Output Quality

Facts, Inferences, Unknowns, and Recommendations: Verify AI Sales Output

AI output can sound equally confident whether it is quoting your notes, summarizing a current source, connecting two clues, or filling a gap. In sales, those are not equivalent. A fabricated stakeholder motive, customer result, product capability, or deadline can damage a live deal even when the rest of the draft is strong.

The safest working rule is not merely “fact-check everything.” It is to make the evidence status visible before review. Require any research, account analysis, transcript summary, qualification score, forecast, proposal, or recommendation to label what it knows and how it knows it.

The five labels

  • Supplied or sourced fact: directly supported by a source you provided or a source the AI cites. The source must support the exact claim, not just discuss the same topic.
  • Reasonable inference: an interpretation that connects supported facts. It must name those facts and use conditional language.
  • Assumption: a working premise supplied by the seller or introduced for planning. It is not evidence and should be tested.
  • Unknown: information the available sources do not establish. Unknowns become questions or owner-routed gaps—not sentences the model completes.
  • Recommendation: a proposed action. It must state which facts, inferences, and constraints justify it.

What counts as a fact

A fact has traceable support: an exact line from a call transcript, a current CRM field with an owner and date, an approved product document, a primary public source, or a verified customer-evidence record. A citation is a locator, not a guarantee. Open it, confirm the claim, check the date, and preserve the source beside the output.

Facts can still conflict. Do not average contradictions into a confident summary. Show both statements, their sources and dates, and identify what must be resolved.

How to label inference without making it useless

Good inference helps a seller prepare. Bad inference impersonates inside knowledge. “The company announced two acquisitions; integration capacity may become a priority” is a transparent inference. “The CIO is urgently buying an integration platform” is an invented fact unless the evidence says so.

Require every inference to include: the supporting facts, an alternative explanation, the confidence level, and the question that would confirm or disprove it. This turns inference into a discovery aid rather than a claim to repeat.

The evidence ledger

For consequential work, ask for a table with these columns:

  • claim;
  • label: fact, inference, assumption, unknown, or recommendation;
  • source and date;
  • exact supporting passage;
  • confidence and reason;
  • conflict or limitation;
  • seller action or validation question.

Any fact without a source moves to unverified. Any recommendation without a traceable basis moves to unsupported. Any unknown that matters to the deal becomes a next-step question with an owner.

Claims that always require extra scrutiny

Verify numbers and calculations independently; competitor and product claims against current authoritative material; customer stories against the approved evidence library and usage restrictions; quotations against the original passage; and dates, owners, pricing, commitments, security controls, legal terms, roadmap items, and buyer motivations against the system or person responsible for them.

A reusable review instruction

Separate the output into supported facts, reasonable inferences, assumptions, unknowns, and recommendations. Cite the exact source for every fact. For each inference, name its supporting facts and one alternative explanation. Do not convert an unknown into a plausible answer. Flag every claim that requires product, finance, legal, security, customer-reference, or seller approval before use.

This instruction improves visibility; it does not replace review. For the numerical-claim boundary, see Never use AI-generated numbers without verification. For who makes the final decision, see Human-in-the-Loop.

Before anything leaves the draft

  • Open every material citation and confirm it supports the claim.
  • Recalculate consequential numbers from the source inputs.
  • Move buyer motives and deal predictions without evidence into inferences or unknowns.
  • Confirm product, pricing, security, legal, roadmap, and customer-reference claims with the accountable owner.
  • Make the seller approve the final message, analysis, recommendation, or system action.

The goal is not to eliminate inference. Selling requires judgment. The goal is to prevent judgment from being mislabeled as evidence.