction (configuring extractions, generating extractions, training extractions, best practices, improving extraction performance) • Describe the best practices of label annotation. • Describe the best practices for general fields annotations. • Describe the best practices for extraction fields annotations. 7. UiPath Communications Mining - Taxonomy Design — 6 objectives • Create a label taxonomy structure according to best practices. • Differentiate between analytics and automation taxonomies. • Provide examples of typical groups of labels (process/request types, quality of service / failure demand etc.). • Distinguish between different types of general fields (pre-trained, trained from scratch, trainable, non-trainable). • Describe Taxonomy Import Options • Quality of Service, Tone and Sentiment 8. UiPath Communications Mining - Setup — 6 objectives • Describe the three main components of data (data sources, datasets, projects) and how to manage them. • Enable, update, or disable general fields in a dataset in UiPath Communications Mining. • Import a taxonomy via the Settings or Train pages in UiPath Communications Mining. • Distinguish between tone analysis and label sentiment. • Role-based access control • Data Architecture and Permissions. www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 8 9. UiPath Communications Mining - Discover — 7 objectives • Label clusters considering key best practices. • Describe what the Search functionality in Discover is and when it is recommended to use it. • Explain the risks associated with using too much Search to train the model vs balancing out with Shuffle and Teach Label. • Define what the Discover phase of the Communications Mining process, how it works, and why it's important. • Describe what clustering labels are and why they are important. • Describe the two main steps of the Discover phase • Generative Annotation functionality in Discover. 10. UiPath Communications Mining - Explore — 11 objectives • Explain what label and general fields predictions are, how they work, and how to use them. • Distinguish between label predictions and label suggestions. • Differentiate between when it makes sense to use Shuffle, Teach Label, or Low Confidence to train the model in the 'Explore' phase. • Use Shuffle, Teach Label, or Low Confidence in the 'Explore' phase according to best practices. • Explain when it is recommended to use Teach general fields to continue label training at the end of the Explore phase. • Prune and reorganize a taxonomy by editing, renaming, merging and deleting labels. • Prune and reorganize a taxonomy by modifying or deleting an general fields. • Define what Explore phase of the Communications Mining process, how it works, and why it is important. • Describe the factors that indicate sufficient labeling training has been performed in the Explore phase. • Generative Annotation functionality in Explore • Generative extraction. 11. UiPath Communications Mining - Refine and Maintain — 22 objectives • Define why the 'Refine' phase of the Communications Mining process is important. • Explain precision and recall metrics, how they impact the performance of machine learning models. • Describe what Model Rating assesses, and what factors it takes into consideration (Performance, Coverage, Balance). • Analyze All Labels and suggest typical solutions to improve the score (understand MAP). • Analyze Underperforming Labels and suggest typical solutions to improve the score. • Analyze Coverage to check how well covered the whole dataset is and suggest typical solutions to improve the score. www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 9 • Analyze Balance to check for a balanced representation of the whole dataset, and suggest typical solutions to improve the score. • Distinguish between the three label performance indicators (blue, amber, red). • List potential reasons that can lead to low label performance. • Address bias labelling by continuing to train the model using Teach Label in the 'Refine' phase of the Communications Mining process. • Continue to train the model using Check Label and Missed Label in the 'Refine' phase of the Communications Mining process. • Name the recommended Model Ratings for automation and analytics use cases. • List indicators of when model training could be finished at the end of the UiPath Communications Mining process. • Analyze what general fields scores are, how they are calculated, and typical solutions to improve them (Teach general fields, Check general fields, Missed general fields). • List the two key factors that can be erode a model's performance (brand new labels are added, but not trained, or concept drift occurs.) • Explain how to add new labels to an existing taxonomy. • Explain how models should be maintained in production. • Use recommended next best actions in the Validation page to improve a training model. • Describe what Mean Average Precision (MAP), why it is useful, and how to view it in the 'Validation' page. • Analyze Metrics in the Validation page to check average label performance statistics. • Use the 'general fields' tab to analyze validation statistics of the performance of all the general fields enabled in the dataset. • Use the 'extraction ' tab to analyze validation statistics of the performance of all the extraction fields enabled in the dataset. 12. Analytics and Monitoring — 8 objectives • Use the 'Reports' pages to create customized and dynamic dashboards. • Use the 'Label Summary' tab to analyze charts and high-level summary statistics. • Use the 'Trends' tab to analyze trends for verbatim volume, label volume, sentiment over a given time period, etc. • Use the 'Segments' tab to analyze label volumes versus verbatim metadata fields, e.g. Sender Domain. • Use the 'Comparison' tab to conduct A/B tests and cohort comparisons between different cohorts of the dataset. • Use the 'Threads' tab to analyze conversations and their characteristics. • Use 'Quality of Service' and 'Tone Analysis' to monitor channel performance. • Use 'Alert Center' to configure and track alerts and issues. www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 10 13. Automation and Model Management — 9 objectives • Apply CI/CD best practices for model management. • View, create and modify streams. • Choosing the right threshold for streams. • Pinning model versions for productions and staging. • Describe the Dispatcher Framework. • Communications Mining Studio Activities • Communications Mining Dispatcher Framework. • Quotas & Deprecated Models pages. • Explain how UiPath Communications Mining and RPA can work together 14. Updates from product version 2023.xx and later — 20 objectives • Use the Document Manager updates in your DU process. • Define and apply business rules at field levels in Taxonomy Manager. • Use the DU Cloud APIs. • Allocate roles using the new Role-based access control in Document Understanding. • Deprecations • Dataset import from Document Manager to Modern Projects • Project Performance dashboard • Field configuration experience • Classification Validation for Cross-platform Activities • Validator Notes • Extended OCR Engine & Arabic language support in UiPath DU OCR • Generative Extraction, Classification & Validation capabilities in APIs • FedRAMP • Get attachments via Exchange integration • Attachment property filters • Notification service integration for CM integrations & alerts • Assignable user roles • Communications Mining Dispatcher Framework • New dataset creation flow • Quotas & Deprecated Models pages 15. Advanced Developer — 1 objective • Advanced Developer www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 11 16. Automation Developer — 2 objectives • SharePoint integration, file manipulation, Microsoft 365 • Automation Developer Generic A navy edge marks the six headings with ten or more objectives. The exam description also lists the environments you should be comfortable in: the SDLC in general, Excel, Outlook, a code editor, browsers, HTML page elements, version control, Studio and the Robotic Enterprise Framework, the Document Understanding template, Communications Mining, AI Center, Action Center, Orchestrator and Robots. SECTION 05 What the Credential Is Worth No salary survey isolates a Specialized AI premium, so the nearest honest figure is the RPA developer role this certificate builds on. Talent.com’s RPA developer salary page puts the average US RPA developer at $120,233 a year, with entry-level positions starting at $100,000 and experienced developers at $148,748, as read on 5 November 2026. Treat those as figures for the job title, not for the certificate. The stronger argument is specialisation. UiPath calls this “a valuable credential that represents a high level of expertise, particularly suited for roles such as Advanced Automation Developers, Solution Architects, Automation Architects.” It also says something a general developer certificate does not: that you can train a Communications Mining model to a usable Model Rating and put a Generative Extractor into a document pipeline with human validation. Why this exam, specifically No prerequisite exam or certification - UiPath states “None.” USD 300 and 180 minutes - an hour longer than the Automation Developer Professional. Covers Document Understanding, Communications Mining and AI Center in one credential. Valid 3 years; the Academy plan unlocks a Specialized AI Professional digital badge. If the Professional exam is a step too far today, CertFun also publishes a UiSAIA Specialized AI Associate practice exam for the Specialized AI Associate, the entry-level exam UiPath recommends you work through first. www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 12 SECTION 06 Getting Certified, Step by Step 1 Start with the Associate learning plan UiPath recommends the Specialized AI Associate plan before the Professional one. 2 Work the Professional learning plan AI Center, Document Understanding, Communications Mining: 18 h 35 min in all. 3 Build one document and one comms pipeline DU Process template with human validation; a CM dataset taken through to Refine. 4 Drill the long headings CM Refine and Maintain (22), AI Center (20), the 2023.xx updates (20), CM Explore (11). 5 Take the practice test, then book 180 minutes, 70% to pass, USD 300, through Pearson VUE at a test centre or online. Step two is the core. The Specialized AI Professional learning plan UiPath names on the exam description runs in three parts - UiPath AI Center (1 h 35 min), UiPath Document Understanding (9 h 45 min) and UiPath Communications Mining (6 h 45 min) - plus a 30-minute assessment, 18 h 35 min in total. The plan page notes it was built on 2023.10 components and is being aligned with 2024.10, with only minor visual differences, and it recommends completing the Specialized AI Associate plan first. UiPath also links a free official practice test from its Academy certifications page. For the last stretch, CertFun’s UiSAI practice exam mirrors the real format and timing so you find the gaps before the exam does. On booking, Pearson VUE’s UiPath page sets the retake rules: a failed first attempt means a two-week wait before the second, and from the third attempt on at least one month between retakes, each paid in full. Reschedule or cancel at least 48 hours ahead or the fee is forfeited - at USD 300 an attempt, that window is worth putting in your calendar. SECTION 07 UiSAI Sample Questions These ten come from CertFun’s UiSAI sample questions page, shown here in shuffled order and verbatim, including the source’s own phrasing. All ten are single-answer with four options. Five are Communications Mining, four Document Understanding and one AI Center - close to the balance of the objectives. www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 13 Q1. Which web application lets users prepare, review and correct the document datasets used to train and evaluate Document Understanding ML models? a) Classification Station b) Validation Station c) Taxonomy Manager d) Document Manager Q2. A dataset in UiPath Communications Mining has both labels and general fields enabled. Which annotation approach is recommended for training efficiency? a) Annotate general fields across the dataset first, then return for labels b) Annotate only general fields, since they reach good performance faster c) Annotate only labels, because general fields learn from label annotations d) Review labels and general fields on each message in the same pass Q3. In the default Document Understanding Process template, the taxonomy fields used in InvoicePostProcessing.xaml are based on which schema? a) A schema built from hardcoded values written for the sample b) The existing schema of a custom-trained invoice ML model c) The existing schema of the out-of-the-box Invoices ML model d) A schema built from dynamic values generated at runtime Q4. The Segments tab in UiPath Communications Mining Reports loads a number of charts by default, but charts with a very high number of potential values can default to hidden. What are these hidden charts based on? a) General fields b) User properties c) Exception types d) Labels Q5. When designing a UiPath Communications Mining taxonomy, which label category is most often mapped to an organization's service catalog? a) Process / Request types b) Customer experience c) Products / Systems d) Root causes / Exceptions www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 14 Q6. Besides the label names, what should a taxonomy file contain when it is imported into UiPath Communications Mining? a) Label predictions b) Confidence thresholds for each label c) Label descriptions d) Annotated example messages for each label Q7. A team migrates a schema from Document Manager to a Document Understanding modern project. What happens if the schema is imported into a document type that already contains a schema? a) The import fails, but only if documents have already been uploaded to that type. b) The import fails because schema imports are limited to document types with no existing schema. c) The import succeeds and only the missing fields are added to the existing schema. d) The import succeeds and the existing schema is overridden. Q8. A financial institution processes thousands of mortgage application packages every week. During user acceptance testing, reviewers find that several handwritten fields occasionally receive low confidence scores, while most printed fields are extracted successfully. Business stakeholders require high automation rates but insist that incorrect customer information must never be submitted to downstream systems without human verification. Which implementation best satisfies both requirements? a) Send every document to manual review b) Disable confidence thresholds so every field is exported automatically c) Route fields below a confidence threshold to human validation before export d) Exclude the handwritten fields from extraction Q9. Within an AI Center project, what information is required when creating a data labeling session? a) A session name and a dataset b) A session name, a language and a number of documents c) A dataset and the AI Center project d) A session name, a dataset and the AI Center project www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 15 Q10. A multinational telecommunications company is implementing Communications Mining to process customer emails submitted through several regional support portals. During pilot testing, analysts discover that messages imported from one region have incomplete metadata, while another region uses different field names for the same business information. If these inconsistencies remain, analytics, annotation and automation may produce unreliable results across business units. The team wants to correct the issue before production rollout while minimizing future maintenance. Which action should the team perform first? a) Publish a new model version. b) Expand the label categories. c) Increase the model's confidence thresholds. d) Standardize the imported data and metadata. Answer key Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 d d c b a c b c a d SECTION 08 Where to Go Next Re-read the official UiSAI exam description before you book - it is on version 1.5 and the generative topics are the part most likely to grow. When the courseware and your own tenant disagree, the UiPath Forum is where candidates compare notes; the thread linked here opens a community video series that walks through the Specialized AI learning plan and the topics the certification covers, with links to the exam description and the Academy plan. Quick reference Official certification programme - uipath.com/learning/certification Exam description PDF and free practice test - academy.uipath.com/certifications Booking, retake and reschedule rules - pearsonvue.com/us/en/uipath Syllabus, sample questions and practice test - certfun.com/uipath www.certfun.com UiSAI UiPath Certified Professional Specialized AI Professional 16 Before you book — the guide in one card Questions 60 (CertFun) Duration 180 minutes Passing score 70% Exam fee USD 300 Exam sections 17, no official weights Most objectives CM Refine and Maintain, 22 of 141 Level Professional Prerequisite None Validity 3 years Delivery Pearson VUE, centre or OnVUE Product versions 2024.10 (CM 2024.20) Exam number UiPath-SAIv1 Good luck - and as you revise, train rather than read. Every objective in this exam names something you can do in a tenant this week: digitise the document, pick the extractor, route the low-confidence field to a human, label the cluster, check the Model Rating. Do each one once and the question about it answers itself.