Amazon Web Services on Wednesday introduced Kiro powers, a system that allows software developers to give their AI coding assistants instant, specialized expertise in specific tools and workflows — addressing what the company calls a fundamental bottleneck in how artificial intelligence agents operate today.
\tAWS made the announcement at its annual re:Invent conference in Las Vegas. The capability marks a departure from how most AI coding tools work today. Typically, these tools load every possible capability into memory upfront — a process that burns through computational resources and can overwhelm the AI with irrelevant information. Kiro powers takes the opposite approach, activating specialized knowledge only at the moment a developer actually needs it.
\t"Our goal is to give the agent specialized context so it can reach the right outcome faster — and in a way that also reduces cost," said Deepak Singh, Vice President of Developer Agents and Experiences at Amazon, in an exclusive interview with VentureBeat.
\tThe launch includes partnerships with nine technology companies: Datadog, Dynatrace, Figma, Neon, Netlify, Postman, Stripe, Supabase, and AWS's own services. Developers can also create and share their own powers with the community.
\tWhy AI coding assistants choke when developers connect too many tools
\tTo understand why Kiro powers matters, it helps to understand a growing tension in the AI development tool market.
\tModern AI coding assistants rely on something called the Model Context Protocol, or MCP, to connect with 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.
\tThe 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 — roughly 40 percent of an AI model's context window — before the developer even types their first request.
\tDevelopers have grown increasingly vocal about this issue. Many complain that they don't want to burn through their token allocations just to have an AI agent figure out which tools are relevant to a specific task. They want to get to their workflow instantly — not watch an overloaded agent struggle to sort through irrelevant context.
\tThis phenomenon, which some in the industry call "context rot," leads to slower responses, lower-quality outputs, and significantly higher costs — since AI services typically charge by the token.
\tInside the technology that loads AI expertise on demand
\tKiro powers addresses this by packaging three components into a single, dynamically-loaded bundle.
\tThe first component is a steering file called POWER.md, which functions as an onboarding manual for the AI agent. It tells the agent what tools are available and how to use them. The second component is a set of pre-built workflows that developers can choose from. The third component is a dynamic endpoint system that loads the necessary code modules when needed.
\tBy using this combination, Kiro powers reduces the amount of overhead required for AI coding assistants and allows developers to focus on their workflow without worrying about the tools.
\tImplicazioni pratiche
\tThe launch of Kiro powers has significant implications for how developers work with AI coding assistants. By providing a more efficient way to connect tools and workflows, Kiro powers reduces the amount of overhead required for these assistants and allows developers to focus on their workflow.
\tThis shift is likely to have a major impact on how AI development is done in the future. As AI technology becomes more prevalent, it will be interesting to see how Kiro powers fits into this ecosystem.
\tConclusione
\tAWS' lotta per il mercato del sviluppatore di code con l'intelligenza artificiale sembra avere una risposta interessante con la lancio della Kiro Powers. Questo sistema permette agli sviluppatori di dare un supporto specializzato ai loro assistenti AI, riducendo la quantità di overhead necessaria per queste attività e permettendo ai professionisti di concentrarsi sul proprio lavoro senza dover preoccuparsi dei tool.
\tQuesto sarà sicuramente un punto di riferimento importante nella futura evoluzione della gestione dei code con l'intelligenza artificiale.
💬 Commenti (0)
🔒 Accedi o registrati per commentare gli articoli.
Nessun commento ancora. Sii il primo a commentare!