Join the event trusted by enterprise leaders for nearly two decades. VB Transform brings together the people building real enterprise AI strategy.\u00a0Learn more<\/em><\/p>\n\n\n\n Enterprises that want to build and scale agents also need to embrace another reality: agents aren\u2019t built like other software.\u00a0<\/p>\n\n\n\n Agents are \u201ccategorically different\u201d in how they\u2019re built, how they operate, and how they\u2019re improved, according to\u00a0Writer\u00a0CEO and co-founder May Habib.<\/span> This means ditching the traditional software development life cycle when dealing with adaptive systems.<\/p>\n\n\n\n \u201cAgents don\u2019t reliably follow rules,\u201d Habib said on Wednesday while on stage at VB Transform. \u201cThey are outcome-driven. They interpret. They adapt. And the behavior really only emerges in real-world environments.\u201d<\/p>\n\n\n\n Knowing what works \u2014\u00a0and what doesn\u2019t work \u2014 comes from Habib\u2019s experience helping hundreds of enterprise clients build and scale enterprise-grade agents. According to Habib, more than 350 of the Fortune 1000 are Writer customers, and more than half of the Fortune 500 will be scaling agents with Writer by the end of 2025.<\/p>\n\n\n\n Using non-deterministic tech to produce powerful outputs can even be \u201creally nightmarish,\u201d Habib said \u2014 especially when trying to scale agents systemically. Even if enterprise teams can spin up agents without product managers and designers, Habib thinks a \u201cPM mindset\u201d is still needed for collaborating, building, iterating and maintaining agents.<\/p>\n\n\n\n \u201cUnfortunately or fortunately, depending on your perspective, IT is going to be left holding the bag if they don\u2019t lead their business counterparts into that new way of building.\u201d<\/p>\n\n\n>>See all our Transform 2025 coverage here<<<\/strong>\n\n\n One of the shifts in thinking includes understanding the outcome-based nature of agents. For example, she said that many customers request agents to assist their legal teams in reviewing or redlining contracts. But that\u2019s too open-ended. Instead, a goal-oriented approach means designing an agent to reduce the time spent reviewing and redlining contracts.<\/p>\n\n\n\n \u201cIn the traditional software development life cycle, you are designing for a deterministic set of very predictable steps,\u201d Habib said. \u201cIt\u2019s input in, input out in a more deterministic way. But with agents, you\u2019re seeking to shape agentic behavior. So you are seeking less of a controlled flow and much more to give context and guide decision-making by the agent.\u201d<\/p>\n\n\n\n Another difference is building a blueprint for agents that instructs them with business logic, rather than providing them with workflows to follow. This includes designing reasoning loops and collaborating with subject experts to map processes that promote desired behaviors.<\/p>\n\n\n\n While there\u2019s a lot of talk about scaling agents, Writer is still helping most clients with building them one at a time. That\u2019s because it\u2019s important first to answer questions about who owns and audits the agent, who makes sure it stays relevant and still checks if it\u2019s still producing desired outcomes.<\/p>\n\n\n\n \u201cThere is a scaling cliff that folks get to very, very quickly without a new approach to building and scaling agents,\u201d Habib said. \u201cThere is a cliff that folks are going to get to when their organization\u2019s ability to manage agents responsibly really outstrips the pace of development happening department by department.\u201d<\/p>\n\n\n\n Quality assurance is also different for agents. Instead of an objective checklist, agentic evaluation includes accounting for non-binary behavior and assessing how agents act in real-world situations. That\u2019s because failure isn\u2019t always obvious \u2014 and not as black and white as checking if something broke. Instead, Habib said it\u2019s better to check if an agent behaved well, asking if fail-safes worked, evaluating outcomes and intent: \u201cThe goal here isn\u2019t perfection It is behavioral confidence, because there is a lot of subjectivity in this here.\u201d<\/p>\n\n\n\n Businesses that don\u2019t understand the importance of iteration end up playing \u201ca constant game of tennis that just wears down each side until they don\u2019t want to play anymore,\u201d Habib said. It\u2019s also important for teams to be okay with agents being less than perfect and more about \u201claunching them safely and running fast and iterating over and over and over.\u201d<\/p>\n\n\n\n Despite the challenges, there are examples of AI agents already helping bring in new revenue for enterprise businesses. For example, Habib mentioned a major bank that collaborated with Writer to develop an agent-based system, resulting in a new upsell pipeline worth $600 million by onboarding new customers into multiple product lines.<\/p>\n\n\n\n Agentic maintenance is also different. Traditional software maintenance involves checking the code when something breaks, but Habib said AI agents require a new kind of version control for everything that can shape behavior. It also requires proper governance and ensuring that agents remain useful over time, rather than incurring unnecessary costs.<\/p>\n\n\n\n Because models don\u2019t map cleanly to AI agents, Habib said maintenance includes checking prompts, model settings, tool schemas and memory configuration. It also means fully tracing executions across inputs, outputs, reasoning steps, tool calls and human interactions.\u00a0<\/p>\n\n\n\n \u201cYou can update a [large language model] LLM prompt and watch the agent behave completely differently even though nothing in the git history actually changed,\u201d Habib said. \u201cThe model links shift, retrieval indexes get updated, tool APIs evolve and suddenly the same prompt does not behave as expected\u2026It can feel like we are debugging ghosts.\u201d<\/p>\n Daily insights on business use cases with VB Daily<\/strong><\/p>\n If you want to impress your boss, VB Daily has you covered. We give you the inside scoop on what companies are doing with generative AI, from regulatory shifts to practical deployments, so you can share insights for maximum ROI.<\/p>\n \n\t\t\t\t\tThanks for subscribing. Check out more VB newsletters here.\n\t\t\t\t<\/p>\n An error occured.<\/p>\n<\/p><\/div>\n
\n<\/div>Why goal-based agents is the right approach\u00a0<\/strong><\/h2>\n\n\n\n
QA for agents vs software<\/strong><\/h2>\n\n\n\n
New version controls for AI agents<\/strong><\/h2>\n\n\n\n
![\"\"\/](\"https:\/\/venturebeat.com\/wp-content\/themes\/vb-news\/brand\/img\/vb-daily-phone.png\")
\n\t\t\t\t<\/div>\n<\/p><\/div>\n<\/div>\t\t\t<\/div>\r\n