Durga Analytics training · instructor-led

Professional Agentic Architect Training

Published as a Beta with one year validity, and unusual in shape: three hours of multiple choice, then hands-on labs in Google Skills if you pass.

Six modules mapped to the published blueprint, taught live by practitioners, and built so the capability outlasts the exam. Take it as a scheduled cohort or have it delivered privately to your team.

DA-500 Architect · Architect · 6 modules · cohort or private team delivery

Or take the wider track

This exam is covered by Google Cloud Platform Mastery

If you want the platform rather than the certificate, the mastery track covers everything this exam tests and a good deal it does not. Our programme leads to the certification, not the other way round. Take this page's programme when you need the credential on a date; take the track when you need the capability.

Start here · no exam required · DA-200 to DA-500

Google Cloud Platform Mastery

Google Cloud assumes you think in projects, service accounts and SRE practice. This is where that clicks. A working command of Google Cloud across the resource hierarchy, networking, data and reliability, covering the ground the Associate and Professional certifications examine.

The programme

What it covers

Six modules mapped to the published exam blueprint, each ending in applied work rather than a quiz. The schedule is agreed before the programme starts.

  1. Low-code agents and enterprise data

    State-based workflows with pages, transition routes and event handlers in Agent Designer and CX Agent Studio, plus connecting proprietary and multimodal data through Agent Search.

  2. Coding agents in the development loop

    MCP servers, custom skills and tool access in Antigravity, sandboxing on GKE and Cloud Workstations, and hooks, plugins and subagents extended with Agents CLI.

  3. Developing custom agents

    Model selection across LLM and SLM and self-hosted against SaaS, ADK agents, Memory Bank sessions, RAG with Vector Search and reranking, Agent Identity and Agent Registry.

  4. Orchestration and evaluation

    MCP and Agent2Agent handoffs in parallel, sequential and graph workflows, golden datasets, ADK evalset and autoraters, and continuous evaluation of tool execution.

  5. Deployment, security and governance

    Runtime choice across Agent Runtime, Cloud Run and GKE, reasoning loop and latency troubleshooting, OAuth 2.0 tool calls, principal access boundary policies, Agent Gateway and Model Armor.

  6. Exam drilling

    Timed practice against the real 3 hour, roughly 80 question paper, plus rehearsal for the Google Skills labs that follow a pass.

How it is delivered

Two ways to take it

Both tiers are live, instructor-led delivery. Schedule and depth are agreed before the programme starts rather than fixed in advance.
FeatureCohortEnterprise
FormatScheduled live sessions with a mixed peer groupThe same programme delivered privately to your team
Live sessionsInstructor-led, scheduledInstructor-led, scheduled around your delivery calendar
LabsShared lab scenariosRun against your own estate where access allows
TailoringFixed syllabusSequenced to your platforms, workloads and governance
Exam focusBlueprint coverage plus question-format drillingBlueprint coverage, plus the gaps found in your team's baseline
Group sizeIndividual seatsWhole team, one cohort
Best forOne person preparing around a jobA team standardising on the same platform
Reference

The certification itself

The credential this programme prepares you for, as Google Cloud publishes it. Open the official page from the exam code before you book or budget.

Level
Exam fee
120 USD beta, 200 USD retail
Validity
1 year
Exam version and format. Google publishes this credential in two parts. Part 1 is the proctored exam, 3 hours and around 80 multiple-choice questions in the beta sitting. Part 2 is a distinct set of hands-on labs in Google Skills, issued only after you pass Part 1, which beta candidates must complete by 31 December 2026. GA registration opens mid-November; Google has not published the GA length, fee or validity, so this programme prepares you for the beta format and we will confirm the GA shape with your cohort.

The exam fee is paid to Google Cloud, not to us, and is separate from the programme. See the Google Cloud credential reference for the rest of the ladder and the renewal rules.

Take this programme

Register and we will come back with cohort dates, scope and pricing. For a team, tell us how many people and which platforms you run and we will scope a private delivery.

Independent training. Durga Analytics is not a vendor partner and does not award credentials. Verify exam details officially. We prepare people for the exam; no training provider can guarantee a pass. Credential detail reviewed 15 October 2026.