An AI CRM that scores deals on evidence, not vibes
Can AI tell me which deals are actually at risk?
Deal health is a computed score, not a model opinion. It starts neutral and moves on days since last contact, meeting count, whether a proposal has gone out, whether decision maker, budget and timeline are confirmed, whether a competitor is present, and how close the expected date is. Every driver is shown with its signed contribution, so you can argue with it.
Every figure in a LekhaPro answer is computed before any model sees it. A router picks the deterministic engines the question needs, those engines read your posted books and return a structured snapshot, and only then is the language model given that snapshot and told to write the reply. Switch the model off and an on-device narrator writes the same answer from the same numbers.
It sits above your own win probability rather than replacing it. A deal you marked eighty per cent, with no contact for three weeks and no confirmed budget, will score poorly — and that disagreement is the point.
Who does what
| Step | Who does it | Can the model change it? |
|---|---|---|
| Read the posted ledger | Deterministic engine | No |
| Compute the figure | Deterministic engine | No |
| Choose which engines to run | Router | No |
| Write the sentence | Language model | Wording only |
| Propose an action | Named, validated tool | Drafts it; you approve |
| Write to your data | Existing audited mutation | Never unattended |
What it does here
- Scores every open deal 0–100 with the drivers shown
- Detects revenue leaks and stalled stages
- Produces a five-scenario forecast from weighted pipeline and run rate
- Surfaces churn risk from each customer’s own ordering interval
The boundary
- A won opportunity posts nothing by itself — converting it to an invoice stays a deliberate step.
- The RevOps CRM is Cloud-edition only and does not sync to the offline Desktop app.
- Integration connectors and a native mobile app remain roadmap.
Questions
Can AI tell me which deals are actually at risk?
Deal health is a computed score, not a model opinion. It starts neutral and moves on days since last contact, meeting count, whether a proposal has gone out, whether decision maker, budget and timeline are confirmed, whether a competitor is present, and how close the expected date is. Every driver is shown with its signed contribution, so you can argue with it.
Does the AI ever calculate the numbers itself?
No. A deterministic engine computes every figure from your posted books and hands the model a structured snapshot; the model writes prose about it. Turn the model off and an on-device narrator produces the same answer from the same numbers — which is the test worth applying to any AI accounting claim.
Can it change my data?
Only through named tools bound to existing audited mutations, argument-validated before they run, and every tool that writes carries an approval requirement. Nothing bypasses the permissions your user account already has, and every write is logged like any other.