Technology & Product - OriginTrail's Decentralized Knowledge Graph (DKG) provides verifiable and traceable context for agents [1] - Model Context Protocol (MCP) allows agents to access verifiable knowledge, discover context, and store trusted memory via DKG [1] - OriginTrail is supercharging Microsoft Copilot with verifiable memory [1] Security & Infrastructure - OriginTrail's DKG is secured by Polkadot [1] Partnership & Integration - OriginTrail is partnering with Microsoft to enhance Copilot [1]

Core Insights - Coveo has expanded its partnership with Salesforce to enhance AI capabilities through the Model Context Protocol (MCP) Server on AgentExchange, aiming to improve the accessibility and reliability of enterprise data for AI agents [1][4] - The MCP Server will enable enterprises, particularly in e-commerce, to create and deploy AI agents that can access real-time data, thereby enhancing customer experiences and operational efficiency [2][3] Company Developments - The Coveo MCP Server on AgentExchange will complement the existing Coveo for Agentforce application, providing a more intelligent self-service experience for users and reducing the time needed to find information [3] - Coveo's commitment to customer success is reinforced through this partnership, which aims to unlock the potential of digital labor and ensure effective AI initiatives [4] Industry Context - The partnership highlights the growing importance of modular, scalable, and standards-based systems in the AI landscape, with the MCP being a critical enabler for enterprises to build reliable AI agents [4] - The collaboration is positioned within a multi-trillion dollar market opportunity, emphasizing the potential for businesses of all sizes to engage in the AI agent economy [4]

MCP Origins and Goals - MCP was created to address the challenge of constantly copying and pasting context into LLMs, aiming to give models the ability to interact with the outside world [4][5][6] - The goal is to establish an open-source, standardized protocol for model agency, enabling broader participation in the ecosystem [7][8] - Anthropic believes that enabling model agency is crucial for LLMs to reach the next level of usefulness and intelligence [8] MCP Development and Adoption - MCP was initially developed internally and gained traction during a company hack week [9][10] - Early feedback questioned the need for a new protocol and its open-source nature, given existing tool-calling capabilities [12][13] - Adoption by coding tools like Cursor marked a turning point, followed by broader adoption from Google, Microsoft, and OpenAI [14] Protocol Principles and Updates - The protocol prioritizes server simplicity, even if it increases client complexity, based on the belief that there will be more servers than clients [20][21] - Recent updates include support for streamable HTTP to enable more birectionality for agent communication [19] - Future development focuses on enhancing the agent experience, including elicitation to allow servers to request more information from end users [26][27] - Plans include a registry API to facilitate models finding MCPs independently, further supporting model agency [28] Ecosystem Opportunities - The industry needs more high-quality servers across various verticals beyond dev tools, such as sales, finance, legal, and education [31][34] - There is a significant opportunity in simplifying server building through tooling for hosting, testing, evaluation, and deployment [36] - Automated MCP server generation is a potential future direction, leveraging increasing model intelligence [37] - Tooling around AI security, observability, and auditing is crucial as applications gain more access to external data [38]

My name is Sarmad and today I want to talk about building effective agents with model context protocol or MCP. So a lot has changed in the last year. Um especially as far as agent development is concerned.I think 2025 is the year of agents and uh things like MCP make agent design simpler and more robust than ever before. So I want to talk about what the agent tech stack looks like in 2025. The second thing is a lot of uh MCP servers today are just you know onetoone mappings of existing REST API uh uh servic ...

Financial Data and Key Metrics Changes - Q1 revenue grew 18% year over year in constant currency and 16% on an as-reported basis [7][26] - Subscription revenue increased by 16% year over year, while services and other revenue rose by 13% on an as-reported basis [26] - Domestic revenue grew 16% year over year, and international revenue growth was 19% in constant currency and 15% as reported, representing 47% of total revenue [26] - Average subscription revenue per customer was $11,000 in Q1, down 2% year over year in constant currency and 4% on an as-reported basis [27] - Net revenue retention was 102% in Q1, down two points sequentially as expected [28] - Q1 operating margin was 14%, down one point compared to the year-ago period [28] - Net income was $96 million in Q1 or $1.78 per fully diluted share [29] Business Line Data and Key Metrics Changes - Total customers grew by 19% to over 258,000 globally, with over 10,000 net customer additions in the quarter [8][27] - Large deal growth was strong, up 23% year over year, with significant momentum among the installed base [9] - Free to start conversion improved year over year, driven by better onboarding and product improvements [10] Market Data and Key Metrics Changes - The macro environment remains uncertain, with a heightened focus on value from customers [12][30] - The company is seeing strong demand across all segments, with no significant changes in demand patterns by industry or geography [51] Company Strategy and Development Direction - The company is focusing on AI adoption and has embedded AI across all hubs, aiming to create a unified customer platform [7][14] - The board has authorized a share repurchase program of up to $500 million, signaling confidence in the business and growth opportunities [8][29] - The strategy includes expanding customer agent capabilities and enhancing multi-agent orchestration [22][24] Management's Comments on Operating Environment and Future Outlook - Management acknowledges ongoing macroeconomic uncertainty but emphasizes the company's resilience and ability to deliver value [12][30] - The company expects net additions to moderate to roughly 9,000 and average subscription revenue per customer growth to be approximately flat in the coming quarters [27] - For the full year of 2025, total as-reported revenue is expected to be in the range of $3.036 billion to $3.044 billion, up 16% year over year [32] Other Important Information - The company has launched over 200 new features at its Spring Spotlight event, focusing on AI integration and customer journey enhancements [21][22] - The company is expanding its customer agent capabilities beyond the Service Hub to all Pro and Enterprise customers [20][81] Q&A Session Summary Question: Update on Agent.ai and multi-agent orchestration - Management discussed the progress of Agent.ai and the use of model context protocol for agent communication across hubs [38][40] Question: Contextualizing revised guidance and margin impact from M&A - Management explained the guidance reflects macro uncertainty and highlighted that the impact of M&A on operating profit is minimal [44][48] Question: Customer segments and hesitance in spending - Management noted that there have been no significant changes in demand patterns across segments, emphasizing the platform's essential role for customers [51][52] Question: Pricing for AI solutions and customer adoption - Management detailed the credit-based pricing model for customer agents, aiming to provide predictability and control over spending for customers [70][72] Question: Stability of gross retention and net revenue retention trends - Management confirmed strong momentum from the seat-based pricing model change, with consistent seat upgrade trends [76][78] Question: Expansion of Customer Agent beyond Service Hub - Management expressed confidence in the success of Customer Agent, noting its use across various customer interactions beyond post-sales support [81][84]