Distributed application development platform Akka, officially known as Lightbend is launching new Akka Agentic Platform that makes it easier to orchestrate teams of AI agents and manage their memory and streaming processes. Akka Agentic Platform features a range of new capabilities that aim to make the behavior of AI agents a bit more predictable. For instance, there’s an Akka Orchestration feature that helps developer teams to guide, moderate and control multi-agent systems, with support for sequential, parallel, hierarchical and human-in-the-loop workflows. Meanwhile, Akka Agents makes it possible to develop goal-directed AI agents and Model Context Protocol-based tools that can reason, act and analyze, and integrate with third-party agentic systems and applications. Another key component is Akka Memory, which allows developers to establish a durable, in-memory resource to aid with AI agent context, history retention and personalized behavior. It supports nanosecond writes and is designed to act as both long- and short-term memory, with replication features in case of any system failures. Finally, the platform includes an Akka Streaming capability for stream processing ambient, adaptive and real-time AI agents capable of continuously processing, aggregating and augmenting live data, video, audio and metrics. These data streams can be ingested from any source and fed into AI agents in real time, keeping them up to date with the world around them. The combination of these capabilities will bring “complete certainty” to AI agents, so they can achieve the required level of accuracy, safety, availability and recovery that’s needed to deploy them in production.
AWS launches Kiro: a ‘spec coding’ developer environment integrated with AI agents that will build in “specs” and use “hooks” that will understand the width and breadth of taking a prototype to production
AWS launched a preview of a new development environment named Kiro, integrated with AI agents for software engineers, which will help them turn ideas into production-ready code. Now in preview, Kiro helps provide speed and resilience to has become known as “vibe coding,” a new way to use development tools to tell an AI assistant what the developer wants built using conversational English and then working with it like a pair programmer or sitting back and letting it do most of the work. Amazon’s newest tool is an integrated development environment, or an IDE, which is a software development interface where software engineers spend most of their time building, coding, testing and compiling software. Traditionally, the experience of vibe coding might start from a blank template or an existing app where a coder prompts the AI to write something. Then they prompt it again to either write more or fix what it wrote. This chain of prompts eventually leads to a final product. Amazon said Kiro will change that with integrated AI agents that will build in “specs” and use “hooks” that will understand the width and breadth of taking a prototype to production. As a result, Amazon calls what Kiro’s new capability “spec coding.” The important thing about this approach is that the code and the agent’s process are completely documented top-to-bottom. Nothing is left out and the developer has a bird’s eye view of how the app or function will be built and is able to guide it from the requirements view before anything happens. Amazon said this eliminates the costly back-and-forth usually associated with vibe coding.
Wolters Kluwer unveils cloud-native and blockchain based bank confirmation platform that enables 100% bank statement retrieval from banks worldwide and entirely online experience and self-serve through a browser-based interface
Wolters Kluwer Tax and Accounting (TAA) unveiled the enhanced CCH Validate, next-generation, cloud-native bank confirmation platform engineered to redefine how audit professionals operate. Purpose-built for speed, security, and intelligence, this fully online solution empowers firms with instant, client-authorized data access and intuitive onboarding—delivering a smarter, faster, and more reliable audit experience. Leveraging advanced technologies—including blockchain for tamper-proof assurance—it enables 100% bank statement retrieval from banks worldwide. Key Features of the New CCH Validate: Entirely Online Experience: Users can self-serve through a browser-based interface and begin using the tool in minutes. Client-Driven Authorization: Clients securely and privately authorize data access, removing the need to wait for bank responses. Trial First: Firms can try the platform before committing. Cloud-Native Architecture: Built for scalability, security, and speed, with compliance to SOC 1, SOC 2, ISO 27001, and audit industry standards. Global Reach: Currently designed to support firms in the U.S., integration across platforms in Canada and the UK will soon follow. Security: Blockchain is leveraged to ensure requests are tamper-proof Audit Trail: Provides a comprehensive and immutable audit trail of the end-to-end process stored in the blockchain. Fraud Prevention: Eliminates the potential for fraud by eliminating human intermediaries in responding to requests.
Liquid AI’s platform offers developers curated catalog of small language models (SLMs) which includes compact models as small as 300MB with various quantization and checkpoint options to simplify deployment on edge devices
Liquid AI has launched LEAP aka the “Liquid Edge AI Platform,” a cross-platform SDK designed to make it easier for developers to integrate small language models (SLMs) directly into mobile applications. The SDK can be added to an iOS or Android project with just a few lines of code, and calling a local model is meant to feel as familiar as interacting with a traditional cloud API. Once integrated, developers can select a model from the built-in LEAP model library, which includes compact models as small as 300MB — lightweight enough for modern phones with as little as 4GB of RAM and up. The SDK handles local inference, memory optimization, and device compatibility, simplifying the typical edge deployment process. LEAP is OS- and model-agnostic by design. At launch, it supports both iOS and Android, and offers compatibility with Liquid AI’s own Liquid Foundation Models (LFMs) as well as many popular open-source small models. Developers can browse a curated model catalog with various quantization and checkpoint options, allowing them to tailor performance and memory footprint to the constraints of the target device. To complement LEAP, Liquid AI also released Apollo, a free iOS app that lets developers and users interact with LEAP-compatible models in a local, offline setting. Apollo is designed for low-friction experimentation — developers can “vibe check” a model’s tone, latency, or output behavior right on their phones before integrating it into a production app. The app runs entirely offline, preserving user privacy and reducing reliance on cloud compute.
OutSystems’s tech enables enterprises of any size to build and scale AI agents that work across the entire enterprise effortlessly for real-time goal interpretation, option evaluation, and decision-making, while controlling tool sprawl through a single platform
OutSystems announced the Early Access Program for OutSystems Agent Workbench which simplifies the transformation of existing business applications, workflows, and tools into intelligent, agentic systems that can reason, plan, and act. With Agent Workbench, organizations of any size can: Build and scale AI agents that work across the entire enterprise effortlessly and safely for real-time goal interpretation, option evaluation, and decision-making, while controlling tool sprawl through a single platform. Seamlessly integrate with custom AI models or leading third-party providers like Azure OpenAI and AWS Bedrock to centralize control over AI and data access, decrease cost, and enable multi-vendor utilization. Ground AI agents with a unified data fabric that connects to diverse enterprise data sources, such as existing OutSystems 11 data and actions, relational databases, data lakes, knowledge retrieval systems like Kendra and Azure AI Search, and even agent memory of past interactions, to ensure accurate and context-rich responses across workflows. Orchestrate multi-agent workflows where agents dynamically adjust process flows based on an understanding of all enterprise systems, with real-time context, reasoning, and decisions to tackle complex tasks—whether working in parallel, sequentially, or hierarchically. This enables collaborative task execution, escalation handling, and human intervention when necessary. Monitor agent performance enterprise-wide with real-time logging, error tracing, and built-in guardrails to ensure transparent, reliable decision-making. Gain full visibility into how AI agents operate at every step—making it easy to audit, troubleshoot behavior, and prevent hallucinations, while building trust through explainability and control.
Google study shows LLMs abandon correct answers under pressure, threatening multi-turn AI systems
A new study by researchers at Google DeepMind and University College London reveals how LLMs form, maintain and lose confidence in their answers. The findings reveal striking similarities between the cognitive biases of LLMs and humans, while also highlighting stark differences. The research reveals that LLMs can be overconfident in their own answers yet quickly lose that confidence and change their minds when presented with a counterargument, even if the counterargument is incorrect. Understanding the nuances of this behavior can have direct consequences on how you build LLM applications, especially conversational interfaces that span several turns. This study confirms that AI systems are not the purely logical agents they are often perceived to be. They exhibit their own set of biases, some resembling human cognitive errors and others unique to themselves, which can make their behavior unpredictable in human terms. For enterprise applications, this means that in an extended conversation between a human and an AI agent, the most recent information could have a disproportionate impact on the LLM’s reasoning (especially if it is contradictory to the model’s initial answer), potentially causing it to discard an initially correct answer. Fortunately, as the study also shows, we can manipulate an LLM’s memory to mitigate these unwanted biases in ways that are not possible with humans. Developers building multi-turn conversational agents can implement strategies to manage the AI’s context.
Liquid AI’s platform enables developers to integrate popular open-source small language models (SLMs) directly into mobile applications just a few lines of code to simplify edge AI deployments
Liquid AI, a startup founded by former MIT researchers, has released the Liquid Edge AI Platform (LEAP), a cross-platform software development kit (SDK) designed to make it easier for developers to integrate small language models (SLMs) directly into mobile applications. The SDK can be added to an iOS or Android project with just a few lines of code, and calling a local model is meant to feel as familiar as interacting with a traditional cloud API. LEAP is OS- and model-agnostic by design, supporting both iOS and Android, and offers compatibility with Liquid AI’s own liquid foundation models (LFMs) as well as many popular open-source small models. The platform aims to create a unified ecosystem for edge AI, offering tools for rapid iteration and deployment in real-world mobile environments. The company also released Apollo, a free iOS app that allows developers and users to interact with LEAP-compatible models in a local, offline setting. The LEAP SDK release builds on Liquid AI’s announcement of LFM2, its second-generation foundation model family designed specifically for on-device workloads. The platform is currently free to use under a developer license, with premium enterprise features available under a separate commercial license in the future.
Codien’s AI agent accelerates the migration from legacy test automation frameworks by generating clean, reliable automation testing scripts from plain English descriptions, understanding source tests, and converting and validating tests in real-time
Codien has launched its new AI agent, designed to simplify and accelerate the transition from legacy test automation frameworks like Protractor and Selenium to the modern Playwright framework, reducing migration time from days or weeks to minutes. It also offers intelligent test creation, helping users write new Playwright tests faster by generating clean, reliable Playwright automation testing scripts from plain English descriptions. Furthermore, Codien ensures accuracy by going beyond simple conversion; it understands your source tests, gradually converts them, and validates each new Playwright test in real-time to ensure correct functionality and that you can trust the results. The user experience is straightforward through an intuitive desktop application, available for macOS, Windows, and Linux. Users simply create a project, scan their source code to automatically discover all test cases, and then initiate the conversion. They can watch Codien convert and validate tests live, one by one, with a clean, intuitive dashboard keeping them updated on progress and status. Built with a local-first architecture, Codien ensures your test files and code remain on your device, keeping your data private and secure. Only minimal, relevant code snippets are securely sent to large language models via encrypted HTTPS, with no files uploaded, stored, or retained after processing. Codien operates on a flexible pay-as-you-go model with no subscriptions or vendor lock-in.
AWS’s new storage solution akin to S3 Bucket can cut the cost of uploading, storing, and querying vectors by up to 90% by eliminating the need for provisioning infrastructure for a vector database
AWS is introducing Amazon S3 Vectors, a specialized storage offering that can cut the cost of uploading, storing, and querying vectors by up to 90% compared to using a vector database. This move is likely to be of interest to those running generative AI or agentic AI applications in the cloud. Machine learning models typically represent data as vectors, which are stored in specialty vector databases or databases with vector capabilities for similarity search and retrieval at scale. AWS proposes that enterprises use a new type of S3 bucket, Amazon S3 Vector, which eliminates the need for provisioning infrastructure for a vector database. AWS has integrated S3 Vectors with Amazon Bedrock Knowledge Bases, Amazon SageMaker Unified Studio, and Amazon OpenSearch Service, ensuring efficient use of resources even as datasets grow and evolve. The OpenSearch integration provides flexibility for enterprises to store rarely accessed vectors to save costs. Developers can dynamically shift these vectors to OpenSearch for real-time, low-latency search when needed.
Tetrate’s solution allows developers to access various AI models with their own API keys and coordinates API calls across multiple LLMs, delegating the tasks assigned by the user to the most appropriate model based on their priorities
Service mesh company Tetrate announced the availability of the Tetrate Agent Router Service, a managed solution that makes it simpler for developers to direct AI queries and requests to AI agents to the most suitable model, based on their priorities, such as query and task complexity, inference costs and model performance or speciality. According to Tetrate, this kind of flexibility is exactly what developers need. The Agent Router Service acts like a centralized tool for controlling AI traffic. It allows them to work around the limitations of various large language models, avoid vendor lock-in and mitigate cost overruns. Tetrate AI Gateway is an open-source project that helps organizations integrate generative AI models and services into their applications. Through its unified API, developers can manage requests to and from multiple AI services and LLMs. With the Tetrate Agent Router Service, developers are getting even more control. It allows them to access various AI models with their own API keys, or use keys provided by Tetrate. It also provides features such as an interactive prompt playground for testing and refining AI agents and generative AI applications, automatic fallback to more reliable and affordable models, plus A/B testing tools for evaluating model performance. It will coordinate API calls across multiple LLMs, delegating the tasks assigned by the user to the most appropriate one. In the case of AI chatbots, the Tetrate Agent Router Service will route the conversation to the most responsive and/or cost-effective model, based on the developer’s priorities. This can help to reduce latency and manage high traffic more efficiently.