Solution Recommendation

Challenges Solution Recommendation addresses

Done by hand, sales engineering means gathering customer requirements, working through 3 separate passes over the same material, then producing components by feasibility, recommendation and requirement coverage. None of it is difficult and all of it is exacting, which is the combination people are worst at holding. The errors that matter are the ones a tired reader does not notice, and they surface later — in a reconciliation, or in somebody’s reply. It waits until someone remembers it, which is usually the point at which it has become urgent. As volume grows the work does not get harder, only longer, and the first thing to go is the checking.

Solution Recommendation runs that same sequence end to end and returns the result as structured artefacts. What it cannot settle it hands over rather than guesses at, and your correction is kept: it asks “Is this the right component set?” after every run, and those answers become the set it is measured against. Nothing that moves money, alters a contract or reaches a customer executes without human approval, and every action is written to an audit log. The gain is in the volume that no longer has to be read, not in removing the judgement.

How it works

Step 1: Reading the component catalogue

First of 3. It works from customer requirements and feeds the step after it.

Key Tasks:

• Locating the material: It works from customer requirements, so nothing has to be forwarded, re-keyed or renamed first.
• Handling the format it arrives in: Scanned pages, native documents, spreadsheets and message bodies are all read the same way, including layouts where the relevant figure sits inside a table rather than a labelled field.
• Pulling the fields that matter: Only the fields the rest of the run needs are extracted. What cannot be read confidently is recorded as unread rather than filled in with a best guess.

Outcome:

• Fields extracted: The fields are available to the steps that follow, with anything unreadable listed rather than silently defaulted — which is what stops a bad extraction becoming a confident wrong answer three steps later.

Step 2: Scoring component fit

Step 2 of 3. It takes what step 1 produced and hands its result to step 3.

Key Tasks:

• Scoring against fixed criteria: The same criteria and weights apply to every item, so two items with the same profile receive the same score whichever run they arrive in.
• Showing the working: The score is returned with its components rather than on its own, so a sales reviewer can disagree with a criterion instead of only with the total.
• Ordering what comes back: The result arrives ranked, which is the form the decision actually needs — not a list to be sorted by whoever opens it.

Outcome:

• A ranked set: A ranked set with every score traceable to the criteria that produced it. Ties are left as ties rather than broken arbitrarily, because an invented ordering reads as a judgement the agent did not make.

Step 3: Writing the recommendation

Last of 3. It takes what step 2 produced and produces components by feasibility and recommendation.

Key Tasks:

• Writing from the run, not from a template: The text is built from what this run actually found, so two sales engineering outputs differ where the underlying records differ.
• Leading with what needs a decision: The exceptions come first and the routine detail follows, because the reader is deciding rather than reading.
• Staying inside the evidence: Nothing appears in the text that is not supported by a record the run examined. Gaps are stated as gaps.

Outcome:

• Artefact ready: A finished artefact, traceable line by line to the records behind it, ready for a person to accept or correct.

Step 4: Your review, and what it changes

The run ends with a person, not with a result being filed.

Key Tasks:

• Asking a specific question: It asks “Is this the right component set?” rather than for a rating. A question about this run is answerable; a score out of five is not.
• Keeping the correction: What you change is recorded against the case that produced it, so the disagreement is retrievable rather than absorbed.
• Building the evaluation set: Those cases become what the agent is measured on. It is scored against your judgement rather than against a general benchmark.

Outcome:

• A measured agent, not an assumed one: The cases Solution Recommendation handles well and the cases it does not are both visible, and the second list is the one that decides what changes. Nothing is retrained silently on the back of a single correction.

Why use Solution Recommendation?

• Answers from your own material: It retrieves from a knowledge base you populate — your policies, contracts and reference documents — so its decisions follow how your business actually operates rather than a general model’s assumptions. Sources are cited alongside the result.
• Every statement cites its source: Findings come back with the records behind them, so a reviewer can check a claim instead of deciding whether to trust it. An assertion with no source is the expensive kind to discover late.
• Checks are evidenced, not asserted: Each check records what was expected and what was found. A failure can be understood — and argued with — without re-running anything.
• A batch is one run, not a hundred: It works the whole set in a single pass and returns a row per item with its verdict, so the volume that needs no attention never has to be opened.
• Corrected by the people using it: After each run it asks “Is this the right component set?”. Those answers become the evaluation set, which means it is measured against your judgement rather than ours.