Clear the IT ticket queue without new hires: one agent assigns incoming tickets by shift rules, a second searches past incidents and your known-error database to suggest a fix the engineer can check: AI agent prompt
TheNextGenTechInsider (Nov 4, 2026), citing HCLTech, describes a Fortune 500 electronics distributor using two agents on HCLTech AI Force.ITOps inside its existing ITSM tool: an Initial Response Agent that triages and assigns tickets to engineers based on shift rules, and a Service Assist Agent that recommends resolutions by querying historical incidents, the Known Error Database (KEDB) and knowledge bases. Reported results: 40% more incident inflow absorbed without new headcount, about 35% higher engineer productivity, 28% lower average resolution time, 17% lower MTTR, about 19% faster initial response and 23x more knowledge references per ticket. Figures are vendor-reported.
The prompt
1. Write your assignment rules down: shifts, skills per engineer, queue per category, and when to escalate. 2. Agent 1 (assign): for each new ticket, classify it, pick the on-shift engineer by those rules, and post the reason in the ticket. Run it in suggest-only mode for a week and compare with what the dispatcher did. 3. Gather your fix memory: closed incidents with resolutions, the known-error list, and KB articles. 4. Agent 2 (assist): when an engineer opens a ticket, it finds the 3 most similar past incidents and known errors, and suggests a fix with links to each source. 5. Engineers mark each suggestion used, edited or wrong; every week update the KB from the 'edited' ones. 6. Track response time, resolution time and tickets per engineer before and after.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
- Paste it into ITSM tool (ServiceNow, Jira Service Management or similar), HCLTech AI Force.ITOps or any agent platform with search over incidents and KB and review the answer before you use it.
Works with: ITSM tool (ServiceNow, Jira Service Management or similar), HCLTech AI Force.ITOps or any agent platform with search over incidents and KB
Real-world example: thenextgentechinsider.com/pulse/agentic-ai-implementation-boosts-it-in
Before you use it: what to check
Already built into this prompt
- Write your assignment rules down: shifts, skills per engineer, queue per category, and when to escalate.
- Agent 2 (assist): when an engineer opens a ticket, it finds the 3 most similar past incidents and known errors, and suggests a fix with links to each source.
Check yourself
- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records. How prompt injection works →
- Check hours, breaks, overtime and any rules for young workers against your local labour law and staff contracts before you publish a schedule.
- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free