Instacart has launched a rewards debit card for its contract “shopper” employees. The Instacart Shoppers Rewards Card, which debuted July 1 in partnership with workforce payments platform Branch, lets these workers get free, automatic payouts of their earnings. “We’re doubling down on our dedication to shopping excellence by empowering and rewarding shoppers who consistently deliver exceptional service to customers,” Daniel Danker, chief product officer at Instacart, said. “Instacart shoppers are shopping experts, and they balance efficiency, empathy and skill to serve their communities every day. Through the Cart Star refresh and the new Shopper Rewards Card, we’re recognizing and supporting their incredible work, while providing valuable resources to help shoppers thrive both on and off the platform.” The program lets shoppers have their earnings deposited directly in their Shopper Rewards bank account for free after every batch they complete. If these employees choose to use a different bank account, they’ll be charged $1.50 for the Instant Cashout service. Instacart will roll out the card to its U.S. shoppers in two phases, first in October, and again in April of next year. The card is part of Instacart’s Cart Star program
Clarifai’s tool allows models or MCP tools to run anywhere, on local machines, on-premise servers, or private cloud clusters and connect them directly to its platform via a publicly accessible API enabling to build multistep workflows by chaining local models
Intelligent application development startup Clarifai Inc. has launched AI Runners, a new offering designed to provide developers and MLOps engineers with uniquely flexible options for deploying and managing their AI models. AI Runners allows users to connect models running on their local machines or private servers directly to Clarifai’s platform via a publicly accessible application programming interface. The new offering assists in dealing with the rising demands for computing power at a time that agentic AI and protocols such as Model Context Protocol strain computing resources. The idea with AI Runners is to provide a cost-effective and secure solution for managing the escalating demands of modern AI workloads. AI Runners give developers and enterprises flexibility and control by allowing models or MCP tools to run anywhere, on local machines, on-premise servers, or private cloud clusters. The setup ensures sensitive data and custom models remain within the user’s environment while still benefiting from Clarifai’s platform, eliminating vendor lock-in. Developers can use AI Runners to instantly serve their custom models through Clarifai’s scalable and publicly accessible API, making it easy to integrate AI into applications and build advanced, multistep workflows by chaining local models. “AI Runners is a pivotal feature that sets Clarifai apart, as it is currently the only platform offering this capability, providing a crucial competitive advantage,” said Chief Technology Officer Alfredo Ramos.
Fabi.ai’s feature addresses the challenges of static dashboards and restricted business workflows associated with legacy BI by automating the delivery of personalized, AI-enhanced insights directly to the tools data teams use daily
Fabi.ai announced the launch of Workflows, a revolutionary data insights pipeline feature that enables data and product teams to build automated, intelligent workflows that deliver personalized insights directly to stakeholders’ preferred tools. Unlike legacy BI platforms that create “dashboard graveyards,” Workflows meets business users where they actually work—in Slack, email, and Google Sheets—while leveraging AI in the data analysis process to generate meaningful summaries and actionable recommendations. The product addresses three critical failures of legacy BI: restricted data access that ignores real business workflows, misaligned incentives that prioritize seat sales over insight sharing, and the creation of static dashboards that users ultimately abandon for spreadsheets. Workflows transforms this paradigm by automating the delivery of fresh, AI-enhanced insights directly to the tools teams use daily, without forcing data experts to an advanced degree in the vendor’s tooling. Key capabilities of Workflows include: Universal Data Connectivity: Connect to any data source including Snowflake, Databricks, MotherDuck, Google Sheets, Airtable, and more; Integrated Processing Tools: SQL for querying, Python for advanced analysis, and AI for natural language processing and insight generation working seamlessly together; Smart Distribution: Automatically push AI-generated, customized insights via email, Slack, or Google Sheets on configurable schedules; AI-Powered Analysis: Leverage AI to process unstructured data, extract insights from notes and comments, and generate executive summaries; Python-Native Architecture: Enterprise-grade security with scalable AI processing capabilities
Cloudflare’s pay per crawl service allows content owners to charge AI crawlers for access using HTTP 402 Payment Required responses with options to allow free access, charge configured prices, or block access entirely by using DNS proxying for functionality
Cloudflare has launched a pay per crawl service for content creators and AI companies, offering a new mechanism to monetize digital assets. The service addresses concerns from publishers who want compensation for their contributions to AI training datasets. The system allows content owners to charge AI crawlers for access using HTTP 402 Payment Required responses, providing three options: Allow free access, Charge configured prices, or Block access entirely. The service operates through Cloudflare’s global network infrastructure and requires publishers to use Cloudflare’s DNS proxying for functionality. Applications accepted through a dedicated signup portal. The service addresses the binary choice between complete blocking or uncompensated access, creating a third monetization option for digital content creators. Cloudflare serves as the Merchant of Record, handling billing event recording when crawlers make authenticated requests with payment intent. The company aggregates events, charges crawlers, and distributes earnings to publishers, simplifying financial relationships for smaller publishers lacking individual negotiation leverage. The system anticipates future agentic applications where intelligent agents receive budgets for acquiring relevant content. Pay per crawl represents one solution in the expanding toolkit for content protection, as research indicates AI search visitors provide 4.4 times higher value than traditional organic traffic, creating economic incentives for controlled access rather than complete blocking. The development coincides with Google’s AI Mode expansion and enhanced content labeling requirements. Content creators interested in pay per crawl can apply for private beta access through Cloudflare’s signup portal.
Meta’s new Llama API to use Cerebras ultra-fast inference tech that would allow developers build apps that require chaining multiple LLM calls while offering generation speeds up to 18X faster than traditional GPU-based solutions
Meta announced a partnership with Cerebras Systems to power its new Llama API, offering developers access to inference speeds up to 18 times faster than traditional GPU-based solutions. What sets Meta’s offering apart is the dramatic speed increase provided by Cerebras’ specialized AI chips. The Cerebras system delivers over 2,600 tokens per second for Llama 4 Scout, compared to approximately 130 tokens per second for ChatGPT and around 25 tokens per second for DeepSeek, according to benchmarks from Artificial Analysis. This speed advantage enables entirely new categories of applications that were previously impractical, including real-time agents, conversational low-latency voice systems, interactive code generation, and instant multi-step reasoning — all of which require chaining multiple large language model calls that can now be completed in seconds rather than minutes. The Llama API represents a significant shift in Meta’s AI strategy, transitioning from primarily being a model provider to becoming a full-service AI infrastructure company. By offering an API service, Meta is creating a revenue stream from its AI investments while maintaining its commitment to open models. The API will offer tools for fine-tuning and evaluation, starting with Llama 3.3 8B model, allowing developers to generate data, train on it, and test the quality of their custom models. Meta emphasizes that it won’t use customer data to train its own models, and models built using the Llama API can be transferred to other hosts—a clear differentiation from some competitors’ more closed approaches. Cerebras will power Meta’s new service through its network of data centers located throughout North America, including facilities in Dallas, Oklahoma, Minnesota, Montreal, and California. By combining the popularity of its open-source models with dramatically faster inference capabilities, Meta is positioning itself as a formidable competitor in the commercial AI space. For Cerebras, this partnership represents a major milestone and validation of its specialized AI hardware approach.
Anthropic’s new feature update to enable Claude to incorporate data from SaaS applications into its prompt responses while its Research tool to allow preparing detailed reports about user-specified topics with more thorough analysis
Anthropic updated Claude with a feature called Integrations that will enable the chatbot to access data from third-party cloud services. The company rolled out the capability alongside an enhanced version of Research, a tool it introduced last month. The latter feature enables Claude to prepare detailed reports about user-specified topics. Research can now perform the task more thoroughly than before. The new Integrations capability will enable Claude to incorporate data from software-as-a-service applications into its prompt responses. If customers wish to connect Claude to an application for which a prepackaged integration isn’t available, they can build their own. Anthropic estimates that the process takes as little as 30 minutes. According to the company, developers can further speed up the workflow by using a set of tools that Cloudflare introduced in March to ease such projects. Claude’s new connectors are powered by MCP, a data transfer technology that Anthropic open-sourced. It provides software building blocks that reduce the amount of work involved in connecting a LLM to external applications. OpenAI, Anthropic’s top competitor, rolled out MCP support to its Agents SDK last month. Anthropic added MCP to Claude immediately after open-sourcing the technology last year. Until now, however, the chatbot only supported connections to applications installed on the user’s computer, which limited the feature’s usefulness.
Salesforce’s new benchmark for tackling ‘jagged intelligence’ in CRM scenarios shows leading agents succeed less than 65% of the time at function-calling for the use cases of three key personas: service agents, analysts, and managers
To tackle “jagged intelligence” one of AI’s most persistent challenges for business applications: the gap between an AI system’s raw intelligence and its ability to consistently perform in unpredictable enterprise environments —Salesforce revealed several new benchmarks, models, and frameworks designed to make future AI agents more intelligent, trusted, and versatile for enterprise use. The SIMPLE dataset, a public benchmark featuring 225 straightforward reasoning questions designed to measure how jagged an AI system’s capabilities really are. Perhaps the most significant innovation is CRMArena, a novel benchmarking framework designed to simulate realistic customer relationship management scenarios. It enables comprehensive testing of AI agents in professional contexts, addressing the gap between academic benchmarks and real-world business requirements. The framework evaluates agent performance across three key personas: service agents, analysts, and managers. Early testing revealed that even with guided prompting, leading agents succeed less than 65% of the time at function-calling for these personas’ use cases. Among the technical innovations announced, Salesforce highlighted SFR-Embedding, a new model for deeper contextual understanding that leads the Massive Text Embedding Benchmark (MTEB) across 56 datasets. A specialized version, SFR-Embedding-Code, was also introduced for developers, enabling high-quality code search and streamlining development. Salesforce also announced xLAM V2 (Large Action Model), a family of models specifically designed to predict actions rather than just generate text. These models start at just 1 billion parameters—a fraction of the size of many leading language models. To address enterprise concerns about AI safety and reliability, Salesforce introduced SFR-Guard, a family of models trained on both publicly available data and CRM-specialized internal data. These models strengthen the company’s Trust Layer, which provides guardrails for AI agent behavior. The company also launched ContextualJudgeBench, a novel benchmark for evaluating LLM-based judge models in context—testing over 2,000 challenging response pairs for accuracy, conciseness, faithfulness, and appropriate refusal to answer. Salesforce unveiled TACO, a multimodal action model family designed to tackle complex, multi-step problems through chains of thought-and-action (CoTA). This approach enables AI to interpret and respond to intricate queries involving multiple media types, with Salesforce claiming up to 20% improvement on the challenging MMVet benchmark.
Postman’s agent framework enables developers to build AI agents by discovering the right APIs and LLMs, evaluating them across providers and testing them, and keeping them running reliably
In this exclusive episode of DEMO, Keith Shaw discusses the platform Postman, the world’s leading API collaboration platform. Postman is designed for developers and enterprises to build intelligent AI agents, simplifying the agent-building process, reducing platform sprawl, and unlocking the full potential of APIs and large language models. One key benefit of Postman is its suite to discover the right APIs and LLMs to use in agents, allowing users to test functionality, integrate, and build through the Flows experience all in one platform. Postman leverages internal APIs and connects to hundreds of thousands of public APIs, enabling agents to access tools like Slack, Notion, UPS, and more. The agent framework involves building agents, discovering APIs and models, evaluating and testing them, and keeping them running reliably. Postman’s core workspace includes a made-up company called ShelfWise, which stores all APIs used by the company. Postman supports multiple protocols like HTTP, GraphQL, and gRPC, and has introduced a new request type: LLMs. With the rise of AI, Postman offers options like OpenAI, Google, and Anthropic. Postman also allows users to evaluate multiple models across providers using a collection runner, which can be run manually or integrated into their CI/CD pipeline. It also provides visualization tools to help teams make smarter decisions. Postman AI Agent Builder is available on postman.com, where users can find collections, examples, and Flows to fork and use right away.
Apple and Anthropic are building AI-powered coding platform that generates code through a chat interface, tests user interfaces and manages the process of finding and fixing bugs
Apple and Anthropic have reportedly partnered to create a platform that will use AI to write, edit and test code for programmers. Apple has started rolling out the coding software to its own engineers. The company hasn’t decided whether to make it available to third-party app developers. The tool generates code or alterations in response to requests made by programmers through a chat interface. It also tests user interfaces and manages the process of finding and fixing bugs. Amazon, Meta, Google and several startups have also built AI assistants for writing and editing code. McKinsey said in 2023 that AI could boost the productivity of software engineering by 20% to 45%. This increased efficiency has far-reaching implications for businesses across industries, CPO and CTO Bob Rogers of Oii.ai told. AI-powered tools enable developers to create software and applications faster and with fewer resources. “Simple tasks such as building landing pages, basic website design, report generation, etc., can all be done with AI, freeing up time for programmers to focus on less tedious, more complex tasks,” Rogers said. “It’s important to remember that while generative AI can augment skills and help folks learn to code, it cannot yet directly replace programmers — someone still needs to design the system.”
StarTree integrates Model Context Protocol (MCP) support to its data platform to allow AI agents to dynamically analyze live, structured enterprise data and make micro-decisions in real time
StarTree announced two new powerful AI-native innovations to its real-time data platform for enterprise workloads: Model Context Protocol (MCP) support: MCP is a standardized way for AI applications to connect with and interact with external data sources and tools. It allows Large Language Models (LLMs) to access real-time insights in StarTree in order to take actions beyond their built-in knowledge. Vector Auto Embedding: Simplifies and accelerates the vector embedding generation and ingestion for real-time RAG use cases based on Amazon Bedrock. These capabilities enable StarTree to power agent-facing applications, real-time Retrieval-Augmented Generation (RAG), and conversational querying at the speed, freshness, and scale enterprise AI systems demand. The StarTree platform now supports: 1) Agent-Facing Applications: By supporting the emerging Model Context Protocol (MCP), StarTree allows AI agents to dynamically analyze live, structured enterprise data. With StarTree’s high-concurrency architecture, enterprises can support millions of autonomous agents making micro-decisions in real time—whether optimizing delivery routes, adjusting pricing, or preventing service disruptions. 2) Conversational Querying: MCP simplifies and standardizes the integration between LLMs and databases, making natural language to SQL (NL2SQL) far easier and less brittle to deploy. Enterprises can now empower users to ask questions via voice or text and receive instant answers, with each question building on the last. This kind of seamless, conversational flow requires not just language understanding, but a data platform that can deliver real-time responses with context. 3) Real-Time RAG: StarTree’s new vector auto embedding enables pluggable vector embedding models to streamline the continuous flow of data from source to embedding creation to ingestion. This simplifies the deployment of Retrieval-Augmented Generation pipelines, making it easier to build and scale AI-driven use cases like financial market monitoring and system observability—without complex, stitched-together workflows.