Skip to content

Inbound lead scoring with reply approval

Each inbound lead from a form or CSV is enriched from the company homepage, scored against a written ideal customer rubric with a reason for every point, and given a draft reply. The run pauses until a person approves, edits or rejects it, and only then writes to the CRM.

SalesWorks with LangGraph · Claude Code+1Community example
Build your promptSee requirements

What it does

  • Fetches the lead's company homepage and extracts size, industry and buying intent
  • Scores the lead against a YAML rubric with hard disqualifiers and tier caps
  • Drafts a reply suited to the lead's tier, grounded in their message
  • Pauses the run and saves it so it can be approved days later
  • Writes approved leads to the CRM and posts a summary to chat

Your approval boundaries

Approval required

These actions always wait for your yes:

  • Approving, editing or rejecting each draft reply
  • Any write to the CRM
  • Sending the reply

You decide what happens next.

More about this workflow

This setup is for founders and small sales teams who want more time for real conversations. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it fetches the lead's company homepage and extracts size, industry and buying intent. Next, it scores the lead against a YAML rubric with hard disqualifiers and tier caps. Then it drafts a reply suited to the lead's tier, grounded in their message. After that, it pauses the run and saves it so it can be approved days later. Finally, it writes approved leads to the CRM and posts a summary to chat. It works with your CRM, web fetch and chat, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before approving, editing or rejecting each draft reply, any write to the CRM and sending the reply, and says plainly if a step cannot be undone.

“waits for a human to approve before anything reaches your CRM or Slack”
Shubham Garje ShubhamGarje99 on GitHub · Oct 26, 2026
Before you startCRM · Web fetch accessScoped permissionsLangGraph or Claude Code
Explore required tools and model recommendations

Tools and access

  • HubSpot CRM

    Handles the crm part of this job. Grant read scopes, plus notes write.

    API required: Yes. Needs a HubSpot private app or OAuth app with the CRM scopes you choose.

    Sign up: HubSpot CRM

  • Web fetch

    Handles the web fetch part of this job. Grant public pages, no logged-in sessions.

    API required: No. Built into most agent harnesses. It reads public pages with no login.

    No sign-up needed

  • Slack

    Handles the chat part of this job. Grant a bot token in the channels it needs.

    API required: Yes. Needs a Slack app created in your workspace. It gets a bot token with the scopes you approve.

    Sign up: Create a Slack app

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Sonnet 5.5

Good balance of speed and quality for briefs and drafts.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

GPT-6 Luna

Very low cost per token for simple research summaries.

$0.10 per million input tokens, $0.50 per million output tokens, for prompts up to 272K tokens.

OpenAI docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

target sizes, industries, weights and disqualifiers

form webhook or csv

e.g. hubspot

e.g. A 75, B 50, C 30

2Your prompt

4 of 4 still empty
Fill these in before you run it: [ICP RUBRIC: target sizes, industries, weights and disqualifiers] [LEAD SOURCE: form webhook or csv] [CRM: e.g. hubspot] [TIER THRESHOLDS: e.g. A 75, B 50, C 30] You are the Inbound lead scoring with reply approval agent. Each inbound lead from a form or CSV is enriched from the company homepage, scored against a written ideal customer rubric with a reason for every point, and given a draft reply. The run pauses until a person approves, edits or rejects it, and only then writes to the CRM. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Fetches the lead's company homepage and extracts size, industry and buying intent - Scores the lead against a YAML rubric with hard disqualifiers and tier caps - Drafts a reply suited to the lead's tier, grounded in their message - Pauses the run and saves it so it can be approved days later - Writes approved leads to the CRM and posts a summary to chat What you must never do without a yes from a person: - Approving, editing or rejecting each draft reply - Any write to the CRM - Sending the reply Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: LangGraph, Claude Code, OpenAI Agents SDK

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect HubSpot CRM with its own login, not yours. Grant read scopes, plus notes write.
  2. 2Set up Web fetch. Keep it to public pages, no logged-in sessions.
  3. 3Connect Slack with its own login, not yours. Grant a bot token in the channels it needs.
  4. 4Paste the prompt where your harness takes instructions. See the note under the Copy button.
  5. 5Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  6. 6Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval30 / 30

Waits for a yes on: approving, editing or rejecting each draft reply, any write to the crm, sending the reply.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope16 / 20

Runs on its own login across 3 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
  • Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
  • Scope: Cut it down from 3 connected tools to the 2 it needs most, each with its own limited login instead of your full account +2

Do all of these to reach 89, up from 78.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Inbound lead scoring with reply approval](https://trustcase.dev/badge/inbound-lead-scoring-with-reply-approval.svg)](https://trustcase.dev/use-cases/inbound-lead-scoring-with-reply-approval)
HTML
<a href="https://trustcase.dev/use-cases/inbound-lead-scoring-with-reply-approval"><img src="https://trustcase.dev/badge/inbound-lead-scoring-with-reply-approval.svg" alt="Trustcase trust score for Inbound lead scoring with reply approval" height="20"></a>

More sales workflows

Other workflows that use the same tools

  • Morning AI news brief

    Personal. Gathers the day's AI news with simple scripts, then has the agent pick the best items and write a short PDF brief. It lands in your chat app before 7 AM.

  • Grocery reorder with running low check

    Personal. Works out what you are about to run out of from past grocery orders, then builds the cart and asks before anything is placed. A weekly read only ping lists what is due.

  • Next day training plan with approval

    Personal. Each evening an agent proposes tomorrow's workout from your recovery data, training load, weather and weekly plan. Fixed rules check the proposal and nothing goes on the calendar until you tap approve.