Terminal X Eval Agent Matches Senior Investor Judgment 88.6% With GPT-6.1 Sol

Terminal X, a startup that builds AI agents for investment firms, reported that its Eval Agent running on GPT-6.1 Sol agreed with senior human reviewers 88.6% of the time across 500 scored judgments, versus 86.4% for the next-best model, an improvement of 220 basis points.

The company's Capital Memory operating system is designed to address what it calls memory debt: when senior investors leave, a firm may keep its documents but lose the reasoning behind its decisions. Terminal X's forward-deployed engineers, who are former finance and investment professionals from JPMorgan and Blackstone, sit with each customer's investment teams, design the firm's agentic architecture, and encode how the firm invests into agents the firm owns, deployed on-premise or in its own cloud.

OpenAI models, including GPT-6.1 Sol and GPT-6 Luna, handle reasoning inside those agents. GPT-6.1 Sol handles stages requiring judgment and a large context window, such as synthesizing investment theses and assessing fit with a firm's mandate, while GPT-6 Luna runs high-volume steps where token efficiency matters more than depth. Terminal X's Eval Agent, an orchestrated workflow on GPT-6.1 Sol and other OpenAI models, checks each agent output against a 54-criterion rubric. GPT-6.1 Sol helped the Eval Agent catch about 25% more recommendations that strayed from a fund's mandate than the next-best model, and ran the same workflows at approximately 30% lower cost per query at similar speed.

According to Terminal X, customers see significant savings from this approach, including one private equity firm that reported $2.4 million in annualized savings from automated due diligence and investment memo workflows. Using GPT-6.1 Sol and GPT-6 Luna, Terminal X has built 1,700 firm Memories, run more than 1 million custom workflows, and reached a weekly active user count equal to 81% of its monthly active users. The company says its next step is to extend firm Memories from desks to individual investment professionals. Co-founder and CEO Hyun Hong said the goal is to make investment judgment measurable so it can be kept, improved, and reused.

Terminal X, a startup that builds AI agents for investment firms, reported that its Eval Agent running on GPT-6.1 Sol agreed with senior human reviewers 88.6% of the time across 500 scored judgments, versus 86.4% for the next-best model, an improvement of 220 basis points.

The company's Capital Memory operating system is designed to address what it calls memory debt: when senior investors leave, a firm may keep its documents but lose the reasoning behind its decisions. Terminal X's forward-deployed engineers, who are former finance and investment professionals from JPMorgan and Blackstone, sit with each customer's investment teams, design the firm's agentic architecture, and encode how the firm invests into agents the firm owns, deployed on-premise or in its own cloud.

OpenAI models, including GPT-6.1 Sol and GPT-6 Luna, handle reasoning inside those agents. GPT-6.1 Sol handles stages requiring judgment and a large context window, such as synthesizing investment theses and assessing fit with a firm's mandate, while GPT-6 Luna runs high-volume steps where token efficiency matters more than depth. Terminal X's Eval Agent, an orchestrated workflow on GPT-6.1 Sol and other OpenAI models, checks each agent output against a 54-criterion rubric. GPT-6.1 Sol helped the Eval Agent catch about 25% more recommendations that strayed from a fund's mandate than the next-best model, and ran the same workflows at approximately 30% lower cost per query at similar speed.

According to Terminal X, customers see significant savings from this approach, including one private equity firm that reported $2.4 million in annualized savings from automated due diligence and investment memo workflows. Using GPT-6.1 Sol and GPT-6 Luna, Terminal X has built 1,700 firm Memories, run more than 1 million custom workflows, and reached a weekly active user count equal to 81% of its monthly active users. The company says its next step is to extend firm Memories from desks to individual investment professionals. Co-founder and CEO Hyun Hong said the goal is to make investment judgment measurable so it can be kept, improved, and reused.