Smarter Report Generation for ServiceNow Teams
For IT service teams that owe leadership a weekly service report: an agent that pulls incident, change and request records from ServiceNow, writes the narrative behind the numbers, and files the report back on a record.
412 incidents, 58 changes and 1,030 requests read for Sep 14–20. Report drafted:
How can I automate a weekly incident report from ServiceNow?
You can automate the weekly service report by having an agent query ServiceNow tables on a schedule.
- 01
Trigger fires
Every Monday it retrieves last week's records from the incident, change_request and sc_req_item tables, counts P1 and P2 incidents by assignment group, lists changes that failed or were rolled back, and finds requests that breached their SLA.
- 02
Query incident, change and request tables for the week
It then writes a short narrative explaining the week, such as which change caused an outage, attaches the PDF to a report record in ServiceNow, and emails it to the service owners.
- 03
Group P1 and P2 incidents by assignment group
When records look incomplete, like a P1 with no resolution code, the report is held for the service desk lead.
- 04
Link outages to the changes that caused them
- 05
You approve
Anything under your confidence bar waits for a human.
How you tell it what to do
Built in plain English.
You write the rule the way you'd describe it to a teammate. The agent reads the rule, breaks it into the actions it'll take, and confirms the apps it'll touch — before it does anything.
- 1Query incident, change and request tables for the week
- 2Group P1 and P2 incidents by assignment group
- 3Link outages to the changes that caused them
- 4Attach the report and email the service owners
How it connects
Connect ServiceNow. The agent does the rest.
Claude and ChatGPT are already running on our side. You connect ServiceNow with one click, and report generation runs inside it.
Claude and ChatGPT run on our keys. Nothing for you to configure.
- ServiceNowConnect
- GmailConnect
Runs on your data, in your apps.
Nothing to deploy. Nothing to maintain.
Actions
What ServiceNow + DeskFerry can do
Real ServiceNow actions your AI agent can perform automatically — no manual work required.
Attach file to record
Attaches a file to a specified record in a servicenow table. this endpoint allows you to attach a file with the provided details to the specified record.
Create a record
Creates a new record in a specified servicenow table. this endpoint allows you to create a new record with the provided data in the specified table.
Delete a record
Deletes a record from a specified servicenow table. this endpoint allows you to delete a record with the provided id from the specified table.
Find file
Finds a file in a specified servicenow table. this endpoint allows you to find a file with the provided name in the specified table.
Get records
Retrieves a record from a specified servicenow table. this endpoint allows you to retrieve a record with the provided id from the specified table.
Resolved, but the resolution code and root cause fields are empty. The report would say 'cause unknown'.
Email outage started 6 minutes after CHG0031190 was implemented. No link between the two records. Mention it?
Request volume for 'Laptop replacement' is well above any week this quarter. Check for a bulk import before reporting.
Human in the loop
Approve before it sends.
Every draft lands in a review queue. You approve, edit, or reject — the agent never acts on its own unless you explicitly turn that on for a workflow you trust.
Governance
Every action, with the reasoning attached.
Each step the agent takes is logged with what it did, why it did it, and which app it touched. Audit-ready, so security and compliance can sign off without backfilling.
- Olivia8:34 AM
Approved the weekly report and released the email to service owners.
- Agent8:09 AM
Created report record RPT0000219 and attached the PDF.
- Agent8:07 AM
Held the note on INC0048877 out of the report body.
Reason: The outage timing matches a change, but the records aren't linked, so naming the change as the cause would be a guess.
- Agent8:04 AM
Matched INC0048812 to CHG0031177 through the caused_by field.
- Agent8:02 AM
Retrieved 1,500 records from incident, change_request and sc_req_item for Sep 14–20.
How it works
Get started in three steps
Step 01
Connect ServiceNow and email
Connect a ServiceNow account that can read the incident, change and request tables, and the mailbox or Slack channel the report should go to.
Step 02
Describe the report you owe
Say what leadership asks for every week: which priorities to count, which groups to break out, which SLAs matter, and where the PDF should be filed.
Step 03
Approve before it's sent
The first few weeks, every report waits for a lead. Incomplete P1s and suspected but unlinked causes always stop in the queue.
Start automating Report Generation for ServiceNow
7-day free trial. Works with the tools you already use.
FAQ
Frequently asked questions
Isn't this what ServiceNow's own reports and dashboards do?
Dashboards show the counts. What leadership usually asks for is the explanation: which change caused the outage, why a group missed its SLA, what's different from last week. The agent reads the records behind the numbers and writes that part, then files it back in ServiceNow.
Which ServiceNow tables can it read?
Any table the connected account has access to. Weekly service reports usually draw on incident, problem, change_request, sc_req_item and task_sla. It reads records with the same permissions as that user, so restricted records stay restricted.
Does it write anything into ServiceNow?
Only what you allow. A common setup is creating one report record per week and attaching the PDF to it. It won't edit incidents or changes to make the report tidier; gaps like a missing root cause are flagged for a person to fix at the source.
Can it produce different versions for different audiences?
Yes. One rule can produce a detailed report for the service desk lead, broken out by assignment group, and a short summary for the CIO covering P1s, failed changes and risks. Each goes to its own recipients.
How do we check the numbers are right?
Every figure in the report traces back to the records it came from, and the audit log lists each query the agent ran and how many records came back. Reviewers can open any incident or change mentioned directly from the report.
Explore more