# Ticket pre-work and runbooks for technical support

Before an engineer sees a ticket, an AI agent answers L1 questions from docs, runs structured runbooks for known L2 processes (e.g. compliance form routing), and collects missing details like call IDs or logs.

**Why it matters:** In developer-facing SaaS, engineers lose time on back-and-forth for basic details. Collecting them upfront makes each ticket debuggable on first touch.

- Trigger: New ticket in Slack / email / chat
- Tools: Pylon, Slack, Linear, OpenAI
- Time saved (rough estimate): 10–15 hours/week
- Typical agency build cost (rough estimate): $3k–$10k

## Steps
1. Try to resolve from docs
2. Runbook: ask for IDs, logs, plan
3. Route to the right engineer
4. Hand over with summary
5. Knowledge gap report

## Pitfalls
- Write runbooks for the 5 most common L2 cases first.
- Review the knowledge-gap report weekly and fix docs.

## Sources
- [Pylon case study: Retell AI](https://www.usepylon.com/case-study/retell-ai)
- [Pylon case study: AssemblyAI](https://www.usepylon.com/case-study/assembly-ai)

---
Source: https://cofounderbase.com/workflows/support-ticket-prework/?utm_source=md&utm_medium=ai · Cofounderbase, a directory of agencies that build AI internal tools and automations. Data comes from each agency's own website and official partner directories; rankings are not sold.
