‹ Customer Success recipesCustomer Success · Agent Blueprint
Quarterly forecasting
Renewals at risk and why. Composite signal: sentiment, support load, commitment drift, time-to-renewal.
Side by side: token usage, with and without Paperbase
~161k tokens saved · 85% less work for the agentWithout Paperbase
~190k tokens
- Pull upcoming renewals from the CRM.
- Ask each CSM to rate renewal risk from their gut.
- Skim support loads and escalations manually.
- Reconstruct commitment histories per account.
- Produce a forecast built on opinion, not the record.
With Paperbase
~29k tokens
- Pull all Renewals in the forecast window.
- For each, pull sentiment trend, support load, commitment drift, and time-to-renewal.
- Ask Paperbase to score renewal risk from the composite signal.
- Attach the evidence behind each at-risk rating.
Agent prompt
You are producing the quarterly renewal forecast.
Using Paperbase:
1. Pull all Renewals in the next {{days}} days.
2. For each account, pull the composite signals: sentiment trend, support load, commitment drift, open escalations.
3. Ask Paperbase to score renewal risk from those signals.
4. For every at-risk account, pull the evidence behind the rating.
Output:
- Renewal forecast table: account, renewal date, risk score.
- At-risk accounts, with the specific evidence for each.
- What would change the outcome for the three most at risk.Placeholders in {double_braces} are inputs the agent will ask for at runtime. Give the prompt to any agent connected to Paperbase, and the rest grounds in your own memory graph.