Introducing Eevo

Eevo is SystemOne model trained to be especially good at comparing consequences, understanding stakes, estimating expected value, systems thinking, and adjacent topics. This makes Eevo excellent for all kinds of tasks where consequences matter, such as model routing decisions, decision support for coding agents, or supporting legal review.

In addition to providing a SystemOne-compatible API, Eevo also provides a native API for consequential decisions. To serve requests for this API, Eevo's harness runs hundreds of calls to the underlying SystemOne model to compare consequences, model their overlap, and compute expected value.

Some use cases for both APIs are provided in the cards below:

Every day, AI systems, agents, and humans encounter situations nobody anticipated, and they still have to choose: a fix that helps some customers but risks others. A refund that falls outside policy. Saving today vs. saving in the future.

These cases need to be handled based on their consequences, not predefined rules. Eevo is trained and built to factor consequences into decisions efficiently and reliably.

For AI agents, the result is better choices in your agents’ tasks, a record of each one, and agents that need people less often. Eevo identifies the most uncertain cases, so only those go to people, and teams ship faster. When those questions go to people, they get a clearly structured list of pros and cons for each stakeholder, each one sized, making tradeoffs visible, and helping also humans make better decisions when steering agents.

In automated AI-supported workflows, the result of using Eevo is fast and reliable automated decisions in unexpected situations, along with no need to endlessly attempt to cover any potential scenario with predefined rules or runbooks.

Upright is perhaps an unlikely company to be releasing an AI model. We are around 30 people in Finland, and most folks in Silicon Valley have never heard of us. Fair enough.

But for nine years, we’ve built models that quantify the positive and negative impacts companies have on people and the planet, across 800 impact categories. Our data is today trusted by financial institutions managing over €1 trillion in assets.

At the heart of that work is a close to impossible challenge: making very different outcomes comparable.

Turns out, AI agents (and AI systems more broadly) have the same problem. That’s why we built Eevo.

Which model should make this decision?

Generative models write. Decision models (SystemOne models) pick from a set of options in a single pass. Consequential decision models choose options based on their consequences. Eevo is both a decision model and a consequential decision model.

A generative model writes its answer one token at a time. It is flexible and fluent, and it writes a new answer every time, with its confidence stated, if at all, in prose that software then has to parse.

A decision model, such as Eevo’s System One (or e.g., Jev), answers a typed question about a state, such as yes or no, a choice or a score, in a single forward pass, with a calibrated probability for each option. Its output is built for agents and software to act on.

A consequential decision model, Eevo’s System Two, goes beyond choosing. It learned to size consequences in training, to model how they interact and overlap, and to return calibrated probabilities for the option with the highest expected value. Eevo’s harness runs about a hundred calls to the model for each decision and answers for each stakeholder, across domains, as decision support for agents and for people.

We built Eevo for System Two decisions inside agents. However, our first users found that its training also makes it a very capable general-purpose decision model, as the top score among decision models on the public Jev Decision Index shows (see evaluations).

Where to use Eevo

Decisions inside agents. Agents regularly face situations their instructions leave open, and the right choice depends on what follows from each option. Ship a fix that affects some customers now, or wait for the data that would confirm it. Report that a task cannot be done, or get the answers from a system the agent has no permission to use. Delete stale records, or ask the owner first. When the CTO’s standing instruction and the runbook contradict each other at 03:10 on Black Friday, decide which rule to break.

Decision support for people. Eevo brings structure and rigour to human decisions by comparing outcomes by their magnitude and making the trade-offs visible. A product team weighing a price change for new customers, long-standing customers and the company. A buyer comparing suppliers for the company, its workers and its sustainability targets. A board choosing between investment options for different owner groups. When people disagree, the sized consequences show which trade-off they disagree about.

Automated decisions in code. For high-volume decisions in code, System One decisions work like any other decision model. They fit best when the decision needs judgement beyond following rules.

Try Eevo on your own decisions: new accounts start with 5 free decisions.

Why not just ask the model you already have?

You still can, as Eevo works together with your agent. Your agent is best at gathering the context, identifying relevant stakeholders, listing the options, and identifying the consequences. Eevo helps it to compare the consequences and model their overlap, computing their expected value. This then informs your agent’s judgement. If the result is unexpected, Eevo can also help your agent realize it missed some essential consequences. In addition to helping your agent make better choices autonomously, this makes the tradeoffs also more visible to humans, useful both for monitoring, and when your agent decides it needs human input to proceed.

Eevo-1's training emphasises expected value problems, coherent sizing of consequences, and modelling overlap between consequences. In coherent sizing, Eevo-1 outperforms current frontier models, while being orders of magnitude faster and cheaper to run.

Every answer is a structured record, with its inputs and each stakeholder’s probabilities, that you can log, audit and compare. Close probabilities are also useful: they tell your agent that the options are nearly equal for the stakeholder, or that the decision lacks the facts that would separate them. The agent adds those facts and asks again, or asks a person.

Decide fast, and slow

System One decisions are fast. For high-volume decisions and custom tasks, the decision runs through Eevo-1 in a single call, with sub-second response times. The SystemOne-compatible API takes custom prompts that don't follow the standard Eevo question structure.

System Two decisions are slow and deliberate. When your agent calls Eevo's decision API with a list of options, stakeholders, and consequences, Eevo's harness runs hundreds of tasks through the underlying Eevo-1 decision model to compare their size, model their overlap, and compute their expected value. This takes typically around 5 seconds, and costs $0.15. This is the way we recommend using Eevo for supporting agentic (and human) judgement.

Decisions you can see

When using Eevo's consequential decision APIs, Eevo logs every decision along the decision context and identified consequences for each stakeholder. You see what your software and agents decided, for whom, and how often the stakeholders’ best options differed. Filter the log by agent, person or channel.

The console shows how often stakeholders’ highest-value options differ, day by day, and which pairs of stakeholders disagree most. Every decision traces back to the Slack thread, pull request or issue that prompted it, and to the person it was made for. Record what was actually done, and over time you see how often the model’s answer is followed, and for which stakeholders.

Agents call Eevo through MCP or the REST API. When a choice depends on its consequences, an agent asks Eevo. It says that it did, shares the answer and its result view, acts or asks a person for approval, and records what was done, so the decision appears in your decision log for people to review.

How we trained Eevo

Eevo-1's training emphasizes calibrated probability, expected value tasks, systems thinking, game theory, Fermi estimation, model routing, comparative sizing of consequences, and modelling their overlap.

When the evidence for a decision is mixed, the target is a probability distribution over the options, such as 0.7 and 0.3, with loss being computed against the whole distribution. After training, a single temperature is fitted on questions with known answers, so that options given 70% are the best option about 70% of the time.

Expected value tasks range from business decisions to game-theoretic problems, such as simultaneous non-zero-sum 2×2 games with a single pure-strategy equilibrium, simultaneous zero-sum games with a unique saddle point, finite sequential games solved by backward induction (including bargaining games such as the ultimatum game), and simultaneous public-goods games with three or more players.

This includes both tasks with mathematically correct answer and realistic decision situations that don't have simply "right answer". For the latter, we generated the data by labelling each item twice, by independent methods. Firstly, a large teacher model answers directly using a high reasoning effort, averaged over both option orders and repeated samples. Separately, another model lists each option’s consequences with their probabilities, and a previous iteration of Eevo sizes them, removes overlaps and computes each option’s expected net effect. If both methods choose the same option, the decision is kept; if they disagree, a review keeps it only when the disagreement can be resolved, and otherwise it is discarded. The method is patent pending.

Evaluations

We evaluate Eevo on both public benchmarks and Upright’s own evals, with the latter being centered around economic rationality, systems thinking, cognitive biases, Bayesian reasoning, strategic reasoning with incomplete information, game theory, and other types of expected-value tasks. While Eevo is built for consequential decisions, it is also a highly competitive general-purpose decision model, as Eevo’s training transfers well also to seemingly unrelated tasks.

Coherent consequence sizing

A decision model does not out-reason a frontier model in general. The largest general-purpose models have access to more context, follow longer arguments and handle more kinds of tasks.

Eevo-1 excels in comparative sizing of consequences. To weigh options, every consequence has to be measured on one scale. If a benefit is twice the size of a harm, and that harm is three times the size of a second benefit, the first benefit has to be six times the second. We measure this transitive coherence with Upright’s CoCoCo benchmark, published for the first time in 2025. In this benchmark, we run thousands of pairwise comparisons across a product’s impacts (consequences), use the results to compute “implied” impact sizes that best fit the pairwise comparison results, and then score the models on how close the pairwise comparison results are to the model’s own implied impact sizes. Random answers score about 8, perfectly coherent ones 100.

Eevo-1 scores 85.7. The best general-purpose model, GPT-6 Astra, scores 79.7, 6.0 points lower, at 12 times Eevo-1’s cost.

Eevo’s System Two decision gives each model the part it does better. Your frontier agent reads the situation, lists the options and names each option’s consequences. Eevo-1 sizes those consequences consistently against each other, models where they overlap, and computes each option’s expected value. The answer uses the frontier model’s general knowledge and Eevo-1’s consistent sizing.

For developers

Eevo works great when connected to coding agents, so this is the first thing we encourage developers to try. Beyond that, you can also integrate Eevo directly from code. You can choose from two APIs:

• Eevo’s consequential decision API for consequence-based decision-support for agents, where your agent calls Eevo with information on the decision context, the options, their consequences (optional), and relevant stakeholders, and receive the best option for each stakeholder, along with sized consequences and probabilities.
• SystemOne-compatible API for System One decisions, which works like any decision model, such as Jev.

For more information, read our developer docs. To let an agent read them, point it at the docs’ llms.txt.

Availability and pricing

Eevo-1 is available through the Eevo API, MCP and the Eevo console, with a context of up to 72k tokens. System One decisions, through the SystemOne-compatible API, cost $0.10 per million input tokens, and output is free. A consequence-based decision, which involves ~100 calls to the underlying decision model for comparative sizing of consequences and modelling their overlap, costs a fixed price of $0.15 per decision*. New accounts start with 5 free decisions, each System Two decision revisable up to 10 times.

Eevo’s assistants (Eevo by email, Eevo in Slack and the chat in the Eevo console) additionally use a generative language model, at $4.40 per million input tokens and $22.00 per million output tokens, and new accounts get roughly their first 25 turns free. The decisions they make are priced as above.

Eevo Enterprise adds dedicated capacity for steady volume, deployment on-premise or in your own cloud, and custom versions of Eevo for your use case.

* Each consequence-based decision gets 2 free revisions, additional revisions billed at $0.05 per revision, up to 50. The fixed price covers decisions with typical context size, option descriptions, consequences lists, etc, covering 95% of decisions.

Security and data processing

Built and stored in Europe. Upright builds Eevo in Finland and stores your decisions in the EU. Any paying organization can also keep processing on Eevo’s EU servers only, at no extra cost: choose the EU per request with the eu.eevo.io base URL, or for your whole organization in the Eevo console’s data controls.

• You decide who sees your decisions. You choose whether the decisions you make in the console or through an AI assistant are shared with your organization.
• Help improve Eevo for everyone or opt out whenever. Stored decisions can train future Eevo models in anonymized form, helping solve AI alignment. You can opt out with one switch.
• ISO 27001 certified, with a DPA ready to go. Upright is certified to ISO/IEC 27001. Paying organizations get our data processing agreement, already signed by Upright, straight from the Eevo console.
• No third-party tracking. eevo.io uses no Google Analytics or other third-party tracking tools, so there is no cookie banner.