B2b Sales Prospecting Agent

If nothing is found, tell the user to install the plugin first.

Prospecting Conversation Flow

When a user wants to find prospects, guide them through this structured workflow:

Step 1 — Understand the Ideal Customer Profile (ICP)

Ask: "What type of companies are you targeting?"

Gather these dimensions:

• Industry/vertical — e.g., SaaS, fintech, healthcare, e-commerce
• Company size — employee count range (e.g., 51-200, 201-500)
• Geography — country, state/region, or city
• Revenue range — if relevant (e.g., $5M-$25M)
• Technology stack — if targeting tech users (e.g., companies using Salesforce, React, AWS)
• Buying intent — if looking for active buyers (e.g., companies researching "CRM software")
• Company age — startup vs. established (e.g., 0-3 years, 10-20 years)
• Recent events — companies that recently raised funding, are hiring, launched products

Step 2 — Define the Buyer Persona

Ask: "Who is your ideal buyer at these companies?"

• Job titles — specific titles like "VP of Engineering", "Head of Marketing"
• Seniority level — c-suite, VP, director, manager
• Department — engineering, sales, marketing, operations, finance
• Contact requirements — need email? phone? both?

Step 3 — Confirm Scope and Budget

Before executing, confirm:

• Number of prospects desired (e.g., 100, 500, 1000)
• Credit budget awareness (~1 credit per entity fetched, additional for enrichment)
• Any exclusions (existing customers, competitors)

Step 4 — Build Filters and Execute

Map the user's requirements to API filters. Consult references/filters.md for the full catalog.

Entity type decision:

• prospects — when user wants people/contacts with job details
• businesses — when user wants company lists only (often a precursor to prospect search)

For each autocomplete-required field, run autocomplete first:

• linkedin_category, naics_category, job_title, business_intent_topics, company_tech_stack_tech, city_region

Key mutual exclusions (see references/filters.md):

• Never combine linkedin_category + naics_category
• Never combine country_code + region_country_code
• Never combine job_title + job_level/job_department

CLI Execution Pattern

At the start of every workflow, generate a plan ID:

PLAN_ID=$(python3 -c "import uuid; print(uuid.uuid4())")
QUERY="<user's original request>"

Autocomplete Required Fields

RESULT=$(python3 "$CLI" autocomplete \
  --entity-type businesses \
  --field linkedin_category \
  --query "software" \
  --semantic \
  --plan-id "$PLAN_ID" \
  --call-reasoning "$QUERY")
cat "$RESULT"

Market Sizing (Free)

RESULT=$(python3 "$CLI" statistics \
  --entity-type prospects \
  --filters '{"linkedin_category":{"values":["Software Development"]},"company_size":{"values":["51-200","201-500"]},"job_level":{"values":["c-suite","director","vice president"]}}')
cat "$RESULT"

Sample Fetch (5-10 Results)

FETCH_RESULT=$(python3 "$CLI" fetch \
  --entity-type prospects \
  --filters '{"linkedin_category":{"values":["Software Development"]},"company_country_code":{"values":["US"]},"job_level":{"values":["c-suite","director"]}}' \
  --limit 10)
cat "$FETCH_RESULT"

Present Sample and WAIT for Confirmation

This step is mandatory — never skip it.

Show the user:

1. Total results found
2. Credit cost estimate
3. Sample rows as a markdown table
4. Ask explicitly:

"Would you like to:

• Fetch all [N] results and export to CSV
• Enrich with contact info (emails, phones, LinkedIn profiles)
• Enrich with company data (firmographics, tech stack, funding)
• Add event signals (recent funding, hiring activity)
• Refine the search (adjust filters)"

Full Fetch (after confirmation)

FETCH_RESULT=$(python3 "$CLI" fetch \
  --entity-type prospects \
  --filters '<confirmed filters>' \
  --limit 500)
cat "$FETCH_RESULT"

Enrich with Contact Information

ENRICH_RESULT=$(python3 "$CLI" enrich \
  --input-file "$FETCH_RESULT" \
  --enrichments "contacts_information,profiles")
cat "$ENRICH_RESULT"

Enrich with Company Data

ENRICH_RESULT=$(python3 "$CLI" enrich \
  --input-file "$FETCH_RESULT" \
  --enrichments "firmographics,technographics")
cat "$ENRICH_RESULT"

Export to CSV

CSV_RESULT=$(python3 "$CLI" to-csv \
  --input-file "$FETCH_RESULT" \
  --output ~/Downloads/prospects_list.csv)
cat "$CSV_RESULT"

Advanced Prospecting Workflows

Find Prospects at Specific Companies

1. Match companies to get their business_id values:

   RESULT=$(python3 "$CLI" match-business \
     --businesses '[{"name":"Salesforce","domain":"salesforce.com"},{"name":"HubSpot","domain":"hubspot.com"}]')
   cat "$RESULT"
   

2. Extract business IDs and use as a filter:

   BID=$(python3 -c "import json; print(','.join([e['business_id'] for e in json.load(open('$RESULT'))['data']]))")
   FETCH_RESULT=$(python3 "$CLI" fetch \
     --entity-type prospects \
     --filters "{\"business_id\":{\"values\":[$(echo $BID | sed 's/,/\",\"/g' | sed 's/^/\"/' | sed 's/$/\"/')]}}")
   

Companies with Buying Intent (Signal-Based Prospecting)

1. Autocomplete intent topics:

   RESULT=$(python3 "$CLI" autocomplete \
     --entity-type businesses \
     --field business_intent_topics \
     --query "CRM software" \
     --semantic)
   cat "$RESULT"
   

2. Use intent as a filter combined with other ICP criteria
3. Fetch matching companies, then find contacts at those companies

Event-Triggered Prospecting

Find companies showing growth signals:

FETCH_RESULT=$(python3 "$CLI" fetch \
  --entity-type businesses \
  --filters '{"events":{"values":["new_funding_round","increase_in_all_departments"],"last_occurrence":60},"company_size":{"values":["51-200","201-500"]}}' \
  --limit 100)

Start from an Existing CSV (Enrich Your List)

When a user has an existing prospect or company list:

1. Convert CSV to JSON: python3 "$CLI" from-csv --input ~/Downloads/my_list.csv
2. Read metadata (columns + 5 sample rows) — never cat the full file
3. Match with deduced column map
4. Enrich matched results with contact info

Error Handling

Key Capabilities Summary