Emergence AI

Welcome to Emergence, where the future of enterprise workflow automation begins. Listen to exciting words from our co-founders Satya Nitta, Sharad Sundararajan, and Ravi Kokku, Learn Capital's founder and investor Rob Hutter, our research scientist Ashish Jagmohan, and our Chief Design Officer Hélène Alonso as they share how we’re advancing the science and development of #AIagents. Follow us to discover how intelligent agents will unlock the full potential of #AI in enterprise systems.

Exciting times ahead — join us at the AI Action Summit 2025! 🚀 Our Co-Founder and CEO, Satya Nitta, is heading to Paris for the #AIActionSummit on February 10, followed by the #AIBusinessDay at STATION F on February 11. We can't wait to dive into insightful discussions, cutting-edge innovations and connect with industry leaders shaping the future of AI. Looking forward to exploring how AI agents and multi-agent orchestration are driving productivity gains for enterprises worldwide. See you there! #AIActionSummit #ParisAIActionSummit #EmergenceAI

📢 Internship opportunity: Join us at Emergence AI! We’re looking for graduate students to come intern with us at Emergence AI. If you're passionate about multi-agent systems, autonomous agents, and cutting-edge AI research, we’d love to hear from you! Don't miss out on the opportunity to work closely with our team to design, develop, and deploy real-world multi-agent systems, create new algorithms and benchmarks, and deploy optimized cloud-based systems at scale. Join us in NYC or remotely. Apply today 👉 https://lnkd.in/eiXXWpGS #SummerInternship #AIinternship #EmergenceAI

🗞️ Emergence AI in the News! Our Co-Founder and CEO, Satya Nitta, was featured in Business Insider today, sharing insights on DeepSeek AI R1. He highlighted how DeepSeek is a meaningful advance in broadening access to AI reasoning and emphasized the importance of open-source solutions. Read the full article here: https://lnkd.in/eW8Q6bpq #AI #OpenSource #TechNews

Verification agents act as “gatekeepers” in autonomous agent orchestration platforms, and here’s why they’re so crucial 👇   As agent orchestration platforms revolutionize autonomous agent collaboration to solve complex problems, verification agents ensure valid outputs, compliance, and trust while safeguarding system integrity.    Verification agents act as the technical backbone — 𝘃𝗮𝗹𝗶𝗱𝗮𝘁𝗶𝗻𝗴 𝗶𝗻𝘁𝗲𝗿𝗺𝗲𝗱𝗶𝗮𝘁𝗲 𝗮𝗻𝗱 𝗳𝗶𝗻𝗮𝗹 𝗼𝘂𝘁𝗽𝘂𝘁𝘀, 𝗺𝗼𝗻𝗶𝘁𝗼𝗿𝗶𝗻𝗴 𝗶𝗻𝘁𝗲𝗿-𝗮𝗴𝗲𝗻𝘁 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝗰𝗮𝘁𝗶𝗼𝗻, and ensuring adherence to predefined protocols and compliance standards. They detect anomalies, cross-reference outputs against trusted data sources, and provide critical feedback loops to refine agent logic and workflows.    A crucial role played by verification agents is 𝗶𝗱𝗲𝗻𝘁𝗶𝗳𝘆𝗶𝗻𝗴 𝗲𝗿𝗿𝗼𝗿𝘀 𝗲𝗮𝗿𝗹𝘆 within the orchestrator flow, allowing quick fixes, improving performance, and minimizing future problems.    Key responsibilities include:    1. 𝗧𝗮𝘀𝗸 𝘃𝗮𝗹𝗶𝗱𝗮𝘁𝗶𝗼𝗻: Ensuring outputs meet accuracy thresholds and domain-specific rules.  2. 𝗜𝗻-𝗦𝘁𝗲𝗽 𝗩𝗲𝗿𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻: Verifying the intermediate agents' output.  3. 𝗗𝗮𝘁𝗮 𝗶𝗻𝘁𝗲𝗴𝗿𝗶𝘁𝘆 𝗰𝗵𝗲𝗰𝗸𝘀: Verifying quality and consistency of inputs and inter-agent dependencies.  4. 𝗘𝗿𝗿𝗼𝗿 𝗱𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻: Identifying conflicts or discrepancies and triggering fail-safes.  5. 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗺𝗼𝗻𝗶𝘁𝗼𝗿𝗶𝗻𝗴: Analyzing task execution metrics to ensure system scalability and efficiency.    Our verification agents assess key metrics to maintain effective operation of the orchestrator, including:    1. 𝗧𝗮𝘀𝗸 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲: Completion rate, error rate, and latency between agent handoffs.  2. 𝗔𝗰𝗰𝘂𝗿𝗮𝗰𝘆: If the response is factually valid.  3. 𝗖𝗼𝗺𝗽𝗹𝗲𝘁𝗲𝗻𝗲𝘀𝘀: Ensure the response returned is complete based on the ask in the user query.  4. 𝗩𝗮𝗹𝗶𝗱𝗶𝘁𝘆: If the response satisfies the requested task.  5. 𝗥𝗲𝗹𝗶𝗮𝗯𝗶𝗹𝗶𝘁𝘆: Failover success rates, downtime, and API call success rates.    Slide 3 illustrates how the verification agent checks the validity of a response concerning Newton’s non-existent ‘fourth law of motion.’    As AI systems scale, verification agents ensure these platforms remain 𝗿𝗼𝗯𝘂𝘀𝘁 𝗮𝗻𝗱 𝘁𝗿𝘂𝘀𝘁𝘄𝗼𝗿𝘁𝗵𝘆, bridging the gap between innovation and reliability. We'd love to hear your thoughts on verification agents. How do they impact your work? Share your experiences in the comments below!    #MultiAgentOrchestration #VerificationAgent #TrustworthyAI #AutonomousSystems   

Web automation is more than browser clicks — it’s about dynamic planning, implicit and explicit search, and adaptive workflows. Let’s explore how hierarchical dynamic planning and tree search are tackling complex tasks 👇 Web automation is a key agentic capability for Emergence AI. Many general enterprise tasks can be accomplished via web-interface manipulation. There is also a universe of legacy apps that may only be controllable via web interfaces. Additionally, API-using agents can be combined with web automation to yield powerful agentic flows. Our state-of-the-art web agent, Agent-E, uses hierarchical dynamic planning to convert complex high-level user queries and tasks to (often long!) sequences of low-level primitive actions. A critical component of planning is search; planning systems search for sequences of actions to attain a specified goal or maximize rewards. Agent-E employs implicit search: its low-level browser navigation agent selects and executes actions, verifies results, and provides feedback to the high-level planner, allowing for replanning upon failure. This process enables Agent-E to search in the space of actions and recover from failures. There are, of course, other approaches to search-for-planning. Other web automation agents experiment with explicit search methods, often based on tree search, where the agent evaluates a set of candidate actions at each stage. This evaluation can rely on per-step AI critics validating the result of the action and/or on the basis of "rolling out" the entire subsequent sequence of states and actions and evaluating the final result. In both cases, the goodness of evaluated actions and browser states is maintained in a tree structure, driving the search for the next candidate action. Here are some examples of explicit tree-based search: 1. Koh et al. Tree Search for Language Model Agents uses a best-first tree search, achieving significant improvements on the VisualWebArena benchmark. 2. Agent-Q uses Monte-Carlo Tree Search, showing significant improvements on the WebShop dataset. 3. Google's Project Mariner reports significant improvement in task completion rate on the Web-Voyager dataset. But there still remain tradeoffs — a tree-based search needs to maintain several browser states and tends to have high latency when used at runtime. Nonetheless, it offers exciting opportunities for innovation and optimization, with significant implications for agent design and performance. #AI #WebAutomation #AgentE #MCTS #AutonomousSystems

We're pleased to announce the acceptance of our paper to the AI Agent for Information Retrieval (Agent4IR) workshop at the 39th Annual AAAI Conference on Artificial Intelligence 🚀 We will present 'Better RAG using Relevant Information Gain,' co-authored by our Research Scientists and Engineers Marc Pickett, Jeremy H., Ayan Kumar Bhowmick, Raquib Ul Alam, and Aditya Vempaty. This work introduces a state-of-the-art principled retrieval algorithm, Dartboard, that implicitly promotes diversity of retrieved passages by optimizing relevant information gain. We look forward to exploring cutting-edge AI research and impactful enterprise solutions with fellow presenters and attendees! #MultiAgentOrchestration #EmergenceAI #AAAI2025 Association for the Advancement of Artificial Intelligence (AAAI)

Impactful conversations on agents and #GenAI in research at #COMSNETS2025! Our Senior Vice President (Innovations) and India Head, Prasenjit Dey, joined an inspiring panel of leaders from academia and industry at COMSNETS to discuss "Research and Education in the Time of GenAI," which explored: ✔️ GenAI's potential to fundamentally transform how scientists and engineers approach research, emerging as an indispensable tool. ✔️ The ability of GenAI to advance the research process, including how we review literature, infer unseen concept connections, and present hypotheses, accelerating the discovery cycle for various applications. ✔️ How agentic systems are inherently well-suited for such iterative loops of Observation -> Hypothesis generation -> Validation -> Refinement. Thanks to COMSNETS and all the attendees for making this event such a success! Follow our journey as we drive productivity gains and unlock new possibilities with AI for enterprises. #AIagents #MultiAgentOrchestration #ScientificDiscovery

Discover how AI agents can adapt to dynamic and challenging enterprise environments👇 In our recent Live Q&A, our Research Scientist and Manager, Aditya Vempaty, joined our VP of AI Agents, Vivek Haldar, and VP of Developer Relations and Community, Waqas Makhdum, to discuss the launch of our enterprise-grade multi-agent orchestrator and its capabilities. Diving into how our multi-agent orchestrator balances the need for adaptability, determinism, and reliability, Aditya Vempaty shares: ✔️ ⁠How our orchestrator flexibly adjusts to complex enterprise environments, accurately assigning AI agents to specific tasks. ✔️ How the orchestrator strikes a balance between adaptability and determinism, focusing on reliable output. ✔️ How self-improvement enables agents to add new skills and align with evolving enterprise systems for long-term success. Explore real-life use cases with our multi-agent orchestrator and drive productivity gains for your enterprise 🚀 #AIOrchestration #MultiAgentSystems #EmergenceAI

Delighted to share a subset of E-Web: a new Web benchmark that our team at Emergence AI designed to rigorously evaluate Web agents. E-Web aims to set a new standard for assessing AI capabilities in real-world enterprise settings. We are releasing many prompts in the open source, and a paper that describes the methodology in developing the benchmark. Benchmark Paper: https://lnkd.in/e5fgFs4R Benchmark Github: https://lnkd.in/eNsXwk_8 What Sets E-Web Apart? - Skill-centric Design: Core, transferable skills such as form filling, dropdown handling, and file operations that are common across applications. - Real-World Relevance: Enterprise tasks based on tools like Salesforce, JIRA, and LinkedIn. In the evolving landscape of AI, there is a clear need for benchmarks that reflect enterprise use cases. While E-Web is a step forward, we believe that there is much more to explore. We look forward to seeing contributions that extend and enrich this benchmark. Heads-up: Multiple Web agents do poorly on these prompts. We will share the evaluation results soon. #WebAgents #EnterpriseAI #Benchmarks #AgentE #Agents