LegalOn Technologies 在全球范围内提供 Professional AI，利用 AI 支持法律工作及其他关键业务职能。通过将领域专业知识与 AI 相结合，它使人们能够专注于复杂的判断和决策。其目标是实现 AI 驱动的管理，提高业务决策的质量和速度。
这种方法不仅体现在其产品中，还延伸到使组织本身成为 AI 原生组织。该公司将 Codex 集成到其开发流程中，并通过日常使用在整个组织内扩大采用范围。
随着采用逐渐深入，一个新的挑战出现了：成本控制。无限制使用高性能模型可能会推高支出，而一刀切的限制则可能削弱 AI 所带来的生产力提升。
如何在不让开发放缓的情况下降低成本？LegalOn Technologies 通过根据任务复杂度和开发阶段在 GPT‑6（Astra、Luna）和 GPT‑6.1 Sol 之间进行选择，并使预算与每个业务的增长阶段相匹配，应对了这一挑战。该公司在保持开发速度的同时将成本减半。
优化模型以保持开发速度并降低成本
该公司最初让开发者无限制访问其主模型 GPT‑5.5 的 Fast 模式。他们将其使用扩展到设计、实现和日常工作，通过实验学习如何在人与 AI 之间最好地划分职责。
然而，继续无限制使用高性能模型将不可避免地超出年度预算。该公司的 AI 驱动开发 CoE（AID CoE）开始制定模型选择指南。AID CoE 测试并监控模型，而管理者则与各自团队分享其发现。这使每位工程师都能独立为每项任务选择最合适的模型。
将模型与任务匹配并战略性地分配资源
新指南使该公司从每项任务都使用能力最强的模型，转向为工作选择合适的模型。团队从轻量级模型开始，随着任务复杂度增加再转向能力更强的模型。
为支持治理，该公司还通过管理员设置引入了系统控制，对部门和个人设置每月使用限额。AID CoE 监控使用情况，并根据业务需求调整限额。
在这些控制措施下进行的内部测试帮助使选择标准更加具体。GPT‑6 Luna 是最轻量的模型，处理需求明确的代码实现；GPT‑6.1 Sol 支持标准设计、数据分析和文档准备；GPT‑6 Astra 是能力最强的模型，处理高级判断，包括架构设计。将模型与任务匹配逐渐成为各团队的共同实践。
针对不同任务在三种模型之间进行选择
GPT-6 Luna
日常执行与实现；运行日常自动化；委派相对简单的任务和分析；代码实现，主要作为子代理。
GPT-6.1 Sol
标准设计与分析；相对简单的软件设计；常规数值分析和文档创建；完成时间要求短于使用 Luna 的任务。
GPT-6 Astra
复杂分析、设计与编排；复杂分析和文档创建；复杂软件设计；作为编排者协调代理。
除了模型选择外，该公司还开始默认限制 Fast 模式，仅在需要时允许个别请求。尽管这一变化引发了对开发速度的担忧，但团队采用了并行运行任务等方法来保持性能并顺利过渡。
它还在部门、小组和个人层面引入了 AI 支出预算上限。成熟的 LegalOn 业务被要求将成本效率提高最多约 20%，而处于启动阶段的新业务则获得充裕预算，以鼓励积极使用 AI。
LegalOn Technologies 高级工程经理 Yuta Tokitake 解释说，新业务优先考虑业务速度，而非成本效率。目标是广泛使用 AI 来提高产出，并最终推动业务增长。
模型选择、功能限制以及为每个业务量身定制的预算共同使估计的每日成本降低了约 65%。这种方法使整体预算保持可控，同时将资源导向公司希望增长的业务。
结果一览
模型优化和战略性资源分配带来了以下结果：
从每项任务都使用能力最强的模型，转向根据任务复杂度和开发阶段选择 GPT‑6 Astra、GPT‑6.1 Sol 或 GPT‑6 Luna。
在默认限制 Fast 模式后，开发性能得以保持，并得到团队实践（如并行任务执行）的支持。
预算上限将成熟业务约 20% 的效率提升与对新业务的积极投资结合起来。
通过在 GPT‑6 和 6.1 模型之间进行选择，与 GPT‑5.5 相比，估计每日成本降低了 65%。
通过功能发布衡量 AI 投资的真实 ROI
通过模型优化，该公司在不牺牲开发速度或质量的情况下降低了成本。团队也看到 AI 正在稳步缩短从开发到发布的周期。
但该公司着眼更长远。仅凭更快的开发就能使 AI 投资成功吗？更快的开发与客户价值之间的联系仍不明确。“AI 能够加速系统开发和更新几乎已是理所当然，”Tokitake 说。“我们真正想了解的是，这种更快的开发是否真的转化为客户价值。”
这个问题促使该公司开发了自己的指标，将评估 AI 投资的基础从开发速度和使用量转向客户价值。
Tokitake 解释说：“使用 AI 时，我们可以跟踪单个任务的成本，但一项完整工作——一次功能发布——的总成本往往仍是黑箱。因此，我们围绕每次功能发布作为一个单一单位来设计衡量方式。通过将该发布所交付的客户价值与投入其中的实际 AI 成本联系起来，我们旨在使投资回报可见且准确。”
该公司目前正在构建用于计算这一指标的管道。一旦完成，它将使以客户价值衡量的真实 ROI 变得可见。LegalOn Technologies 正在超越 AI 成本管理，迈向将技术投资与业务价值直接连接起来。
构建面向 AI 时代的组织与治理
下一个目标是将个别工程师的AI专业知识转化为整个组织的能力。作为第一步，公司计划建立一个知识库，以收集和分享实践经验。它将捕获诸如设计、实施和审查的最佳模型组合等知识，并迅速将个人成功转化为全公司的最佳实践。
这些由团队实践经验驱动的变化，也在塑造着组织和招聘。AI驱动的生产力提升正促使公司从根本上重新思考人与AI之间的工作分配，以及其劳动力规划。随着投资策略和组织结构的演变，公司已开始在招聘中强调AI技能。
将AI应用转化为持久的竞争优势，需要不断优化治理与团队行动自由之间的平衡。AID CoE和安全团队正携手合作，从多个角度优化性能、成本和风险，构建一个支持全组织实验的灵活框架。
“通过规则和预算施加过多限制可能会削弱组织的动力。我们需要的是一个灵活的运营模式，能有效平衡风险控制与团队所需的速度。”
Yuta Tokitake，LegalOn Technologies高级工程经理
LegalOn Technologies offers Professional AI globally, using AI to support legal work and other key business functions. By combining domain expertise with AI, it enables people to focus on complex judgments and decisions. Its goal is AI-driven management that improves the quality and speed of business decision-making.
This approach extends beyond its products to making the organization itself AI-native. The company integrated Codex into its development process and expanded adoption across the organization through day-to-day use.
As adoption took hold, a new challenge emerged: cost control. Unlimited use of high-performance models could drive up spending, while blanket restrictions risked undermining the productivity gains AI had enabled.
How could it reduce costs without slowing development? LegalOn Technologies addressed this challenge by selecting among GPT‑6 (Astra, Luna) and GPT‑6.1 Sol based on task complexity and development stage, and aligning budgets with each business’s stage of growth. The company halved costs while maintaining development speed.
Optimizing models to maintain development speed and reduce costs
The company initially gave developers unlimited access to its main model, GPT‑5.5 in Fast mode. They expanded its use to design, implementation, and everyday work, learning through experimentation how best to divide responsibilities between people and AI.
Continuing to use high-performance models without limits, however, would inevitably exceed the annual budget. The company's AI-powered Development CoE (AID CoE) began developing guidelines for model selection. AID CoE tested and monitored models, while managers shared its findings with their teams. This enabled each engineer to independently choose the most suitable model for each task.
Matching models to tasks and allocating resources strategically
The new guidelines shifted the company from using the highest-capability model for every task to choosing the right model for the job. Teams started with a lightweight model and moved to more capable models as task complexity increased.
To support governance, the company also introduced system controls through administrator settings, with monthly usage limits for departments and individuals. AID CoE monitors usage and adjusts limits as business needs require.
Internal testing under these controls helped make the selection criteria more specific. GPT‑6 Luna, the lightest model, handles code implementation with clear requirements; GPT‑6.1 Sol supports standard design, data analysis, and document preparation; and GPT‑6 Astra, the most capable model, handles advanced judgment, including architecture design. Matching models to tasks gradually became a shared practice across teams.
Choosing among three models for different tasks
GPT-6 Luna
Everyday execution and implementation; running everyday automations; delegating relatively simple tasks and analysis; code implementation, mainly as a subagent.
GPT-6.1 Sol
Standard design and analysis; relatively simple software design; routine numerical analysis and document creation; tasks requiring shorter completion times than with Luna.
GPT-6 Astra
Complex analysis, design, and orchestration; complex analysis and document creation; complex software design; coordinating agents as the orchestrator.
Alongside model selection, the company began restricting Fast mode by default, allowing individual requests only when needed. Although the change raised concerns about development speed, teams used approaches such as running tasks in parallel to maintain performance and transition smoothly.
It also introduced budget caps for AI spending at the department, group, and individual levels. The established LegalOn business was asked to improve cost efficiency by up to approximately 20%, while new businesses in the launch phase received generous budgets to encourage active use of AI.
Yuta Tokitake, Senior Engineering Manager at LegalOn Technologies, explains that new businesses prioritized business speed over cost efficiency. The aim was to use AI extensively to increase output and ultimately drive business growth.
Together, model selection, feature restrictions, and budgets tailored to each business reduced estimated daily costs by approximately 65%. This approach kept the overall budget under control while directing resources toward businesses the company wanted to grow.
Results at a glance
Model optimization and strategic resource allocation delivered the following results:
A shift from using the most capable model for every task to selecting GPT‑6 Astra, GPT‑6.1 Sol, or GPT‑6 Luna based on task complexity and development stage.
Development performance maintained after restricting Fast mode by default, supported by team practices such as parallel task execution.
Budget caps that combined approximately 20% greater efficiency in mature businesses with active investment in new businesses.
A 65% reduction in estimated daily costs compared with GPT‑5.5 by choosing among GPT‑6 and 6.1 models.
Measuring the true ROI of AI investment through feature releases
Through model optimization, the company reduced costs without sacrificing development speed or quality. Teams are also seeing AI steadily shorten the cycle from development to release.
But the company is looking further ahead. Does faster development alone make AI investment a success? The connection between faster development and customer value remained unclear. “It is almost a given that AI can accelerate system development and updates,” says Tokitake. “What we really want to understand is whether that faster development actually translates into value for customers.”
This question prompted the company to develop its own metric, shifting the basis for evaluating AI investment from development speed and usage volume to customer value.
Tokitake explains: “When using AI, we can track the cost of individual tasks, but the total cost of a complete piece of work—a feature release—often remains a black box. So we designed the measurement around each feature release as a single unit. By linking the customer value that release delivers to the actual AI costs invested in it, we aim to make the return on investment visible and accurate.”
The company is currently building the pipeline to calculate this metric. Once complete, it will make the true ROI in terms of customer value visible. LegalOn Technologies is moving beyond AI cost management toward directly connecting technology investment with business value.
Building an organization and governance for the AI era
The next goal is to turn individual engineers' AI know-how into an organization-wide capability. As a first step, the company plans to build a knowledge base to collect and share practical experience. It will capture knowledge such as the best model combinations for design, implementation, and review, and quickly turn individual successes into company-wide best practices.
These changes, driven by teams' practical experience, are also shaping the organization and hiring. AI-driven productivity gains are prompting the company to fundamentally rethink how work is divided between people and AI, as well as its workforce plans. It has already begun emphasizing AI skills in hiring, as its investment strategy and organizational structure evolve.
Turning AI adoption into a lasting competitive advantage requires continually refining the balance between governance and teams' freedom to act. AID CoE and the security team are working together to optimize performance, cost, and risk from multiple perspectives, building a flexible framework that supports experimentation across the organization.
“Excessive restrictions through rules and budgets can undermine an organization's momentum. What we need is a flexible operating model that effectively balances risk control with the speed teams need.”
Yuta Tokitake, Senior Engineering Manager, LegalOn Technologies
本文内容采集自官方网站，排版和翻译可能与原页面存在差异。
阅读官方全文