Customer Support Resolution Agent
Scenario 1 for real: MCP tools, verification gates, spend-cap hooks and structured human handoffs targeting 80%+ first-contact resolution.
*The certification exam is administered independently by Anthropic via Pearson VUE; the exam fee ($125) is paid separately and is not included in tuition.
Proudly Featured In












Built For
This is the design-level credential, built for people who make the architecture, configuration and trade-off calls, not just the people who write the code. Tap any card to see exactly why it fits.
Solution architects designing Claude implementations end to end
Tap to learn moreThe exam tests exactly your judgment: workflow vs agent, hooks vs prompts, plan mode vs direct execution, batch vs realtime. We drill those trade-offs on the official scenarios until they're reflex.
Senior engineers & tech leads who own architecture and configuration decisions
Tap to learn moreYou've shipped Claude systems; now certify the judgment behind them. Coordinator–subagent patterns, tool distribution, CLAUDE.md hierarchies and CI/CD integration, with labs, not theory.
Developers stepping up from CCDV-F to the design-level credential
Tap to learn moreThe natural next rung: Developer proves you can build it, Architect Foundations proves you can design it. Much of the stack overlaps, so your CCDV-F prep compounds here.
Consultants delivering agentic systems who must defend architectural choices to clients
Tap to learn moreEvery exam question is 'what's the most effective change?', the exact question clients ask you. You leave able to justify tool designs, escalation logic and reliability patterns with authority.
Curriculum
Twelve live sessions across 6 weekends. The real exam presents 4 scenarios picked at random out of a published bank of 6, so we simply build all six with you in class, and every module is weighted to match its real share of the exam.

The biggest exam domain starts here: correct loop control flow and the anti-patterns the exam explicitly punishes.


Coordinator–subagent architecture done right: context passing, parallel spawning, and hooks where prompts aren't enough.

Tool descriptions are how models choose, you learn to write ones that never misroute, and error responses that enable recovery.

Team-grade Claude Code: configuration hierarchies, conditional rules, skills, and the plan-mode judgment the exam tests hard.


Automated review pipelines that developers actually trust: headless flags, structured findings and false-positive control.


Explicit criteria over vibes, few-shot where it counts, and schemas that make hallucinated fields impossible.


What separates systems that demo from systems that ship: context discipline, escalation design and provenance.

Rapid-fire question drills on all six scenarios, then two full scenario-based timed mocks and the official registration walkthrough.
Portfolio
Each project, drawn as the system you build: the real tools, and the data moving through them. Scroll; they animate.
Scenario 1 for real: MCP tools, verification gates, spend-cap hooks and structured human handoffs targeting 80%+ first-contact resolution.
Scenario 3: a coordinator with specialised subagents spawned in parallel, claim–source mappings and conflict-preserving synthesis.
Scenarios 2 & 5: a CLAUDE.md hierarchy, glob-scoped rules, forked skills and a CI review pipeline emitting schema-validated findings.
Scenario 6: tool_use schemas with nullable fields, validation-retry with error feedback, and a batch strategy sized to an SLA.
Your consolidated decision matrix — hooks vs prompts, plan vs direct, batch vs realtime, split vs consolidate — the exam’s question style in one artifact.
Two full timed mocks in the real 4-scenario format with percent-correct per domain, mirroring the Pearson VUE score report.
Skills Covered
Tools & Frameworks Covered
Claude Agent SDK
Claude Code
MCP
Claude API
Message Batches API
JSON Schema / PydanticBuilt-in Tools (Grep/Glob/Edit)
GitHub + CI/CD
CLAUDE.md & RulesHooks API
Certification & Partnerships
Every module maps to the current public CCAR-F exam blueprint, v1.0, effective July 2026, and every lab is one of its six published scenarios. A typical self-paced video platform gives you recordings. A generic question bank gives you MCQs. Neither gives you a certified trainer, four real scenario builds on your GitHub, two scored mocks, or a walkthrough of the real Pearson VUE registration. This program does.
Authorized Training & Technology Partners







Anthropic's official, proctored credential at the architecture level. It validates practical judgment about trade-offs in production Claude systems across Claude Code, the Agent SDK, the API and MCP, tested through realistic scenarios. 60 questions, 4 of 6 scenarios, 120 minutes, pass at a scaled 720/1000.
Claude CodeStructured OutputReliability
The certification exam is administered independently by Anthropic through Pearson VUE; the exam fee ($125) is paid separately and is not included in program tuition. Registration currently runs through Anthropic's Partner Academy, we walk you through the official registration process step by step.
Program Creators
Six trainers authorized by industry partners run this program live. Hover any card for their full background.

Johan
Certified Trainer
D365 Customer Service Lead, Power Platform School Founder
More about Johan
D365 Customer Service Lead – Europe at Avanade, and founder of the Power Platform School. A Microsoft Business Applications MVP and Microsoft Certified Trainer based in London, specializing in Dynamics 365 Customer Service and Power Platform.

Akim Nyamande
Certified Trainer
Microsoft, CompTIA, Juniper and Cisco Certified Trainer.
More about Akim
IT training facilitator with over five years of experience and certifications across Microsoft, CompTIA, Juniper, and Cisco. Previously a Network Administrator before moving into technical training, now delivering hands-on courses in networking, systems administration, and cybersecurity fundamentals.

Ali El Khatib
Certified Trainer
Cisco Certified Systems Instructor (CCSI), Microsoft Certified Trainer
More about Ali
Infrastructure Engineer at RHUH with 13 years in the training field, holding CCSI, MCSE, CCNP Routing and Switching, CCNP Security, CompTIA and Microsoft Azure certifications.

Arshad Ahmad
Certified Trainer
Microsoft Certified Trainer (MCT), Cybersecurity & Power Platform Expert
More about Arshad
Technology Trainer with 15 years in strategic client delivery, holding MCT, Azure Solutions Architect Expert, Cybersecurity Architect Expert and Power BI Data Analyst credentials, with 200+ trainings delivered.

Florian Garcia Compte
Certified Trainer
Cisco Certified Systems Instructor (CCSI)
More about Florian
Partner Director at AVAANZA FORMACION, a Cisco Learning Partner based in Madrid. Certified Cisco Systems Instructor (CCSI No. 21053) specializing in Cisco Data Center (ACI/SDN), Nexus, and Wireless, delivering official Cisco certification courses including CCNA, CCNP Enterprise, and CCNP Data Center.

Shantanu Pandey
Certified Trainer
Microsoft, Google, NVIDIA and HPE Certified Trainer
More about Shantanu
Director of Engineering at Meteoros Automation, ranked in Microsoft's Top 100 Trainers of 2025, holding MCT, Google Cloud, NVIDIA and PeopleCert credentials, with 500+ trainings delivered since 2011.

Deep
Certified Trainer
Anthropic Authorized Instructor and AI Cloud Specialist
More about Deep
Seasoned technology leader with over 20 years of experience across AI, cloud computing, and enterprise training. Known for simplifying complex ideas and delivering practical, real world learning.

Sid
Certified Trainer
Anthropic Authorized Instructor and Azure Data Engineer
More about Sid
Dynamic corporate trainer and consultant with more than 10 years of experience across Microsoft Fabric, Azure Data Engineering, and modern cloud platforms. Focused on clear, practical learning that sticks.

Sravia
Certified Trainer
NVIDIA Authorized Instructor and AI Data Specialist
More about Sravia
Passionate AI and data evangelist with over 10 years of experience across machine learning, MLOps, and cloud native technologies. Dedicated to delivering impactful, engaging enterprise training programs.

Vikas Mittal
Certified Trainer
Google and Anthropic Authorized AI Instructor
More about Vikas
Veteran technology trainer with more than 25 years of rich industry experience spanning Google, Microsoft, and emerging AI platforms. An exceptional mentor recognized for proven teaching excellence.

Bipeen
Certified Trainer
AWS, Microsoft, and Anthropic Certified Trainer
More about Bipeen
AI, machine learning, and cloud transformation expert with more than 25 years of experience. A renowned global corporate trainer and conference speaker known for practical, outcome driven sessions.
Student Voices
Coordinates HR operations and talent strategy across territorial branches at UMANA SPA in Veneto, Italy, with over eight years of experience in organizational development.

Eric Mandviwala
HR Operations & Talent Strategy, UMANA SPA
Works as a Senior Spatial Data Analyst at HERE Technologies, specializing in GIS, Python, SQL, and FME, with a track record of building automation processes for large-scale mapping data.

Siriporn Ariyadilak
Senior Spatial Data Analyst, HERE Technologies
Works as a Senior Software Engineer at HERE Technologies, with nearly three years of QA experience testing e-learning web apps across functional, UI, accessibility, and API testing.

Nihar Gawde
Senior Software Engineer, HERE Technologies
Your Certificate
A verifiable, portfolio-ready certificate that signals real, project-tested skill, not just seat time.
Fees & Batch
Claude Certified Architect Prep Course, Foundations (CCAR-F)
EMI options available · Corporate/team batches, contact us
Put it in perspective: the CCAR-F is the design-level Claude credential, and its exam runs on six published scenarios. This cohort builds all six with certified trainers, drills the trade-off judgment every question tests, and runs two scenario-based domain-scored mocks, a full path to the credential, not a self-paced video library.
Bundle & save with add-on courses
Stack these onto your enrollment, built to round out the same skill set employers screen for. Tap any course to add it.
Cloud & Deployment
AI-Specific Add-Ons
Career & Soft Skills
Add-ons are added to your enrollment automatically when you click Enroll Now below.
Where This Takes You
Most companies already have people who can build with Claude. What they are actually short on is someone who can design the system so it survives contact with real users. The Architect Foundations credential is Anthropic's own way of proving you're that person.
AI Solutions Architect 🔥 Highest Paid
Own the design decisions everyone else implements.
Choose the architectures, tool designs and reliability patterns for production Claude systems, and defend them.
Agentic Systems Architect ⚡ Frontier Role
The scarcest specialization in applied AI right now.
Design coordinator–subagent systems, enforcement hooks and escalation logic that survive real traffic.
Claude Platform Lead 🛠️ Mission Critical
Be the person who makes Claude work for the whole org.
Own CLAUDE.md standards, rules, skills, MCP integrations and CI pipelines across teams.
Senior AI Engineer 🏆 In Demand
Step up from building features to owning systems.
Carry design authority on agents, extraction pipelines and review automation, with the credential to match.
AI Consultant / Delivery Architect 🚀 Startup Favorite
Get hired to make the architecture calls.
Scope, design and de-risk client Claude deployments with certified, scenario-tested judgment.
DevEx / AI Tooling Lead 💼 Emerging Role
Own how your engineering org uses AI.
Design the Claude Code workflows, review pipelines and guardrails a whole team ships through.
Live, online, Saturday–Sunday · Only 60 seats · All 6 exam scenarios built before you sit the real 4.
Reserve Your SeatFAQ
Claude Certified Architect – Foundations is Anthropic's official, proctored, architecture-level credential. Uniquely, it's scenario-based: the exam presents 4 realistic production scenarios drawn from a published bank of 6, with 60 questions in 120 minutes via Pearson VUE, passing at a scaled 720/1000. This course builds all six scenarios in class and teaches the five domains in blueprint proportion.
Developer proves you can build it; Architect Foundations proves you can design it. The CCDV-F tests API integration and implementation breadth across 8 domains; the CCAR-F tests architectural judgment, trade-offs, configuration and reliability decisions, through production scenarios. Many engineers take both; if you design systems or review others' designs, this is your track.
Anthropic recommends roughly 6+ months of hands-on experience with the Claude API, Agent SDK, Claude Code and MCP. There are no mandatory prerequisites for the exam, and our labs rebuild each scenario from the ground up, but you should be comfortable reading and writing code, since every lab is a real build.
No. The certification exam is conducted separately by Anthropic through Pearson VUE and its fee of $125 is paid directly at registration. Anthropic currently runs certification registration through its Partner Academy, in the final week we walk you through the official registration and scheduling process step by step, plus exam-day rules and the retake policy.
Both mocks mirror the real structure: 4 scenarios, 60 questions, 120 minutes, in the exam's "which change is most effective?" style. After each you get a domain-wise score report, percent-correct across the 5 domains, just like the real Pearson VUE report, so your final week targets your actual weak areas.
Every session is recorded and you get lifetime access to the recordings, along with the lab files, question bank and community. You can catch up any time and still join the next weekend live.
CCAR-F exam guide: all 5 domains and weightings, the US$125 fee, Anthropic's 6 published scenarios, agentic AI salary data, and an 8-week...
How to pass CCAR-F: the 6 published scenarios and why only 4 reach your sitting, blueprint-proportional study hours, and the 5 ways...
CCAR-F covers 5 exam domains in a 6-week prep cohort; CCAR-P covers 7 plus a capstone architecture defense in 8 weeks. Salary...
CCDV-F and CCAR-F cost the same and sit at the same level. A domain-by-domain comparison of what each tests, and which one...
Model Context Protocol is 18% of the CCAR-F blueprint and appears on CCDV-F. What MCP is, why it exists, and what the...
No salary data exists for Claude-certified people yet. Here is what adjacent AI architect and agentic engineer roles pay in India, and...