Deployed Architect - Professional Services

DXC Technology has partnered with LangChain to bring governed AI agents into mission-critical IT operations. DXC uses LangChain's LangGraph framework within its OASIS orchestration platform, and is licensing the LangSmith platform to develop and evaluate OASIS agents. OASIS is in production and scaling toward 125 customer environments across regulated industries. Across more than 500 measured use cases, DXC says it has cut resolution time by 95% on average, with diagnostic accuracy of 92% or better. Database performance incidents that took two to three hours now take 5-12 minutes. Agents act within defined authority, and sensitive actions can be paused for human approval. Their decisions and tool calls are traced. OASIS is model agnostic and can run on public cloud, private cloud, dedicated, and sovereign environments.

Querit Search API launches Code Search for AI Coding Agents. Sep 30, 2026, 11:00 ET SINGAPORE, Sept. 30, 2026 /PRNewswire/ - Querit, a search infrastructure company purpose-built for AI, today announced the official launch of a dedicated Code Search capability for its core Querit Search API. By simply configuring a single parameter (Vertical=Code), developers can instantly pivot from general web search to a programming-focused search optimized for code generation, IDEs, and deep engineering workflows. Rather than layering a simple filter on top of general web search, Querit treats vertical retrieval as a first-class capability, giving AI coding agents verifiable technical context aligned with programming constraints and helping reduce failures caused by stale, incorrect, or mismatched information. Querit Search API: A Real-Time Information Layer for AI Agents The Querit Search API is a real-time information layer built for AI agents. It runs on Querit's proprietary web index, which covers hundreds of billions of pages, spans multilingual and cross-regional coverage, and draws on authoritative sources from regulatory bodies and standards organizations to technical documentation and professional communities. Unlike traditional link-by-link browsing designed for humans, Querit is built for an agent's end goal of task delivery. Rather than returning only a list of links, it delivers structured, model-ready search results and content designed to support reasoning, grounding, and verification. On FreshQA, a public benchmark for time-sensitive retrieval, the Querit Search API ranked #1 with 83.17% accuracy. The Coding Vertical: Retrieval Rebuilt for Coding Agents Many coding-agent failures come not from high-level reasoning, but from real-world engineering constraints, framework and dependency versions, runtime environments, complexity requirements, and long-tail errors. General-purpose search may surface results that are semantically relevant yet incompatible with those constraints, increasing the risk of incorrect code or failed execution. Querit rebuilt its coding vertical along three axes: * High-quality source prioritization: prioritize official documentation, API references, SDK manuals, and trusted developer communities such as Stack Overflow, while reducing the weight of stale or low-quality secondary content. * Constraint-aware retrieval: specialized models identify programming languages, framework versions, runtime environments, complexity requirements, and error signatures, filtering out results that are semantically relevant but incompatible with the task. * Adaptive, structured output: granularity scales from a single API how-to to an end-to-end task, delivering high-density, clean text within a strict token budget while preserving code blocks and parameters. In internal, programming-focused evaluations, 81% of the results Querit Search API returned were directly adoptable by coding agents across core tasks such as function generation, autocomplete, and debugging - scored under identical token budgets by an LLM-as-a-judge for intent and constraint satisfaction. Asked to "reverse a string in JavaScript without built-in methods or extra data structures, within a set complexity," for example, Querit prioritizes implementations that satisfy every constraint, where control-group results routinely do not. Available Today, Completing the Real-Time Information Layer for AI "The value of an AI agent is in what it can deliver," said Shawn Xu, Head of Global Product at Querit. "General search decides what an agent sees; deep, vertical retrieval decides how good its output is. We're building a real-time information layer that truly understands task intent - and coding is where that architecture proves itself." The Querit Search API and its code vertical are generally available worldwide today. Existing Search API users can enable Code Search without changing endpoints or reworking their integration, simply by setting the code vertical parameter in the request. Beyond direct API access, Querit supports the Model Context Protocol (MCP) and is integrated with agent frameworks and platforms including LangChain, Dify, RAGFlow, CAMEL-AI, Cherry Studio, Eigent, EigenFlux, Continua, ModelOS, and Atlas Cloud, so developers can call it inside the toolchains they already use. Together with the Contents API and Monitors API, the Search API forms a real-time information layer for AI spanning web search, content extraction, and continuous monitoring. Next, coding coverage will expand to major open-source repositories. Read the docs and start a trial at www.querit.ai. About Querit Founded in 2025 and headquartered in Singapore, Querit is a search infrastructure company purpose-built for AI that empowers developers to build systems capable of efficiently searching, retrieving, and processing information from the Open Web. SOURCE Querit

It's trending: Jev by former OpenAI researcher, why is everyone rushing to use it? marsbitPublished on 2026-09-19Last updated on 2026-09-19 Abstract. The AI community is buzzing about Jev, a new "System One Model" from TypeSafe AI, designed for fast, structured judgment calls. Specializing in Yes/No, multiple-choice, and scoring tasks, Jev returns decisions with probabilities, ideal for high-volume, low-latency scenarios. Its popularity is surging as developers integrate it into AI agents to act as a low-cost, high-speed "judge" for tasks like evaluating if an agent's goal is complete, analyzing ad campaigns, or selecting the next action in a browser automation. For instance, it classified 724 real-time ads in about 40 seconds and is being used in projects like `fast-jev-compaction` to intelligently prune AI context. Early benchmarks from TypeSafe suggest dramatic speed and cost advantages, positioning Jev as potential infrastructure for the myriad small, intelligent decisions that could power future AI applications. Named after economist William Stanley Jevons, it embodies the "Jevons paradox": by making intelligent judgments radically cheaper, their overall usage may explode. Machine Heart Editorial Department Recently, a new name has emerged in the AI circle: Jev. Over the past few days, Jev has rapidly trended on X, GitHub, and Agent developer communities. Some used it to analyze 724 real-time ads in 40 seconds, some integrated it into Claude Code to clean up context, others used it for task acceptance testing of AI Agents, and developers have even connected Jev to browser Agents, using it to decide which button to click next or which page to navigate to. LangChain quickly followed up, releasing a Jev-as-a-Judge experiment on September 20th to test its performance as an Agent evaluator. Even OpenAI's "Reset God" Tibo promoted Jev. What exactly is Jev? Simply put, it's an AI specialized in handling "True/False questions." On September 15th, TypeSafe AI officially launched Jev, categorizing such models as "System One Models." According to TypeSafe's definition, these models receive a program state or text information and quickly return structured judgment results along with corresponding probabilities. HTX Group reported on Jev when it was first released. A few days later, its popularity has surged again, with related tweets garnering 37 million views. For example, suppose a customer service system receives an email. A developer can have Jev simultaneously judge: "Is this a sales lead?" "Is the user's sentiment intense?" "Does it require manual intervention?" "Does it belong to billing, technical, or sales issues?" Jev might return a set of probabilities: sales lead: 0.91; requires manual intervention: 0.12; technical issue: 0.83. The application can immediately proceed to the next step based on these numbers. Matija Sosic, Co-founder and CEO of Wasp, also posted a 45-second explanatory video about Jev on X. Currently, Jev offers three core judgment forms: Noul, Choice, and Score. Noul handles Yes/No type judgments, Choice selects answers from given options, and Score rates based on predefined criteria. Each result comes with a probability or confidence score, and multiple questions can be judged simultaneously based on the same input. This design quickly propelled Jev into a rapidly growing application scenario: acting as a "referee" for Agents. Today's AI Agents often need to complete dozens or even hundreds of consecutive steps. After writing code, calling tools, searching the web, and modifying files, the system still needs to judge whether the task is complete. This type of problem perfectly aligns with Jev's mode of operation. Developers can feed an Agent's execution logs to Jev and then ask: "Is the goal achieved?" "Does the result meet requirements?" "Are there any omissions?" "Which quality tier does the current result belong to?" LangChain's latest published experiment follows a similar approach. They had Jev, GPT-5.6 Luna, GPT-5.6 Terra, and Claude Sonnet 4.6 repeatedly score fixed Agent outputs. In this small-scale experiment, Jev averaged about 0.44 seconds per call with a cost of approximately $0.00035, while also demonstrating strong consistency in consecutive scoring. LangChain also emphasized that this is still an early, small-scale test requiring further validation with more Agents and real-world production tasks. A set of data from Jev's performance in ad analysis further boosted its popularity. In an experiment shared by developer Matthew Berman, the system used Jev to analyze 724 real-time ads from 37 brands, classifying them based on Hook, format, Offer, CTA, user cognitive stage, and the consistency between ad and landing page, resulting in a total of 8,724 judgments. According to the data shared by the developer, these tasks were completed in about 40 seconds, with a token cost of about 9 cents, and a median processing time per ad of about 216 milliseconds. This case has been included in the Jev community case library. Another project that spread quickly among developers is called fast-jev-compaction. This Claude Code plugin sends numerous tool calls and terminal outputs to Jev for scoring. Jev judges which content remains relevant to the current task, and then compresses the context sent to the model based on the results. After its release, the project quickly gained significant attention and spawned multiple ported versions. Browser Agents have also become a popular testing ground for Jev. Several open-source projects have already adopted the loop of "browser reads page -> generates candidate actions -> Jev selects action -> browser executes." In a public flight search demo, developers reported the entire search process took about 7 seconds, costing about $0.004. These applications well explain why Jev suddenly caught the attention of Agent developers. Many Agent steps are essentially high-frequency decisions: which button to click, which tool to call, whether this information is relevant, whether the current task is finished, whether a certain result passes acceptance. When these judgments occur hundreds of thousands or even millions of times a day, latency and cost quickly become integral parts of system design. In its own workflow benchmark, TypeSafe claims Jev can achieve up to approximately 193.6x speed improvement and 444.6x cost advantage on certain tasks. TypeSafe also clarifies that these results are at the high end of their estimated practical benefits, and the test set was prepared by the company's model capability team, so these figures are better suited as early references for the technical direction. The naming of Jev also hints at TypeSafe's ambitions. "System One" comes from the System 1 concept proposed by Daniel Kahneman in "Thinking, Fast and Slow," referring to the fast, intuitive judgment system. "Jev" comes from the economist William Stanley Jevons. TypeSafe borrows the meaning of the "Jevons Paradox": when the efficiency of using a resource significantly improves, its overall consumption may instead rapidly increase. In the context of AI, the implication is very clear. When the price of an intelligent judgment drops by orders of magnitude, developers will start incorporating AI in places they previously wouldn't have dared to call a model. Whether a log is important, what type an email belongs to, whether an Agent has completed its task, what cognitive stage an ad is in, which button to choose for a webpage action - these tiny judgments combined could form a massive volume of calls within the next generation of Agent systems. Jev is currently still in early access. Community experiments around it for browsers, code Agents, ad analysis, evaluators, and context management have just begun. But it has already raised a very interesting question: in future AI applications, what truly consumes the most intelligent computing power might be the tens of thousands of small judgments hidden within software processes. And what Jev aims to become is precisely the infrastructure behind these "intelligent if statements." Have you tried Jev yet? What do you think? Reference Links: