How Aptifold investigates, builds and learns
Give Aptifold a difficult question. It can work out what evidence to look for, build the model or tool the investigation calls for, and run checks that show what you can conclude.
From a question to a working result
Aptifold’s agentic operating system organizes the work around AI models. It keeps track of what the project is trying to accomplish, chooses what to investigate next, and uses tools to collect evidence, run calculations and build software. It can write a mathematical model or a program when the work calls for one.
- Frame the problemRecord the goal, constraints and what would change the decision.
- Build a way to test itFind sources and make the model, simulation or analysis.
- Challenge the resultRun the test, examine failures and revise what the evidence calls into question.
- Hand over the workDeliver the result with inputs, assumptions and checks someone can inspect.
You can start with a goal in ordinary language and let Aptifold carry the investigation. You can also work alongside it. A scientist can propose a competing explanation, an engineer can tighten a design limit and a business team can change what counts as an acceptable outcome. Aptifold can find which results depend on that change and redo the relevant work.
In a delivery-planning investigation, Aptifold modeled which routes and storage slots would be available at different times. It searched for bookings that could serve both depots, checked them against pairs of closures and used a separate crate-routing calculation to check the answer. The planner lets a visitor change the booking and inspect where the crates go.
Choose a test that could change the answer
Suppose a star dims every three days. One explanation has one dip in a three-day cycle. Another has two identical, evenly spaced dips in a six-day cycle. Both predict the same dips. A useful next experiment would measure something the two explanations predict differently.
| Cycle | Day 0 | Day 3 | Day 6 | Day 9 |
|---|---|---|---|---|
| 3 days | Dip | Dip | Dip | Dip |
| 6 days | Dip 1 | Dip 2 | Dip 1 | Dip 2 |
Shadow Observatory makes this problem inspectable with 993 archived brightness readings of WASP-126. By default, the workshop uses 390 early readings to fit each candidate and 603 later readings to check the fixed predictions. Its export includes the observations and both predictions, so you can examine where they agree and where either misses a measurement.
Open the timing workshop and compare the predictions.
The reference clock had a later RMS error of 0.179% of normalized brightness. The nearby 3.31-day clock scored 0.221%. Two equal dips per 6.57766-day cycle gave the same predicted light as the reference.
Download the timing record and use node aptifold-timing-verification.mjs to repeat both fits and check the later scores.
How to put a value on another measurement
When the candidate models, measurement noise and downstream decision can be specified, Aptifold can build a numerical model for choosing a test. Expected information gain measures how much a possible observation would change beliefs about the candidate explanations. A decision model can instead score the measurement by how much it improves the action you would take.
Net value = current risk − expected risk after the measurement − measurement cost
Here risk is the expected loss of the best available action given the evidence. The second term averages over the possible readings, each followed by an updated decision. The calculation depends on the proposed models, likelihoods, losses and costs. It earns its place when those inputs make the comparison meaningful. Modern Bayesian Experimental Design.
Check what the result supports
In the gravitational-wave study, Aptifold reproduced a public analysis of GW150914. Five of seven checks matched on the first run. Two absolute peak times differed. It traced the discrepancy to the choice of analysis window and repeated the calculation with the notebook’s convention. All seven checks then matched.
That gave the investigation a checked starting point for a new question. After filtering a noisy signal and keeping fewer samples, how reliable is a quoted 95% uncertainty region? Aptifold made simulated recordings with known signal strengths so it could count how often each analysis included the known values.
| Simulated noise | Reuse the old noise model | Update for filtering |
|---|---|---|
| Narrow interference | 84.5% | 94.8% |
| White noise alone | 95.6% | 94.5% |
The technical difference is where the filter enters the model. If H is the linear processing operator and Σ is the covariance of the original noise, the processed noise has covariance HΣH⊤. This covariance describes how the noise moves together across samples. The comparison isolates the effect of updating it under the stated simulation conditions.
Compare the recorded reproduction runs. Explore the uncertainty results and download the evidence.
A different check answers each question. A reproduction checks whether the same inputs and method lead to the reported result. A controlled simulation checks behavior against a known answer. A reader trying an unfamiliar case checks whether the finished tool helps someone understand or decide. These checks can expose different failures.
What to inspect before relying on a check
Start with the decision and the criterion. A four-crate total can pass while one depot is empty. The delivery plan needs a test of the minimum at each depot under every declared closure. A counterexample that passes the total makes that distinction visible.
Ask how the result was checked and where the checking methods share assumptions. A feasible dispatch and a matching capacity bound establish the modeled maximum. A separate routing calculation can catch an implementation error. Both calculations can share a mistaken estimate of real-world capacity.
Download the delivery verification record. Run node aptifold-delivery-verification.mjs to independently recompute all three acceptance rules from the embedded inputs.
A usable handoff shows the inputs, criterion, observation or calculation, outcome, and open decisions. Aptifold can run these checks within the authority the owner grants. The owner approves a changed requirement, spending, publication, or use of a consequential result. Follow the decision and replay its counterexample.
How Aptifold learns from its work
When a project exposes a mistake or a better approach, Aptifold can trace what happened, change its working method, and test whether that change helps on a different project. It carries forward the evidence and the conditions that make a lesson worth applying.
- Trace the cause
- Aptifold records the earlier result, the assumption or step that caused the problem, and the evidence or rerunnable test that exposed it.
- Find where the lesson applies
- Aptifold records the conditions behind the result. In the filtering study, it repeated the comparison under white noise to see how much the effect depended on the structure of the noise.
- Revise the method
- The operating system can update an instruction, calculation or test and keep the earlier version for comparison. It can revisit the change as new evidence comes in.
- Test whether the lesson carries over
- Aptifold checks a new case where the same problem arises and a similar case where the lesson should stay inactive. It also checks whether the agent can apply the lesson on a later run without a reminder.
Aptifold makes these changes in the working instructions, project knowledge and software it uses around the underlying AI models. When a rule fails to change the result, Aptifold checks whether the agent received the rule when it needed it and how it applied it. That diagnosis guides the fix, from clarifying the rule to bringing it forward at the right moment or correcting the procedure.
For changes under evaluation, Aptifold runs the earlier and revised methods on cases set aside for that purpose. It compares the quality of the results and tracks how much preparation or correction a person had to supply. Feedback from an evaluation case can shape a revision, so Aptifold uses fresh cases to check whether the improvement carries over. See The Reusable Holdout for the underlying evaluation issue.
Bring a result you want to reach
Aptifold can take an open question through research and testing, or work with you as a project develops. The result could be an analysis you can reproduce, an experiment you can run, a decision tool, or an interactive engine. The engines on this site let you inspect and change the inputs to already-built models.