Best for
- Plant tours tied to MES, PLM, ERP, automation, or engineering services
- Onsite discovery and solution workshops
- Automotive OEM and supplier facilities
Plan objectives, stakeholders, safety, observation routes, workshop exercises, evidence capture, and post-visit decisions so an onsite becomes structured technical discovery.
A complete plant-visit charter, agenda, role map, safety and logistics checklist, observation guide, workshop board, evidence template, and debrief decision pack.
Quick view
Check the audience, core tools, and access before you start the detailed steps.
Best for
Core tools
4 tools used across the workflow.
Access
Preview the open steps, then unlock the remaining implementation details and prompts.
Why this works
Onsite access is scarce and easily wasted when the visit becomes an unstructured tour. This workflow connects objectives, participant roles, safety, observation evidence, workshop decisions, and post-visit follow-up so the team can learn from the real operating environment without turning observations into unsupported requirements.
Expected results
Visit readiness
One approved charter and agenda
Objectives, roles, evidence, logistics, and decisions are agreed before travel.
Observation coverage
All priority processes assigned
Each production, quality, maintenance, engineering, IT, or OT observation has an owner and capture field.
Evidence quality
Facts separated from interpretations
Photos, notes, timestamps, statements, and hypotheses retain permissions and source context.
Post-visit action
Debrief completed within 24 hours
The team converts observations into validated questions, requirements, risks, and next decisions while context is fresh.
Step-by-step 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.
45-60 min
45-60 min
Use Salesforce and Google Drive to set visit objectives, questions, required decisions, in-scope sites and processes, participant roles, evidence rules, and success criteria. Create or update the exact fields `visit_id`, `opportunity_id`, `site_id`, `visit_date`, `objective`, `decision_required`, `process_scope`, `participant_role`, `evidence_rule`, `success_criterion`, 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 team cannot add surveillance, photography, or sensitive-data collection beyond host permission, and write every proposed change to a dated change log rather than replacing the prior approved value. Validate the work by testing agenda ideas against objectives, time, site scope, and evidence rules; 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 customer host and internal account leader approving the charter; document the rollback or fallback path if the source is unavailable, the connector fails, or the buyer disputes the record.
An approved visit charter linked to the opportunity.
A plant tour and a design workshop are different jobs; state which decisions the day must support.
45-60 min
45-60 min
Use Claude and Google Drive to package instructions, site context, field dictionary, safety rules, observation taxonomy, source register, workshop templates, tests, and changelog. Create or update the exact fields `project_version`, `instructions_file`, `field_dictionary`, `safety_rules`, `observation_taxonomy`, `source_register`, `workshop_templates`, `test_cases`, `changelog`, 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 uses required versioned files, owners, refresh rules, tests, and `vYYYY.MM` or visit-date releases, and write every proposed change to a dated change log rather than replacing the prior approved value. Validate the work by testing the package on a prior visit and confirming site, process, and evidence distinctions remain intact; 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 visit lead approving the workspace; 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 onsite-workshop 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.
A maintained onsite preparation workspace with named files and owners.
Pro workflow preview
Previewing 2 of 13 steps
Get the remaining 11 steps, copy-paste prompts, pro tips, tool-by-tool setup guidance, and ongoing workflow and prompt releases.
$9/month
Archive each visit as its own dated release; do not mix observations from different plants without explicit site IDs.
ROLE
You are the governed sales-execution analyst supporting an account executive, sales engineer, or industrial solution architect. You work inside the “Prepare plant visits and onsite workshops for technical sales” 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 onsite Claude Project,” and produce this operational outcome: A maintained onsite preparation workspace with named files and owners. 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_onsite_claude_project_source_records}}
2. FIELD DICTIONARY AND ALLOWED VALUES: {{create_the_versioned_onsite_claude_project_field_dictionary}}
3. ACCOUNT, OPPORTUNITY, OR PROGRAM CONTEXT: {{create_the_versioned_onsite_claude_project_deal_context}}
4. OPERATING RULES, PERMISSIONS, AND APPROVAL MATRIX: {{create_the_versioned_onsite_claude_project_operating_rules}}
5. PRIOR APPROVED VERSION OR CURRENT STATE: {{create_the_versioned_onsite_claude_project_prior_state}}
6. DEADLINES, OWNERS, AND REVIEW CADENCE: {{create_the_versioned_onsite_claude_project_approval_context}}
WORK TO PERFORM
1. Perform the exact job described by “Create the versioned onsite 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, site context, field dictionary, safety rules, observation taxonomy, source register, workshop templates, tests, and changelog.
OUTPUT SCHEMA
Return valid JSON only with this exact top-level structure:
{
"workflow_slug": "plant-visit-onsite-workshop-preparation-agent",
"step_number": 2,
"step_title": "Create the versioned onsite 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",
"safety_rules": "value|null",
"observation_taxonomy": "value|null",
"source_register": "value|null",
"workshop_templates": "value|null",
"test_cases": "value|null",
"changelog": "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.Related workflows
Continue with workflows that share a similar GTM motion, category, or tool stack.
A reusable discovery plan with stakeholder branches, evidence requirements, qualification mapping, follow-up logic, and post-call capture fields.
An evidence-linked requirements traceability matrix that preserves who asked for what, how it will be accepted, what remains uncertain, and who must validate it.
A governed solution-fit register with requirement links, evidence, assumptions, dependencies, validation owners, scope impact, and buyer-confirmation status.