B2B AI DirectoryB2B AI Directory
Sales ProspectingadvancedPro

Turn a territory into a weekly account priority and execution plan

Rank every account using potential, timing, relationship access, opportunity evidence, and rep capacity, then convert the score into an approved weekly action queue.

What you will have

A governed weekly territory plan with ranked accounts, reason codes, next actions, owners, evidence, and capacity limits.

Setup time
6-9 hours
Time saved
4-7 hours per week
Estimated cost
$150 to $700 per month
Tools used
4 tools

Why this works

Territory execution improves when reps allocate scarce selling time against explicit evidence instead of familiarity or the most recent reply. The workflow separates score inputs from managerial judgment, caps weekly work to available capacity, and preserves why an account moved up or down so prioritization can be audited and improved.

Step-by-step workflow

Preview the workflow

The first 2 steps are open. Pro unlocks the remaining steps, copy-paste prompts, pro tips, tool-by-tool setup guidance, and implementation details.

1

Define the territory decision contract

45-60 min

Use Salesforce and Google Sheets to define territory boundaries, ownership, scoring authority, review cadence, and the difference between a model recommendation and a manager decision. Create or update the exact fields `territory_id`, `account_id`, `account_owner`, `segment`, `region`, `review_cadence`, `score_owner`, `override_authority`, retaining the native account, opportunity, contact, site, program, requirement, and source IDs instead of matching on display names alone. Apply the operating rule that one account has one accountable owner for the review period and overrides require a reason code, and write every proposed change to a dated change log rather than replacing the prior approved value. Validate the work by sampling account ownership against the current Salesforce territory report and checking for unassigned or duplicate owners; assign each warning or exception an owner, severity, due date, and evidence link, and hold records that fail the check. The completion gate is sales leadership approval of boundaries, scoring authority, and override rules; document the rollback or fallback path if the source is unavailable, the connector fails, or the buyer disputes the record.

Output

An approved territory contract and decision policy.

SalesforceGoogle Sheets
Pro tip

Lock ownership rules before scoring; otherwise the model will optimize a territory that the rep does not actually control.

2

Create the versioned territory Claude Project

45-60 min

Use Claude and Google Sheets to package instructions, field definitions, approved examples, source registers, and the weekly release process in a persistent Claude Project. Create or update the exact fields `project_version`, `instructions_file`, `field_dictionary`, `source_register`, `review_rubric`, `approved_examples`, `changelog`, `primary_owner`, `backup_owner`, retaining the native account, opportunity, contact, site, program, requirement, and source IDs instead of matching on display names alone. Apply the operating rule that the project contains `instructions.md`, `field-dictionary.json`, `source-register.csv`, `review-rubric.md`, `approved-examples.md`, and `changelog.md`, and write every proposed change to a dated change log rather than replacing the prior approved value. Validate the work by testing the project against three historical weeks and confirming identical inputs produce explainable outputs; assign each warning or exception an owner, severity, due date, and evidence link, and hold records that fail the check. The completion gate is the primary and backup owners approving the initial project package; document the rollback or fallback path if the source is unavailable, the connector fails, or the buyer disputes the record. Run this template in Claude within the approved persistent territory Claude Project after attaching the source records named for this step; store the returned JSON beside the source register before any downstream action. Maintain the Claude Project with `instructions.md`, `field-dictionary.json`, `source-register.csv`, `review-rubric.md`, `approved-examples.md`, and `changelog.md`; name releases `vYYYY.MM`, assign a primary and backup owner, refresh source exports before each operating review, and review permissions and maintenance quarterly.

Output

A versioned territory workspace with named files and maintenance ownership.

ClaudeGoogle Sheets
Pro tip

Use `vYYYY.MM` releases and never edit the only copy of a prior scoring rubric.

Prompt template
ROLE
You are the governed sales-execution analyst supporting a quota-carrying account executive and frontline sales manager. You work inside the “Turn a territory into a weekly account priority and execution plan” operating system, where source traceability, stable CRM identifiers, buyer-safe language, and human authority are more important than producing a polished but unsupported answer.

OBJECTIVE
Complete workflow step 2, “Create the versioned territory Claude Project,” and produce this operational outcome: A versioned territory workspace with named files and maintenance ownership. Execute only this step; do not silently broaden the task, fabricate buyer facts, or make external changes.

INPUTS
1. APPROVED SOURCE RECORDS: {{create_the_versioned_territory_claude_project_source_records}}
2. FIELD DICTIONARY AND ALLOWED VALUES: {{create_the_versioned_territory_claude_project_field_dictionary}}
3. ACCOUNT, OPPORTUNITY, OR PROGRAM CONTEXT: {{create_the_versioned_territory_claude_project_deal_context}}
4. OPERATING RULES, PERMISSIONS, AND APPROVAL MATRIX: {{create_the_versioned_territory_claude_project_operating_rules}}
5. PRIOR APPROVED VERSION OR CURRENT STATE: {{create_the_versioned_territory_claude_project_prior_state}}
6. DEADLINES, OWNERS, AND REVIEW CADENCE: {{create_the_versioned_territory_claude_project_approval_context}}

WORK TO PERFORM
1. Perform the exact job described by “Create the versioned territory Claude Project” using the supplied IDs and field names.
2. Separate observed facts, direct buyer statements, operator-entered decisions, calculations, and model inferences.
3. Preserve account_id, opportunity_id, contact_id, site_id, program_id, requirement_id, source_id, owner, and effective_date whenever supplied; do not merge records merely because names look similar.
4. Populate the requested fields, identify missing values, and flag contradictions, stale evidence, duplicate entities, unsupported claims, permission issues, and dependencies.
5. Return records that can be copied into the declared system of record without renaming identifiers, flattening one-to-many relationships, or overwriting an approved value.
6. Provide a compact change summary, exception queue, approval request, and next-action list with owner and due date.
7. Apply the step-specific instructions: package instructions, field definitions, approved examples, source registers, and the weekly release process in a persistent Claude Project.

OUTPUT SCHEMA
Return valid JSON only with this exact top-level structure:
{
  "workflow_slug": "territory-weekly-account-priority-agent",
  "step_number": 2,
  "step_title": "Create the versioned territory Claude Project",
  "run_status": "pass|warning|hold|fail",
  "source_register": [{"source_id":"string","source_type":"string","captured_at":"ISO-8601|null","authoritative":true,"notes":"string|null"}],
  "records": [{
    "project_version": "value|null",
    "instructions_file": "value|null",
    "field_dictionary": "value|null",
    "source_register": "value|null",
    "review_rubric": "value|null",
    "approved_examples": "value|null",
    "changelog": "value|null",
    "primary_owner": "value|null",
    "backup_owner": "value|null",
    "evidence_source_ids": ["string"],
    "confidence": "high|medium|low",
    "review_status": "approved|needs-review|held"
  }],
  "exceptions": [{"record_id":"string|null","exception_type":"string","severity":"low|medium|high|critical","evidence":"string","owner":"string","required_action":"string"}],
  "changes_from_prior_state": [{"record_id":"string","field":"string","prior_value":"value|null","proposed_value":"value|null","reason":"string","source_ids":["string"]}],
  "review_summary": {"facts":["string"],"inferences":["string"],"open_questions":["string"],"next_actions":[{"action":"string","owner":"string","due_date":"YYYY-MM-DD|null"}]},
  "qa": {"schema_valid":true,"ids_preserved":true,"evidence_complete":true,"human_approval_required":true}
}

GUARDRAILS
- Treat the supplied field dictionary, approval matrix, security policy, commercial rules, and prior approved state as binding.
- Do not invent quotes, dates, metrics, relationships, customer permissions, product capabilities, legal positions, security answers, pricing authority, or approvals.
- Do not perform, simulate, or claim an external write. Return proposed records or actions for the named operator or governed automation to apply.
- Do not collapse conflicting evidence into one confident statement. Preserve each source and route the conflict to the exception queue.
- Do not expose confidential margin, personal data, security detail, or contract language to an audience not authorized in the inputs.
- Mark any record that could change scope, price, legal obligations, security posture, implementation effort, or buyer commitment as human-approval-required.

EVIDENCE REQUIREMENTS
- Every material claim must cite one or more supplied source_id values and include the source date when available.
- Direct buyer statements must remain distinguishable from seller interpretation and model inference.
- Calculations must show inputs, units, formula, and rounding rule; relationships must show the evidence supporting the match.
- A record without adequate evidence must be marked needs-review or held, never approved by default.

UNCERTAINTY HANDLING
- Use high confidence only for current authoritative records or direct, corroborated buyer evidence.
- Use medium confidence for a plausible interpretation supported by one credible source, and low confidence for hypotheses requiring validation.
- When two sources disagree, list both values, explain the conflict, and name the person who must resolve it.
- If required inputs are absent, return run_status “hold” and state exactly what is missing instead of guessing.

HUMAN REVIEW
The named operator must review the source register, exceptions, inferred fields, proposed changes, and audience permissions. Require explicit approval before any CRM write, buyer-facing publication, pricing or scope commitment, legal or security response, pilot promise, or external notification. Return the approval decision, reviewer, timestamp, rejected items, and required revisions in the final review summary.

Pro workflow preview

Previewing 2 of 13 steps

Pro membership

Unlock the full workflow

Get the remaining 11 steps, copy-paste prompts, pro tips, tool-by-tool setup guidance, and weekly new workflows.

$9/month

Export the authoritative territory and opportunity records
Configure optional read-only Salesforce MCP access
Normalize account hierarchy and weekly scoring inputs
Add Sales Navigator relationship and activity evidence
Generate the explainable account priority score
Apply capacity limits and build the weekly queue
See Pro plan
3Export the authoritative territory and opportunity records
Locked
4Configure optional read-only Salesforce MCP access
Locked
5Normalize account hierarchy and weekly scoring inputs
Locked
6Add Sales Navigator relationship and activity evidence
Locked
7Generate the explainable account priority score
Locked
8Apply capacity limits and build the weekly queue
Locked
9Create account-specific next-action briefs
Locked
10Route exceptions and manager overrides
Locked
11Run the weekly rep-manager operating review
Locked
12Execute actions and record evidence without score gaming
Locked
13Measure calibration and publish the next weekly version
Locked

Expected results

Accounts governed

50-300 per territory

The account register can cover a full named territory while the weekly queue remains limited by rep capacity.

Weekly focus queue

10-25 approved accounts

A bounded queue prevents a scoring model from becoming an unworkable list of every attractive account.

Priority traceability

100% with reason codes

Every rank change retains source IDs, score components, manager overrides, and the effective date.

Operating cadence

One reviewed plan per week

The workflow is designed for a repeatable manager-rep review rather than a one-time territory exercise.

Related workflows

Continue with workflows that share a similar GTM motion, category, or tool stack.