AWS launches Kiro powers with Stripe, Figma, and Datadog integrations for AI-assisted coding
Amazon Web Services Introduced on Wednesday Kiro powersa system that allows software developers to give their AI coding assistants immediate, specialized expertise in specific tools and workflows – addressing what the company calls a fundamental bottleneck in the way artificial intelligence agents operate today.
AWS made the announcement at its annual meeting re: Invent conference in Las Vegas. This capability marks a departure from the way most AI coding tools work today. Typically, these tools preload all possible possibilities into memory – a process that burns computer resources and can overwhelm the AI with irrelevant information. Kiro Powers takes the opposite approach and only activates specialized knowledge when a developer actually needs it.
“Our goal is to give the agent a specialized context so they can get to the right result faster – and in a way that also reduces costs,” said Deepak Singh, Vice President of Developer Agents and Experiences at Amazon, in an exclusive interview with VentureBeat.
The launch includes partnerships with nine technology companies: Data hound, Dynatrace, Figma, Neon, Netlify, Postman, Stripe, Supa baseand AWS’s own services. Developers can also create their own powers and share them with the community.
Why AI coding assistants choke when developers plug in too many tools
To understand why Kiro power issues it helps to understand a growing tension in the AI development tools market.
Modern AI coding assistants rely on something called the Model context protocolor MCP, to connect to external tools and services. When a developer wants their AI assistant to work with Stripe for payments, Figma for design, and Supabase for databases, they connect MCP servers for each service.
The problem: Each connection loads dozens of tool definitions into the AI’s working memory before it writes a single line of code. According to AWS documentation, connecting just five MCP servers can consume more than 50,000 tokens — about 40 percent of an AI model’s context window — before the developer even types their first request.
Developers have become increasingly vocal about this problem. Many complain that they don’t want to burn their token allocations just to let an AI agent figure out which tools are relevant for a specific task. They want to get started with their workflow right away and not watch an overloaded agent struggle to sort through irrelevant context.
This phenomenon, which some in the industry call “context rot,” leads to slower responses, lower quality results, and significantly higher costs – as AI services typically charge per token.
Within the technology that loads AI expertise on demand
Kiro Power tackles this by packaging three components into one dynamically charged bundle.
The first component is a control file called POWER.md, which acts as an onboarding guide for the AI agent. It tells the agent what tools are available and, crucially, when to use them. The second part is the MCP server configuration itself: the actual connection to external services. The third contains optional hooks and automations that trigger specific actions.
When a developer mentions “payment” or “checkout” in their conversation with Kiro, the system automatically activates the Stripe power, putting the tools and best practices into context. When the developer switches to database work, Supabase is activated while Stripe is deactivated. Basic context usage when no privileges are active approaches zero.
“You click a button and it loads automatically,” Singh said. “Once a force is created, developers simply select ‘open in Kiro’ and the IDE is launched with everything ready to go.”
How AWS brings elite developer techniques to the masses
Singh described Kiro’s power as a democratization of advanced development practices. Before this capability, only the most advanced developers knew how to properly configure their AI agents with specialized context: writing custom control files, crafting precise prompts, and manually managing which tools were active at any given time.
“We found that our developers were adding capabilities to make their agents more special,” Singh said. “They wanted to give the agent some special powers to solve a specific problem. For example, they wanted their front-end developer, and they wanted the agent to be an expert in backend-as-a-service.”
This observation led to an important insight: if Supabase or Stripe could build the optimal context configuration in one go, every developer using these services could benefit.
“Kiro Power formalizes that – things that people, only the most advanced people, did – and allows anyone to acquire those kinds of skills,” Singh said.
Why dynamic loading is a better fit for most AI coding applications
The announcement also positions Kiro’s powers as a more economical alternative to fine-tuning, the process of training an AI model on specialized data to improve its performance in specific domains.
“It’s much cheaper,” said Singh, when asked how powers compare to sophistication. “Fine tuning is very expensive, and most groundbreaking models cannot be fine-tuned.”
This is an important point. The most capable AI models of Anthropic, Open AIAnd Googling are typically ‘closed source’, meaning developers cannot change their underlying training. They can only influence the models’ behavior through the cues and context they provide.
“Most people are already using powerful models like Sonnet 4.5 or Opus 4.5,” Singh said. “What these models need is to be steered in the right direction.”
The dynamic charging mechanism also reduces running costs. Because permissions are only activated when they are relevant, developers don’t pay to use tokens for tools they don’t currently use.
Where Kiro’s powers fit into Amazon’s larger push on autonomous AI agents
Kiro Powers comes as part of a broader push from AWS toward what the company calls “agentic AI”: artificial intelligence systems that can operate autonomously for extended periods.
Earlier at re:Invent, AWS announced three “frontier agents” designed to run for hours or days without human intervention: the Kiro autonomous software development agent, the AWS Security Agent, and the AWS DevOps Agent. These represent a different approach than the Kiro powers: tackling large, ambiguous problems rather than providing specialized expertise for specific tasks.
The two approaches are complementary. Frontier agents run complex, multi-day projects that require autonomous decision-making across multiple codebases. Kiro’s powers, on the other hand, provide developers with precise, efficient tools for everyday development tasks where speed and token efficiency matter most.
The company is betting that developers need both ends of this spectrum to be productive.
What Kiro does reveals about the future of AI-assisted software development
The launch reflects a maturing market for AI development tools. GitHub Copilot, which Microsoft launched in 2021, introduced millions of developers to AI-assisted coding. Since then, a proliferation of tools has emerged, including Cursor, KlijnAnd Claude Code – have competed for developers’ attention.
But as these tools have become more capable, they have also become more complex. The Model context protocolthat Anthropic open sourced last year, created a standard for connecting AI agents to external services. That solved one problem and created another: the context overload that Kiro is now addressing.
AWS is positioning itself as the company that understands production software development at scale. Singh emphasized that Amazon’s experience running AWS for 20 years, combined with its own massive internal software engineering organization, gives the company a unique insight into how developers actually work.
“It’s not something you would use just for your prototype or your toy application,” Singh said of AWS’ AI development tools. “If you want to build production applications, there is a lot of knowledge that we as AWS bring to the table that applies here.”
The way forward for Kiro powers and cross-platform compatibility
AWS indicated that Kiro forces are currently only within the Kiro IDEbut the company is building cross-compatibility with other AI development tools, including command-line interfaces, Cursor, KlijnAnd Claude Code. The company’s documentation describes a future where developers can “build a force once and use it everywhere” — though that vision remains ambitious for now.
For the technology partners launching powers today, the appeal is simple: Instead of maintaining separate integration documentation for every AI tool on the market, they can create a single power that works everywhere Kiro does. As more AI coding assistants hit the market, that kind of efficiency becomes more and more valuable.
Kiro powers are available now for developers using Kiro IDE version 0.7 or higher, at no additional cost beyond the standard Kiro subscription.
The underlying bet is a familiar one in the history of computing: that the winners in AI-assisted development won’t be the tools that try to do everything at once, but those that are smart enough to know what to forget.
