Terminal X positions investment judgment as a data problem. Its Capital Memory operating system is designed for firms that keep documents when senior investors leave but lose the reasoning behind them, a gap Terminal X calls memory debt. The company embeds forward-deployed engineers, many with backgrounds at JPMorgan and Blackstone, with customers to design agentic architecture and encode how a firm invests into agents the firm owns, deployed on-premise or in its own cloud. Reasoning inside those agents runs on OpenAI models: GPT-6.1 Sol and GPT-6 Luna. A separate Eval Agent grades outputs against firm standards. Terminal X says GPT-6.1 Sol helped the Eval Agent catch about 25% more recommendations that strayed from a fund’s mandate and ran the same workflows at approximately 30% lower cost per query than the next-best model.

At each customer, Terminal X engineers spend weeks onsite reverse-engineering the firm’s trusted memos and capturing processes that were never written down, such as how the credit desk screens a borrower or which sources the co-investment team pulls before a memo. Those processes are encoded in hundreds of agents customized by asset class and strategy, with sub-agents for each investment stage. GPT-6.1 Sol handles stages requiring judgment and a large context window: synthesizing the investment thesis, identifying key considerations, and assessing fit with the firm’s mandate. GPT-6 Luna runs high-volume steps where token efficiency matters more than depth. The agents work inside each firm’s private data room and process documents in English, Korean, Japanese, and Chinese. What they learn becomes a firm Memory, a versioned record of how one desk makes one kind of decision, including past analyses, committee decisions, workflow instructions, and house views. Terminal X engineers turn each Memory into a repeatable workflow, and every production query is auditable with its full trail: steps taken, sources retrieved, model used, and reasoning. Terminal X cites one private equity firm that reported $2.4 million in annualized savings from automated due diligence and investment memo workflows.

To check agent answers against the firm’s own standard, Terminal X built an Eval Agent: an orchestrated workflow on GPT-6.1 Sol and other OpenAI models designed to read every agent output the way a VP reads an analyst’s work. It checks each output against a 54-criterion rubric, asking whether numbers, comps, consensus figures, and quotes come from the right sources, whether the narrative holds, and whether the recommendation ties to the house view. Each check scores pass or fail; every fail includes a one-line reason and a better source or corrected text and becomes a Memory. For example, a missed source, a wrong comparable, or a thesis that drifts from the house view is encoded as a new workflow instruction or test case. CTO Ken Lee describes the feedback loop: every answer is evaluated, and whatever the analyst corrects teaches the system more about how that firm works.

Terminal X chooses models based on its own evaluation results. Across 500 scored judgments, its Eval Agent on GPT-6.1 Sol agreed with the senior human reviewer 88.6% of the time, versus 86.4% for the next-best model, an improvement of 220 basis points. One error class where GPT-6.1 Sol outperformed was style drift: a buyout fund with a mandate to find take-private candidates trading at a discount to NAV, underwrite the business, and structure financing might start recommending distressed credit or rescue financing when scenario models suggest a market turn. The Eval Agent on GPT-6.1 Sol caught about 25% more of these departures than the next-best model. Its token efficiency on long-context work also let Terminal X build a deeper review workflow within the same budget: the thesis is tested first against the fund’s mandate, then against recent deals; uncertain verdicts are re-run; and the agent reconciles the results before reporting. That deeper review flagged deals that a single pass on a comparable model had waved through. GPT-6.1 Sol ran the same workflows at about 30% lower cost per query than the next-best model, at similar speed.

Terminal X reports it 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 next step is to extend firm Memories from desks to individuals, so each investment professional’s standard is captured as it is practiced, not only as it is described. CEO Hyun Hong frames the goal as owning judgment as data: “The firms that win the next decade will own their judgment as data. Our job is to make that judgment measurable, so it can be kept, improved, and reused.”