Salesforce MVP Hall of Fame (Shivanath Devinarayanan) · Founded 2022
Lead scoring against your ICP
Each lead scored on the criteria you wrote down. Your code applies the weights. Sales sees why.
Founded 2022 · Founder in the Salesforce MVP Hall of Fame · Dubai HQ · Kochi studio
- 01Models · Claude, Gemini, OpenAI, Bedrock
- 02Agentic systems · Agentforce, CrewAI, ADK, A2A
- 03Agentic memory · Neo4j, Cognee, IndyKite
- 04Automation and voice · n8n, Retell
- 05Deployment and governance · identity, evals, policy, audit
The stack
How we would assemble it.
The honest no: if the work is a software factory with a named delivery date, we are the wrong partner.
The decision
The decision, drawn.
Score per ICP criterion (industry fit, size, intent) + Choice segment; code weights
Jev · Score+Choice
How well does this lead fit each ICP criterion?
- poor fit
- partial fit
- strong fit
VP Operations, 400-person logistics firm, Dubai, visited pricing twice this week.
- industry2.00
- size1.60
- intent1.80
The flow
One lead, scored on what you wrote down.
Arrives
A lead lands in Sales Cloud
Title, company size, city and the pages they visited.
Jev decides
Fit on each ICP criterion
Poor, partial or strong fit, per criterion. Your code applies the weights.
Above the line
Sales sees the lead and the why
Claude or OpenAI writes the outreach. The rep sees which criterion carried the score.
Below the line
A person scores the unsure ones
Those labels are how you check the threshold.
The job
What has to be true.
Act at 0.90 confidence or higher. Below that, a person or a larger model. Set the threshold on the score. Low confidence goes to review.
The figure
Builder's figure. Not reproduced by us.
700 leads scored in 40s for $0.09 (Gojiberry)
madewithjev.com/jev-use-casesWrite your house rules into the request. When rules were left out, Jev got 5 of 24 right with high confidence (Huryn). Validate thresholds on labelled samples.
Who runs it
Who would run this, and what changes.
Example
Sales director, Dubai logistics software vendor
Today: SDRs work the lead list top to bottom. A VP at a large firm waits behind a student download.
After: Every lead is scored on the ICP the sales director wrote. SDRs open the strong fits first and see why.
Sales CloudExample
Head of growth, Riyadh B2B services firm
Today: Marketing calls a lead qualified and sales disagrees. Neither side has the criteria written down.
After: The criteria sit in the request, so both teams read the same reasons on every lead.
For CMOsExample
Managing director, Abu Dhabi fit-out contractor
Today: Tender enquiries and small repair jobs come through the same form. The estimator reads all of them.
After: Enquiries are scored on size and fit before the estimator opens them. The unsure ones still reach a person.
Fit-out contractors
The brief
Name the decision your team makes a thousand times a day.
We read the process and write down where Jev fits, where it does not, and where the line sits.