Tool Gate · How it works
How the Inferred-Fact & Unstated-Assumption Trace gate works
How the Inferred-Fact & Unstated-Assumption Trace grades every fact in each deliverable, rolls each deliverable up to its weakest fact, then the portfolio up to its weakest deliverable: one unsourced assumption demotes the whole portfolio to RESTS ON ASSUMPTION.
How the gate works
This tool grades every fact in each finished deliverable, rolls the deliverable up to its weakest material fact, then the portfolio up to its weakest deliverable. It reads 4 deliverables and rolls them into one verdict — the worst, never the average — and then a gate that can only make it worse.
The 4 deliverables
| Deliverable | Verdict |
|---|---|
| Vendor risk memofix first | RESTS ON ASSUMPTION6 material facts · 33% asserted · F-05 demoted, rests on unsourced F-04 |
| Renewal summary | RESTS ON ASSUMPTION2 material of 3 · 50% asserted · F-08 derives from F-20, absent from the trace |
| Pricing note | INFERRED2 material of 3 · 50% asserted · F-11 derivable and holds |
| Contact sheet | GROUNDED2 material of 2 · 100% asserted |
The verdict bands
A fact can name its inputs and state its rule and still be an assumption, because something underneath it is assumed. The trace follows every derivation back up to ten levels and demotes the ones standing on nothing, so a fact that reads DERIVABLE on its own row becomes ASSUMED. A deliverable is its weakest material fact and the portfolio is its weakest deliverable — worst-not-average, and the grounding percentage decides nothing.
In the worked sample it reads RESTS ON ASSUMPTION — Contact sheet is GROUNDED and Pricing note is INFERRED — but two deliverables rest on an assumption. In the Vendor risk memo, F-05 names F-04 as its input and applies a sensible rule, yet nothing ever sourced F-04, so F-05 is demoted from DERIVABLE to ASSUMED — a failure one row away that no claim-by-claim review sees. The Renewal summary's F-08 derives from F-20, a fact not in the trace at all. The portfolio is its weakest deliverable, so it reads RESTS ON ASSUMPTION even at 50% grounding. The one thing to fix first: Vendor risk memo — F-04. It is unsourced, and F-05 is built on top of it, so sourcing F-04 lifts F-05 with it. Fix the root, not the symptom; the trace names F-04, never F-05..
Common questions
Can every deliverable look survivable on the How the Inferred-Fact & Unstated-Assumption Trace works and the company still read RESTS ON ASSUMPTION?
Yes. The roll-up takes the worst of 4 deliverables — never the average — then a worsen-only gate, the Propagation demotion gate, escalates when trouble clusters. In the worked sample it reads RESTS ON ASSUMPTION because contact sheet is GROUNDED and Pricing note is INFERRED — but two deliverables rest on an assumption. In the Vendor risk memo, F-05 names F-04 as its input and applies a sensible rule, yet nothing ever sourced F-04, so F-05 is demoted from DERIVABLE to ASSUMED — a failure one row away that no claim-by-claim review sees. The Renewal summary's F-08 derives from F-20, a fact not in the trace at all. The portfolio is its weakest deliverable, so it reads RESTS ON ASSUMPTION even at 50% grounding.
What is a worsen-only gate?
A dispositive rule that can only lower a verdict, never raise it. One fatal flaw overrides an otherwise-set of survivable lines, because a single disqualifying gap shouldn't hide behind an average of the healthy ones. The tool also names the one thing to fix first — here, "Vendor risk memo — F-04. It is unsourced, and F-05 is built on top of it, so sourcing F-04 lifts F-05 with it. Fix the root, not the symptom; the trace names F-04, never F-05.".
Grades the facts you record about a deliverable — never people, and never runs an agent. It does not fetch or verify your sources: GROUNDED means each material fact traces back to a source you named, not that the source says what you think. A working aid, not legal, audit, or compliance advice.
Embed this diagram
Free to share and embed with attribution (CC BY 4.0) — keep the link to redhub.ai.
Interactive — renders the live diagram
<iframe src="https://redhub.ai/visuals/tool/inferred-fact-unstated-assumption-trace.html" title="How the Inferred-Fact & Unstated-Assumption Trace gate works — RedHub AI" width="760" height="2001" loading="lazy" style="border:0;width:100%;max-width:760px"></iframe>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai/visuals/tool/inferred-fact-unstated-assumption-trace">How the Inferred-Fact & Unstated-Assumption Trace gate works</a> — by <a href="https://redhub.ai">RedHub AI</a>, the AI that tells you when to doubt it.</p>Image + link — a static picture for any blog
<a href="https://redhub.ai/visuals/tool/inferred-fact-unstated-assumption-trace"><img src="https://redhub.ai/visuals/tool/inferred-fact-unstated-assumption-trace-share.png" alt="Diagram of the Inferred-Fact & Unstated-Assumption Trace: facts rolled up to the weakest per deliverable and the portfolio rolled up worst-not-average, reading RESTS ON ASSUMPTION on one unsourced root fact." width="760" loading="lazy" style="max-width:100%;height:auto;border-radius:16px"></a>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai">RedHub AI</a> — the AI that tells you when to doubt it.</p>
This is how Inferred-Fact & Unstated-Assumption Trace works. More diagrams in the Visual Field Guide.