Gemini 2.5 Flash-Lite is now usually accessible
The mannequin is Google’s quickest and most cost-effective mannequin, costing $0.10/1M tokens for enter and $0.40/1M tokens for output (in comparison with $1.25/1M tokens for enter and $10/1M tokens for output in Gemini 2.5 Professional).
“We constructed 2.5 Flash-Lite to push the frontier of intelligence per greenback, with native reasoning capabilities that may be optionally toggled on for extra demanding use circumstances. Constructing on the momentum of two.5 Professional and a couple of.5 Flash, this mannequin rounds out our set of two.5 fashions which are prepared for scaled manufacturing use,” Google wrote in a weblog publish.
GitLab Duo Agent Platform enters beta
GitLab Duo Agent Platform is an orchestration platform for AI brokers that work throughout DevSecOps in parallel. For example, a person might delegate a refactoring process to a Software program Developer Agent, have a Safety Analyst Agent scan for vulnerabilities, and have a Deep Analysis Agent analyze progress throughout the repository.
Among the different brokers that GitLab is constructing as a part of this embrace a Chat Agent, Product Planning Agent, Software program Check Engineer Agent, Code Reviewer Agent, Platform Engineer Agent, and Deployment Engineer Agent.
The primary beta is offered for GitLab.com and self-managed GitLab Premium and Final prospects. It features a VS Code extension and JetBrains IDEs plugins, and subsequent month the corporate plans so as to add it to GitLab and broaden IDE assist.
Google provides up to date workspace templates in Firebase Studio that leverage new Agent mode
Google is including a number of new options to its cloud-based AI workspace Firebase Studio, following its replace a number of weeks in the past when it added new Agent modes, assist for MCP, and integration with the Gemini CLI.
Now it’s asserting up to date workspace templates for Flutter, Angular, React, Subsequent.js, and basic Net that use the Agent mode by default. Customers will nonetheless be capable of toggle between the “Ask” and Agent mode, relying on what the duty at hand requires.
The templates now have an airules.md file to supply Gemini with directions for code era, like particular coding requirements, dealing with strategies, dependencies, and growth greatest practices.
Google says will probably be updating templates for frameworks like Go, Node.js, and .NET over the subsequent few weeks as properly.
ChatGPT now has an agent mode
OpenAI is bringing the ability of agentic AI to ChatGPT in order that it may well deal with complicated requests from customers autonomously.
It leverages two of OpenAI’s present capabilities: Operator, which may work together with web sites, and deep analysis, which may synthesize info. In line with OpenAI, these capabilities have been greatest suited to totally different conditions, with Operator scuffling with complicated evaluation and deep analysis being unable to work together with web sites to refine outcomes or entry content material that required authentication.
“By integrating these complementary strengths in ChatGPT and introducing extra instruments, we’ve unlocked totally new capabilities inside one mannequin. It may now actively have interaction web sites—clicking, filtering, and gathering extra exact, environment friendly outcomes. It’s also possible to naturally transition from a easy dialog to requesting actions immediately inside the similar chat,” the corporate wrote in a weblog publish.
YugabyteDB provides new capabilities for AI builders
The corporate added new vector search capabilities, an MCP Server, and built-in Connection Pooling to assist tens of 1000’s of connections per node.
Moreover, it introduced assist for LangChain, OLLama, LlamaIndex, AWS Bedrock, and Google Vortex AI. Lastly, YugabyteDB now has multi-modal API assist with the addition of assist for the MongoDB API.
“At this time’s launch is one other key step in our quest to ship the database of alternative for builders constructing mission-critical AI-powered functions,” stated Karthik Ranganathan, co-founder and CEO, Yugabyte. “As we constantly improve YugabyteDB’s compatibility with PostgreSQL, the expanded multi-modal assist, a brand new YugabyteDB MCP server, and wider integration with the AI ecosystem present AI app builders with the instruments and suppleness they want for future success.”
Composio raises $29 million in Collection A funding
The corporate is attempting to construct a shared studying layer for AI brokers in order that they’ll study from expertise. “You’ll be able to spend a whole bunch of hours constructing LLM instruments, tweaking prompts, and refining directions, however you hit a wall,” stated Soham Ganatra, CEO of Composio. “These fashions don’t get higher at their jobs the best way a human worker would. They’ll’t construct context, study from errors, or develop the refined understanding that makes human employees invaluable. We’re fixing this on the infrastructure stage.”
This funding spherical will probably be used to speed up the event of Composio’s studying infrastructure. The spherical was led by Lightspeed Enterprise Companions, with participation from Vercel’s CEO Guillermo Rauch, HubSpot’s CTO and founder Dharmesh Shah, investor Gokul Rajaram, Rubrik’s co-founder Soham Mazumdar, V Angel, Blitzscaling Ventures, Operator Companions, and Agent Fund by Yohei Nakajima, along with present buyers Elevation Capital and Collectively Fund.
Parasoft brings agentic AI to service virtualization in newest launch
The corporate added an agentic AI assistant to its digital testing simulation answer Virtualize, permitting prospects to create digital companies utilizing pure language prompts.
For instance, a person might write the immediate: “Create a digital service for a cost processing API. There ought to be a POST and a GET operation. The operations ought to require an account id together with different knowledge associated to cost.”
The platform will then draw from the offered API service definitions, pattern requests/responses, and written descriptions of a service to generate a digital service with dynamic conduct, parameterized responses, and the right default values.
Learn final week’s updates right here.
