Agents
The linking work, done between reviews.
Tensol’s agents tie each run back to the requirement it verifies, trace what a change touched, and flag the evidence it made stale — so the review starts from a current picture instead of a rebuilt one.
Precharge shall complete within 250 ms 200 ms of power-on.
Five of six children inherit the tightened limit. Two cases assert the old value and must be re-authored.
What they do
Three jobs nobody has time for before a review
Each one used to be a spreadsheet pass the week before. The agents do it every time something changes.
Linking
Every run, tied to what it verifies
A run lands and is matched to the test case it executed, the requirement that case verifies, and the channel that carries the result. The link is made from the data, not typed into a field.
2026-08-16_rig01_precharge_044.mf4
2.4 GB · 61 channels · ingested in 38 sassert precharge_complete_ms ≤ 250Change impact
What a change broke — and what it didn’t
When a limit moves, every run already on disk is re-scored against the new value. What comes back is itemised: what lost its evidence, which sign-offs went stale — and, just as usefully, what is untouched.
Impact
Sub-components affected
Admissibility
A pass on the wrong rig doesn’t count
A run can pass and still verify nothing. Each result is checked against the level the requirement demands, and anything from a rig below it is held out of coverage instead of counted.
Precharge timing, cold
They cannot verify a requirement that needs the contactor in the loop, so they do not count toward it.
Guardrails
Scoped, and on the record
Permission-scoped
Agents act only within the permissions you grant them.
Traceable
Every action stays traceable to its source record and workflow, and every step opens to the run behind it.
See it on your data
Point an agent at one subsystem and watch the chain build.
Bring existing requirements and a handful of representative runs.
Book a demo