Aquarela Cloud Solutions

Aquarela SmartCode

Aquarela SmartCode: AI-assisted development for your team

We implement Kiro, the development environment with AI agents from Amazon Web Services (AWS), or Claude Code, the development tool with AI agents from Anthropic. We train your team to specify before coding.

Tool and licensing setup
We work with you to define Kiro or Claude Code for each role, the number of licenses or seats and the purchasing model.
Implementation and training
We configure your integrated development environment (IDE), command-line interface (CLI), single sign-on (SSO), standards and hooks. Your team practices with a real feature.
Usage and cost governance
We track consumption and cost per developer and work with your team to define usage policies and spend limits.
The challenge

AI-assisted development needs requirements, standards and usage control.

In your team, every bit of rework hurts. When AI goes straight from prompt to code, intent gets lost in the chat history and problems show up late, in review or in production.

Implicit requirements

Requirements left out of your request can lead to errors. Your team may only identify edge cases after the code has been written.

Undocumented standards

Your architecture and your team's conventions are passed on case by case, in every pull request review.

Deferred maintenance

Your tests, documentation and test data become outdated between development cycles because they depend on someone remembering to review them.

Unpredictable cost

Your subscriptions are scattered, with no view of who uses what, how much is consumed or the monthly spend cap.

How it works

Specification first, code second.

Your team reviews and approves requirements, design and tasks before implementation. With Kiro, we use native specs; with Claude Code, version-controlled project documents, as a practice in Aquarela's method.

Specify
01
Describe
You describe the goal in natural language, without a single line of code.
02
Record requirements
Kiro generates requirements.md with user stories and acceptance criteria. With Claude Code, your team records requirements in version-controlled documents, following Aquarela's method.
03
Define design and tasks
In Kiro, design.md captures architecture and technical decisions; tasks.md, the implementation sequence. With Claude Code, your team documents these decisions and tasks in the project, without relying on a native specs feature.
Build
04
Review the specification
Your team approves or adjusts the spec before implementation.
05
Implement and test
The Kiro agent or the Claude Code agent runs the tasks, writes the files, runs tests and iterates, following the specification approved by your team.
06
Review the pull request
The approved specification accompanies your pull request and gives reviewers an objective reference.
Maintain
07
Automate with hooks
We configure actions for your tests and documentation. In Kiro, Agent Hooks respond to session events; in Claude Code, hooks run commands defined by your team at specific points in the execution lifecycle.
08
Maintain your standards
Your team maintains architecture and conventions in steering files for Kiro or in CLAUDE.md for Claude Code. These files guide each tool's work on your project.
The gain is not typing faster: it is cutting the rework caused by implicit requirements.
Tool features

Kiro or Claude Code in your daily work.

Specs and project documents

Kiro offers native specs with requirements, design and sequenced tasks. With Claude Code, your team documents requirements, design and tasks in files versioned alongside the code, following Aquarela's method.

Steering files and CLAUDE.md

Steering files give Kiro persistent knowledge of your project. Claude Code reads CLAUDE.md at the start of every session, with your coding standards, architecture decisions and review checklists.

Agent Hooks and hooks

In Kiro, Agent Hooks run commands or prompts on session events. In Claude Code, hooks run commands defined by your team at specific points in the execution lifecycle to enforce rules and automate tasks.

Model Context Protocol (MCP)

Kiro and Claude Code use this open standard to connect to your team's tools and data sources. Kiro also offers Powers for integrations.

Kiro checkpoints

With checkpoints, you can undo the Kiro agent's changes and return to an earlier state.

Kiro CLI and Claude Code in the terminal

Use Kiro CLI or Claude Code in the terminal to work with your code and run commands in your team's development workflow.

What Aquarela delivers

We implement the tools and train your team to develop with AI.

Aquarela leads the work with your team: defines the licensing setup, configures the tools in your workflow, teaches best practices and tracks usage and costs.

01

Tool and licensing setup

We work with you to define which tool fits each role, how many Kiro licenses or Claude Code seats your team needs and the purchasing model. We size and support purchasing, with Claude Code through an Anthropic subscription on Team or Enterprise plans.

02

Implementation in your workflow

We configure identity and access: Kiro with SSO through AWS IAM Identity Center; Claude Code with SSO and administration on Anthropic's Team or Enterprise plans. We integrate the tool into your pull request workflow and configure least-privilege permissions with AWS Identity and Access Management (IAM) for authorized interactions with your AWS account.

03

Best-practice training

We train your team in specifications before code and in reviewing requirements, design and tasks. We lead a pilot with a real feature from your backlog, from request through specification review to pull request.

04

Steering files and CLAUDE.md

We document your architecture and conventions in steering files to guide the Kiro agent or in CLAUDE.md to guide the Claude Code agent. We configure hooks for your tests and documentation.

05

Usage and cost governance

We track credits per developer in Kiro and usage and cost per user in Claude Code. With your team, we define consumption policies and spend limits using the controls available in your chosen plan.

06

AI pull request review

Add-on

We configure automated review of your pull requests with Amazon Bedrock models, with feedback in your development workflow and support for vulnerability detection.

Plans and purchasing

Kiro by credits; Claude Code by seats and usage.

Aquarela sizes and supports purchasing based on usage measured during your pilot. Kiro uses monthly credits per developer; Claude Code uses seats on Anthropic's Team or Enterprise plans, with their own usage and billing rules.

Tool and planBilling and usageSizing for your team
Kiro Free50 credits/monthAssess whether spec-driven development fits your team.
Kiro ProSubscription; 1,000 credits/monthOccasional Kiro use throughout the week.
Kiro Pro+Subscription; 2,000 credits/monthKiro as a regular part of the workday.
Kiro Pro MaxSubscription; 5,000 credits/monthIntensive development, several hours a day.
Kiro PowerSubscription; 10,000 credits/monthContinuous, high-volume use.
Claude Code - Team StandardMonthly or annual seat; usage limitsSize your team's access to Claude Code based on pilot usage.
Claude Code - Team PremiumMonthly or annual seat; 5x Standard usageSupport profiles that need more usage by combining Standard and Premium seats.
Claude Code - EnterpriseAnnual seat + metered usageSupport your organization with additional identity, audit and spend-limit controls.
  • Kiro: team plans include consolidated billing, usage analytics and SSO through AWS IAM Identity Center.
  • Kiro: plan credits do not roll over between months; add-on credits can be purchased on paid plans and expire after 12 months.
  • Kiro: on Pro, Pro+, Pro Max and Power plans, your content is not used to train models and generated output is covered by intellectual property indemnity, under AWS terms.
  • Anthropic Team: for teams of 2 to 150 people, with Standard and Premium seats that can be combined, monthly or annual billing and usage limits. Includes SSO, usage analytics and user and organization spend controls; your content is not used to train models by default.
  • Anthropic Enterprise: a minimum of 20 seats, annual seat billing and usage billed at application programming interface (API) rates. Administrators set user and organization spend limits; the plan includes SSO, domain capture, provisioning through System for Cross-domain Identity Management (SCIM), audit logs and usage analytics.

Check current prices on the official Kiro pricing page

Phased adoption

Aquarela guides your team from licensing setup to rollout.

We start with your team's roles, implement Kiro or Claude Code in one repository and lead training with a real feature. You decide on expansion using usage and cost data and consumption policies defined with Aquarela.

PHASE 1

Tool and licensing

  • We work with you to define Kiro or Claude Code for each role in your team
  • We size licenses or seats and help you choose the purchasing model
PHASE 2

Tool in your repository

  • We configure identity, SSO and your standards in steering files or CLAUDE.md
  • We configure hooks for tests and documentation and integrate your pull request workflow
PHASE 3

Pilot and training

  • We train your team in specifications before code and in reviewing requirements, design and tasks
  • We guide a real feature from request to pull request and measure usage and cost
PHASE 4

Rollout with governance

  • We work with you to adjust licenses or seats for rollout, based on pilot data
  • We define consumption policies and spend limits and track your usage and costs
Tools and services

Kiro and AWS services, or Claude Code with an Anthropic subscription.

Aquarela guides your team in adopting and using the tools and is an Amazon Web Services (AWS) Advanced Tier Services Partner and an Anthropic partner. Aquarela uses Kiro and Claude Code in its daily work.

Claude Code on Team or Enterprise plans

Aquarela sizes and supports the purchase of your team's seats. Team lets you combine Standard and Premium seats; Enterprise combines seat and usage billing. Check Anthropic's current limits and terms.

View Anthropic plans
Kiro
AI agent IDE and CLI for specification-driven development. AWS ends support for the Amazon Q Developer IDE plugins on April 30, 2027 and recommends Kiro as the replacement. Aquarela plans your transition with a pilot, standards and governance.
Claude Code
Anthropic's development tool with AI agents, purchased per seat on Team or Enterprise plans. In this offering, access to Claude Code is through an Anthropic subscription, not through Amazon Bedrock.
AWS IAM Identity Center
Single sign-on (SSO) and management of the users and groups with Kiro access.
Amazon Bedrock
Generative AI models for automated review of your pull requests, as an add-on to development with Kiro or Claude Code.
AWS Identity and Access Management (IAM)
Least-privilege permissions for authorized interactions with your AWS account, according to the configured integrations.
Get started

Bring AI-assisted development to your team.

Talk to our team and start with a pilot on a real feature from your backlog. Work with Aquarela to determine whether Kiro or Claude Code fits your workflow.

SubjectAquarela SmartCode

By clicking, you'll be redirected to WhatsApp with your information pre-filled.