Sales / Sales Engineering Live
Solution Recommendation
Score which solution components actually fit a customer's requirements, by feasibility rather than by what would be nice to sell.
- Run on demand
- ~7 credits per run
- Uses a knowledge base
- v1.0.0
What does Solution Recommendation do?
Solution Recommendation is a production AI agent in the sales section of the Leverge agent store, built for the sales engineering process. Score which solution components actually fit a customer's requirements, by feasibility rather than by what would be nice to sell. It runs on demand, works through 3 steps and returns 5 outputs, including components by feasibility.
What it needs
-
Customer requirements
What they need, at what volume, with what constraints.
What it does
- Reading the component catalogue
- Scoring component fit
- Writing the recommendation
What you get back
- Components by feasibility
- Recommendation
- Requirement coverage
- Cannot be met
- Catalogue entries used
After each run it asks: “Is this the right component set?”
When it runs
Run on demand
Oversight
Runs under scoped, least-privilege credentials with every action written to an audit log. Anything that moves money, alters a contract or reaches a customer requires human approval before it executes.
Sales Engineering
Other agents in sales engineering
Pipeline, proposals, renewals and the CRM hygiene underneath them
-
Acceptance Test Generation
Turn agreed requirements into acceptance tests the customer would sign off — each traceable to a requirement, prioritised, with the untestable ones named.
-
Requirements Clarity Check
Take rough requirements from a discovery call and turn them into ones an engineer could build against — with everything still ambiguous written as a question rather than resolved by guessing.
-
Solution Blueprint
Describe what the customer needs and get a solution architecture written against your own standards, with every component justified and every deviation from standard called out.
-
User Story Generation
Paste discovery notes and get them turned into user stories with acceptance criteria — and an explicit list of what the notes do not say clearly enough to write.
-
Account Plan Review
Check an account plan against what a plan is supposed to contain — whether its actions have owners, whether its targets are grounded, and whether it says anything the data does not support.
-
Account Risk Monitor
Name an account and get external signals searched for anything that changes your plan — funding, restructures, leadership moves, regulatory news — with what is corroborated separated from what is rumour.
Next Step
Deploy Solution Recommendation, or adapt it
It runs as-is against the inputs above. Most deployments diverge — a different source system, a different tolerance, a different approval path. A 30-minute technical call establishes which.