AI Incident Response Process Flowchart

What to do when an AI feature gives a harmful, wrong or leaked answer: contain it fast, find whether the prompt, model, data or a tool caused it, fix it and add the case to the tests.

4 teams11 steps2 decisionsFree download

Edit this flowarrow_forward
AI incident response processReporter1On-call engineer5AI team4Privacy and comms1YesNoYesNoHarmful orwrong AIoutput…2Triageseverity?Serious?4Switch thefeature off orto fallback5Queue for thenext fix?Personal dataexposed?7Assess andnotify8Find the causefrom the trace9Fix and add atest case10Re-enableafter evalspassClosedwithwrite-up

Free to download. Edit it in Flow Studio to change the teams and steps, ask AI for changes, or export to PowerPoint, Word or draw.io.

Step by step

The same flow as a numbered list, ready for an SOP, a BRD or a ticket.

#Step
1Harmful or wrong AI output reportedStartUser report, monitoring alert or red-team findingReporter · step 2
2Triage severitySev by harm, reach and whether data left the companyOn-call engineer · step 3
3Serious?DecisionOn-call engineer · Yes: step 4, No: step 5
4Switch the feature off or to fallbackFeature kill switch; keep tracesOn-call engineer · step 6
5Queue for the next fixAI team · step 8
6Personal data exposed?DecisionOn-call engineer · Yes: step 7, No: step 8
7Assess and notifyRegulator and affected people within legal deadlines (e.g. GDPR 72 h)Privacy and comms · step 8
8Find the cause from the tracePrompt, model version, retrieved data, injected input, tool permissionAI team · step 9
9Fix and add a test casePatch prompt, data or guardrail; add the case to the eval suiteAI team · step 10
10Re-enable after evals passOn-call engineer · step 11
11Closed with write-upEndAI team · Done

When to use it

Use it next to your normal incident process for any AI feature in production, so the on-call team knows how AI failures differ and what to switch off.

Who's involved

  • Reporter1
  • On-call engineer5
  • AI team4
  • Privacy and comms1

Yours works differently?

Describe your own process in a few sentences and Flow Studio draws it, with your teams and your rules.

Describe your processarrow_forward

For the technical team

The build decisions behind this flow. Each step above also carries its technical detail.

  • 01Kill switch per feature via config; fallback copy or human queue when off.
  • 02Trace store keyed by request id: prompt version, model id, retrieved chunks, tool calls, output, user feedback.
  • 03Root-cause buckets: prompt regression, model version change, bad or poisoned source data, prompt injection, tool permission, missing guardrail.
  • 04Post-incident: add the case to the eval suite and block release until it passes.

How to get it right

  1. 1Build a kill switch for each AI feature before launch: off, or fall back to a safe non-AI path.
  2. 2Keep the exact inputs, retrieved passages, tool calls and outputs for the incident. Without them you can't find the cause.
  3. 3Every incident ends with a new test case, so the same failure can't ship again.
  4. 4If personal data may have leaked, bring in privacy straight away: notification deadlines can be as short as 72 hours.

Questions

What counts as an AI incident?

Any output or action that causes or could cause harm: unsafe or offensive content, confident wrong answers people relied on, leaked personal or confidential data, an agent taking an unintended action, or a jailbreak or prompt-injection exploit.

How is AI incident response different from normal incidents?

The cause is often not a code bug but a prompt, a model update, retrieved data or a malicious input. You need the full trace of the request to find it, and the fix usually comes with a new evaluation case.

More process flow templates

See all 34 process flow templates