Basis（在新窗口中打开）构建 AI 智能体，以自动化会计师每天所做的大量手工工作，帮助他们将时间从重复性任务转向战略性工作。该公司的研究聚焦于能够可靠完成长任务的智能体，而借助 GPT‑6 Astra，它看到模型对会计师想要达成的目标有了更强的理解。
“GPT-6 Astra 在真正理解用户意图和问题方面做得更好。”
——Mitch Troyanovsky，Basis 联合创始人
以一半时间完成 50 个工作表的税务工作簿
Basis 在一个包含 50 个工作表的复杂税务工作簿上比较了 GPT‑6 Astra 和 GPT‑5.6 Sol。任务是准确且可靠地完成该工作簿，而 GPT‑6 Astra 明显更快。
“GPT-6 Astra 能够在 GPT-5.6 Sol 所需时间的一半内完成该工作簿。”
——Mitch Troyanovsky，Basis 联合创始人
Basis 还指出，GPT‑6 Astra 在任务开始时能做出更好的决策，帮助 Basis 的智能体以更直接的路径完成工作，并减少用于纠正错误的时间。Troyanovsky 表示，这也使模型在 token 使用上更高效。
让推理投入与任务相匹配
Basis 还让 GPT‑6 Astra 随着任务推进调整其使用的推理量，在步骤困难时加大计算量，在步骤较容易时减少计算量。该模型可以在保持缓存完整的同时做出这些调整。Troyanovsky 表示，这有助于降低成本和响应时间，使长时间运行的任务对 Basis 及其客户更经济。
在真实世界使用中建立信心
借助 GPT‑6 Astra，Basis 的内部评估分数提升了约 20%，这得益于对用户意图更好的理解，包括何时提问、标记假设以及遵循指令。
Basis 会评估其智能体如何工作以及它们的最终答案，包括它们是否遵循模板、就税务问题查阅一手资料，以及检查自己的工作。GPT‑6 Astra 能够从更广泛的上下文中推断这些期望，而所需的明确指令更少。
这减少了 Basis 为个别情况编写规则的需要，并让团队更有信心，认为其智能体能够处理内部测试未覆盖的情况。
Basis(opens in a new window) builds AI agents to automate much of the manual work that accountants do each day, helping them shift their time from repetitive tasks to strategic work. The company’s research focuses on agents that can reliably complete long tasks, and with GPT‑6 Astra, it’s seeing a stronger understanding of what accountants want to accomplish.
“GPT-6 Astra does a better job of really understanding the intent of the user and the problem.”
—Mitch Troyanovsky, Co-founder, Basis
Completing a 50-tab tax workbook in half the time
Basis compared GPT‑6 Astra and GPT‑5.6 Sol on a complicated tax workbook with 50 tabs. The task was to complete the workbook accurately and reliably, and GPT‑6 Astra was markedly faster.
“GPT-6 Astra is able to complete that workbook in half the time that GPT-5.6 Sol is able to.”
—Mitch Troyanovsky, Co-founder, Basis
Basis also noted that GPT‑6 Astra makes better decisions at the start of a task, helping Basis’s agents take a more direct path through the work with less time spent correcting mistakes. Troyanovsky says that also makes the model more efficient in its use of tokens.
Matching reasoning effort to the task
Basis also has GPT‑6 Astra adjust how much reasoning it uses as a task progresses, dialing up computation when a step is difficult, and using less when a step is easier. The model can make these adjustments while keeping its cache intact. Troyanovsky says this helps reduce cost and response time, making long-running tasks more economical for Basis and its customers.
Building confidence in real-world use
Basis saw about a 20% improvement in its internal evaluation scores with GPT‑6 Astra, driven by better understanding of user intent, including when to ask questions, flag assumptions, and follow instructions.
Basis evaluates how its agents work and their final answers, including whether they follow templates, consult primary sources for tax questions, and check their own work. GPT‑6 Astra can infer these expectations from a broader context, with fewer explicit instructions.
That reduces the need for Basis to write rules for individual situations and gives the team more confidence that its agents can handle situations beyond those covered in internal tests.
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