AI AGENT TEMPLATE
An AI agent that drafts a professional customer-facing damage report from staff notes and photos. Consistent, defensible, 30-second review.
Bike rental damage is frequent and low-dollar per incident — a derailleur hanger, a torn saddle, a scratched top tube — which is exactly why most operators either eat the cost or charge inconsistently. Neither is great. Eating it is steady revenue leak; inconsistent charging creates customer disputes and leaves your staff in the uncomfortable position of being cop instead of host.
The Bike Damage Report Drafter Agent makes small-dollar damage handling fair, fast, and uniform across your staff. On return, staff photograph the damage and tag the bike in the booking app. The agent cross-references your rate card, drafts a clear evidence-backed customer email, and stages the charge for manager approval before any money moves against the security hold.
Consistency is the lever. Two different staff members handling the same damage produce the same email and the same charge — without the agent, they won't, and over a season that inconsistency costs you in disputes, reviews, and staff friction. Operators report dispute rates down 50-70%, average processing time down from 20 minutes to under 3, and damage revenue recovery up 40-60% versus the "too small to bother with" default.
Below is the full agent spec: trigger, tools, rate-card integration, and how to configure per-category damage thresholds and approval flows.
"When I upload damage photos and a one-line note plus rental ID, draft a full damage report: type, location, cause analysis, repair plan referencing rate card, charge calculation, and a professional customer-facing letter. Save as draft; do not send without approval."
Paste this into Dash Agents. Dash reads the prompt, picks the right tools, assembles the logic, and creates a ready-to-run agent in seconds.
The agent uses the standard Dash Agents tool library. Every tool call is logged.
On trigger, the agent runs these steps in order. Any step can be customised by re-prompting.
Photos, note, rental ID — all uploaded at once by counter staff.
Vision AI identifies damage type (scratch, bent, broken, missing).
Booking: customer name, dates, bike model, agreement policy.
Type, location, dimensions where visible, repair path.
Professional, warm tone referencing agreement terms and rate card lines.
From rate card: parts + labour, total.
Attached to booking, visible to manager for approval.
Customisations by re-prompting in plain English: change the trigger timing or conditions, adjust the recipient list, tune thresholds, modify tone, add approval gates, connect additional channels (SMS, WhatsApp) if available. Run in approval mode for the first week to build confidence before switching to autonomous.
Structured automation beats manual follow-up in three ways:
Set this agent up on your first week. Run in approval mode for five days while you watch the outputs, then flip to autonomous. The ROI compounds across a full season — a quiet automation that simply does the right thing, every time, without anyone having to remember.
Rental booking ID and customer info, rental dates and bike model, damage type and precise location, photos from multiple angles, a cause analysis where feasible, a line-item repair plan from rate card, total charge, reference to the signed rental agreement, and a professional customer letter. Reports without photos or rate card references are hard to defend in disputes.
Dash Agents handle the repetitive work so your team can focus on customers. Start your free trial and build your first agent in minutes.
