What is jev-gtm-cookbook?

A bcharleson repository of 15 open-source outbound recipes on TypeSafe Jev, spanning ICP scoring, job-change interpretation, reply classification, lead routing, first-message scoring, and follow-up selection.

How does Jev fit into these recipes?

The README splits the work: code does the retrieval, counting, and enrichment, while Jev makes the judgment calls, such as whether a connection fits your ICP, what a job change means, or which follow-up fits a thread.

Do I need a Jev API key to run the recipes?

The recipes call Jev for judgments, so a TypeSafe key is needed for real runs. The digest is cut off before any setup notes, so where to put the key is not documented in the capture.

What data do the recipes need?

Mostly data you already own, such as a LinkedIn connections export or a CSV lead list; recipe 13 can enrich any list through Prospeo, LeadMagic, BlitzAPI, or MoltSets.

What is the headline result reported?

The repository description reports 16,711 connections scored for $0.73. That is the author's own run on their network, not an independent benchmark or an invoice.

Are the recipes runnable without coding?

They are JavaScript recipes meant to be read and adapted; the README says the full app for recipe 01 lives in the repository, but the capture includes no install or usage commands.

Who maintains it and how current is it?

bcharleson, per the GitHub metadata: 31 stars, 4 forks, MIT licensed, JavaScript, created and last pushed on 2026-09-22, so nothing has landed since the initial push in the digest.

Jev directory

CommunityJev Cookbooks

Jev Gtm Cookbook

Fifteen open-source go-to-market recipes built on TypeSafe Jev by bcharleson: code does the work, Jev makes the judgment calls, and each recipe runs locally on data you already own. The README reports 16,711 connections scored for $0.73.

See highlights Open github.com

Stars: 31
Language: JavaScript
License: MIT
Reading time: 2 min
Published by: Community
Author: bcharleson
Last verified: Oct 2026

bcharleson/jev-gtm-cookbook

User repository on GitHub

View on GitHub

15 open-source outbound recipes on TypeSafe Jev. Score your LinkedIn network or any lead list against your ICP, catch job changes, triage replies. Local, zero dependencies. 16,711 connections scored for $0.73.

Forks: 5
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity github gtm lead-scoring javascript

Works forJev for Scoring Jev for Classification Jev for Routing

Used inJev for Sales & Marketing

Languages: JavaScript
Capabilities: Open sourceRuns locallyRequires API key

Highlights

Recipe 01 scores a whole LinkedIn network against your ICP; the repository description reports 16,711 connections scored for $0.73.
Others cover job-change interpretation, cold-email reply classification, inbound lead routing, connection-request intent, and account ICP scoring.
Later recipes: personalization fact-check, first-message scoring, learning from your own inbox, warm-intro finding, and social signal triage.
Recipe 13 scores any CSV and keeps it fresh with Prospeo, LeadMagic, BlitzAPI, or MoltSets enrichment.
README framing: each recipe runs locally on data you already own, with zero dependencies, and Jev is what makes the judgment calls.

Watch out

README and GitHub metadata reviewed 2026-10-17; the digest cuts off at the clipped sentence "Every reci", so closing notes, setup, and key instructions were not reviewed. The 16,711-connections / $0.73 figure is the author's own reported run, not a bill and not an independent benchmark.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Retrieval with Decisions: Filter, Rerank, and Verify

Oct 12, 2026

Retrieval is a sequence of bounded judgments. How a decision model slots into passage filtering, semantic find, reranking, and citation checks, and what stays in deterministic code.

Jev Cookbooks#retrieval#reranking#rag

Read article

One Request, Many Questions: Batching, Fan-Out, and Composite Scoring

Sep 12, 2026

Jev bills input tokens and gives output away, and questions in one request run in parallel. The design consequence is simple: ask more per call, then decide in code.

Jev Cookbooks#batching#patterns#search