Birbal AI

Vertex AI Agent Builder

Vertex AI Agent Builder agents, built, run and governed on Google Cloud.

Vertex AI Agent Builder is now part of Gemini Enterprise Agent Platform, Google Cloud's platform to build, scale, govern and optimize agents. Birbal AI builds your agents with the Agent Development Kit (ADK) or Agent Studio, deploys them on Agent Runtime with sessions and memory, connects your tools and data, and sets up identity, registry and gateway policies before launch.

  • Engineers based in the UAE
  • In your Google Cloud projects
  • Fixed-price or team-based

Agent Platform

Formerly Vertex AI
4Your usersThe Gemini Enterprise app, your website, apps and channels
3Your agentsBuilt with ADK or Agent Studio, on Gemini or other models
2Agent RuntimeSessions, Memory Bank, sandboxes and evaluation
1GovernanceAgent Identity, Agent Registry and Agent Gateway
Illustrative architecture, simplified

Authorized vendor to

  • Ministry of Finance
  • Ministry of Interior
  • DGE Abu Dhabi
  • Etihad Aviation
  • EDGE Group

Delivered for

  • Hindustan Unilever
  • Nokia
  • Linde
  • USA Today
  • JSL

Procurement-ready

  • Emirati national company
  • National ICV certificate
  • Abu Dhabi Government Procurement Gate
  • UAE Ministry of Finance, federal procurement
  • Registered ADNOC vendor

What we build

Agents in code, ready for production on Google Cloud

Agent design

What the agent does, which model it uses from Model Garden (Gemini, Claude and others) and where people review its work.

Build with ADK

Agents and multi-agent systems in code with the open-source Agent Development Kit, or started in Agent Studio and exported to ADK.

Deploy on Agent Runtime

Managed hosting with sessions and Memory Bank, in a Google Cloud region that fits your data rules.

Tools and data

Your APIs, databases and documents as tools, MCP servers, and search over your content with Agent Search.

Govern

Each agent with its own Agent Identity, listed in Agent Registry, and its calls checked by Agent Gateway policies.

Evaluate and observe

Evaluations, traces and dashboards before and after launch, so quality and cost stay visible.

What it costs

How Agent Platform is priced

From Google Cloud's pricing page, checked on 20 November 2026. Rates differ by region and change, so we estimate them with you.

Usage-based

You pay for the model tokens your agents use and for the agent infrastructure they run on, not a per-user licence.

Agent Runtime

Agent Compute at $0.085 per vCPU-hour and Agent Memory at $0.009 per GiB-hour, after a monthly free tier; idle time between turns is not billed.

Sessions and Memory Bank

Storage at $0.30 per GiB a month, plus reads and writes billed in vCPU-hours, for example 1 vCPU-hour per 3 million reads.

Models

Gemini and the other models in Model Garden are billed per token at each model's own rates.

How we work

From a shortlist to a governed rollout

  1. 01

    Discovery

    Your Google Cloud projects, the agent's job and the data and systems it needs.

  2. 02

    First agent

    One agent for one team, built and tested on real cases before anyone else sees it.

  3. 03

    Connect

    Tools, data and identity connected, with gateway policies and evaluations in place.

  4. 04

    Govern and launch

    Permissions, logging and review, then a wider launch with training.

  5. 05

    Run and improve

    Monthly reviews of answers, usage and cost, then the next agents on the list.

Why Birbal AI

Why teams bring us in for Google Cloud agents

Engineers based in the UAE

An Emirati national company in Abu Dhabi, with engineers who work onsite in the UAE or remotely for teams anywhere.

Your tenant, your data

Agents are built in your own accounts and cloud, under your data rules.

People stay in charge

Agents hand over to your staff when they are unsure, and every action they take is logged.

You own the work

Configurations, code and documentation are transferred to you on delivery, with NDAs as standard.

Free estimate

Get a free Vertex AI Agent Builder estimate in 48 hours

Tell us which agents you need and the systems they should use. You get a scope, timeline and cost range within 48 hours, then a fixed-price proposal after a short discovery.

  • Free and no obligation
  • Fixed-price or team-based options
  • NDA on request

4.9/5 average rating · 98% client satisfaction · 150+ clients served

Free Vertex AI Agent Builder estimate

We only use your details to reply to you. Arabic or English, as you prefer.

FAQ

Vertex AI Agent Builder: questions teams ask

What is Vertex AI Agent Builder?

Google Cloud's suite of products to build, scale and govern AI agents in production, including the Agent Development Kit (ADK) and Agent Engine. Since April 2026 it has been part of Gemini Enterprise Agent Platform, which Google describes as the evolution of Vertex AI.

What happened to Vertex AI Agent Engine?

Google renamed it Agent Runtime on Gemini Enterprise Agent Platform. Agent Engine Sessions and Memory Bank are now Agent Platform Sessions and Memory Bank.

Is it the same as Gemini Enterprise?

No. Gemini Enterprise is the app where employees use agents; Agent Platform is where developers build, run and govern them. Agents built on the platform can be delivered to employees through the Gemini Enterprise app.

How much does it cost?

It is usage-based: model tokens at each model's rates, plus Agent Runtime at $0.085 per vCPU-hour and $0.009 per GiB-hour of memory beyond a monthly free tier, and storage and operations for sessions and memory.

Can the agents run in the Middle East?

As of November 2026, Google lists Tel Aviv (me-west1) as the only Middle East location for Agent Runtime, Sessions and Memory Bank, not Doha or Dammam. We choose a region with you based on where your data may be stored and where the model processes it.

Who owns what you build?

You do. The code, agents and settings live in your Google Cloud projects, and their documentation is handed over on delivery.

Agents on Google Cloud, built and governed

Get a scope, timeline and cost range within 48 hours.

Get a free estimate