CPQ quote preparation
Turn an approved deal configuration into a policy-checked quote draft with exception routing.
What this workflow does
Turn an approved deal configuration into a policy-checked quote draft with exception routing. It coordinates dependencies across connected systems, pauses at exception boundaries, and records the state of every approved sub-step.
What you gain
Versioned quote draft
What the AI agent changes
How this worked before
A fixed workflow required every system and input to behave exactly as expected; one exception stopped the entire chain.
What the AI agent changes
The agent chooses the next tool from the current state, recovers from common exceptions, and asks for a decision at the right boundary.
Agent trigger
An opportunity reaches the quote stage with required configuration fields.
Inputs
- Approved product and pricing catalog
- Opportunity, terms, and entitlement data
Agent flow
- 1
Validate configuration completeness.
- 2
Apply pricing, discount, and compatibility rules.
- 3
Draft quote and isolate policy exceptions.
- 4
Generate the approved quote and update stage.
Human decisions
After step 3
Deal desk approves discounts, exceptions, and legal terms.
Outcome
- Versioned quote draft
- Exception register
Guardrails
- The model cannot calculate final price.
- Block quote creation when required evidence is missing.
Risks and mitigations
Incorrect pricing or entitlement can create material leakage.
Keep deterministic pricing outside the model and require approval for every exception.
Sources and evidence
Sources establish feasibility or impact. Not every metric comes from an identical implementation.
Salesforce
Agentforce for Sales customer stories
Salesforce documents agents that qualify, research, and route sales opportunities inside CRM workflows.
Michel Lieben on X
Enterprise agent workflow example
A practitioner example illustrates guarded enterprise automation rather than a standalone chat experience.