Verify mission requirements in Ansys STK
Where space requirements actually get answered. The scenario is the result's biggest dependency, so it is recorded in full alongside every number.
The problem this solves
A coverage figure quoted without its constraint set is meaningless, and two runs with different masks are not comparable. Mission analysis results reach a review as a single number, and nobody in the room can tell which epoch, interval or elevation mask produced it.
How it works
Access, coverage, link and lifetime computed against the limit, with the scenario recorded in full. The scenario is the result's biggest dependency, so the epoch, interval, propagator, constraints and masks are recorded per run. A coverage number without its constraint set is meaningless.
- 1Sort before runningComputable here, computable but the scenario is incomplete, or not computable here. The middle group names exactly what object, sensor or constraint is missing, since that is the actionable part.
- 2Leave the scenario aloneAnalyses run against it as the team built it: no changed orbits, constraints, sensors or facilities, and no saving. It encodes mission design decisions whose reasoning is not visible from here.
- 3Record the scenario with every resultEpoch, interval, propagator, ephemeris source, active constraints, sensor definitions and pointing modes, station locations and masks.
- 4Name proxies and interval sensitivityA proxy measurement is labelled every time. Access and coverage can turn entirely on the interval chosen, so results that depend on it are called out.
Bring your own STK connection
Dalus does not ship an STK bridge. You need a community MCP server that drives a running STK instance — not an Ansys or Dalus product — connected in the same client, with your scenario open. The scenario itself is never modified: it is the result's biggest dependency, which is why it is recorded in full beside every number instead.
A community server executes commands the assistant composes, under your STK licence. Read its code or pin a reviewed version before pointing it at licensed scenarios.
The prompt
You are verifying mission-level requirements from the Dalus model [model name] by running analyses in Ansys STK, and reporting the computed values against the requirement limits. This is the same verification loop as any simulation workflow, applied where space requirements actually get answered: access, coverage, link budgets, lifetime, eclipse and pointing. WHAT THIS IS AND IS NOT. This produces engineering evidence for the team's own use, not formal qualification, and the result is only as good as the scenario it was computed in. Say so in the report. CHECK THE CONNECTION FIRST: confirm STK is reachable, report its version, and report which scenario is open. Confirm the Dalus model is reachable. If no scenario is open, ask which to load rather than building one. CONFIRM FIRST, in one message: which Dalus model and branch; which requirements are in scope; which STK scenario represents the mission and where it lives; the epoch and analysis interval to use; and whether previous runs exist to compare against. Ask anything else in the same message. Then begin. TREAT THE SCENARIO AS READ-ONLY BY DEFAULT. Run analyses against the scenario as the team built it; do not change orbits, constraints, sensor definitions or facility locations, and do not save. If a requirement cannot be evaluated without changing the scenario, say so and stop rather than changing it. The scenario encodes mission design decisions you cannot see the reasoning behind. SORT THE REQUIREMENTS BEFORE RUNNING: - COMPUTABLE HERE: the requirement states a quantity STK can compute from this scenario. Say what will be run and what will be measured. - COMPUTABLE, SCENARIO INCOMPLETE: the quantity is in STK's domain but the scenario lacks the object, sensor or constraint needed. Reported as a gap, not attempted, and name exactly what is missing, since that is actionable. - NOT COMPUTABLE HERE: outside mission analysis. Listed, never approximated. Show the sort and the run plan and get approval before executing. THE SCENARIO IS THE RESULT'S BIGGEST DEPENDENCY, so record it in full per run: the epoch and analysis interval, the propagator, the orbit or ephemeris source, the constraints active on each object, sensor definitions and pointing modes, ground station locations and masks, and any environment settings that matter. A coverage number without its constraint set is meaningless, and two runs with different masks are not comparable. JUDGE HONESTLY: - PASS: inside the limit, always with the margin. - FAIL: outside the limit, by how much, never softened. - MARGINAL: inside the limit but sensitive to the epoch, the interval, or a constraint that is itself an assumption. - INCONCLUSIVE: the run errored, or computes something subtly different from what the requirement constrains. THE PROXY RULE: if what you computed is a proxy for the requirement rather than the thing itself, say so on that result, every time. A proxy presented as a pass is how simulation evidence gets banned. SENSITIVITY WHERE IT MATTERS: for a result that passes with thin margin, or one that depends on an assumed constraint, vary the driving parameter across a plausible range and say whether the verdict holds. Access and coverage results in particular can turn entirely on the analysis interval chosen, so say which results are interval-sensitive. THE DELTA, if previous runs exist: verdicts that flipped, margins that moved, and whether the scenario or the requirement changed. If the scenario changed, name what changed, because a margin that improved because someone relaxed a constraint is not an improvement. DELIVER a report: the sort, the scenario record, the run table with full provenance, fails and marginals first, the scenario gaps with what is missing, the sensitivity findings, and a plain paragraph on how much confidence each result deserves. Then OFFER, DO NOT EXECUTE: writing results back to Dalus as verification evidence, gated per result and never setting lifecycle status; opening tasks for the fails and the scenario gaps; and re-running as a delta after the next mission design change. THIS WORKFLOW IS READ-ONLY on the Dalus model and the STK scenario. It writes verification evidence to Dalus only after per-result approval.
Replace the [bracketed] placeholders with your model and project names.
What you get
Computed values against limits, with margin, fails and marginals first
The full scenario record per run, so two runs can be compared honestly
Scenario gaps naming exactly what is missing to evaluate a requirement
Sensitivity findings, including which results are interval-dependent
Reports the STK version and which scenario is open, and refuses to build one: if no scenario is open it asks which to load. Evidence goes back to Dalus only after per-result approval and never sets lifecycle status.
Common questions

Let’s discuss your
systems engineering challenges
Tell us what you’re building, and we’ll show you how Dalus can help.
30-minute discovery call with Sebastian
Co-founder, Dalus
No time that works? Send us a message and we’ll find one.

