checklist

AI chatbot change approval checklist for small teams

A practical change approval checklist for customer-facing AI chatbots, covering change types, risk tiers, approval records, source changes, prompt changes, tool actions, release gates, rollback, and post-change monitoring.

Audience: Founders, support leads, product owners, security owners, privacy owners, trust owners, support operations owners, and admins approving changes to customer-facing AI chatbots Risk: High Evidence: NIST AI RMF Core, NIST AI 800-4 monitoring report, NIST continuous-monitor-and-update AI security note, CISA joint guidance on deploying AI systems securely, OWASP Top 10 for LLM Applications, FTC AI guidance, and Cybergiz chatbot operations templates

Use this checklist before changing a customer-facing AI chatbot’s prompt, knowledge sources, connector scope, tool actions, admin settings, customer notice, retention setting, model/vendor configuration, or rollout location.

AI chatbot changes are risky because a small configuration update can change what the bot knows, what it says, what data it can reach, and what actions it can take. Before approving a change, run the AI Tool Risk Checker and attach the result to the change record.

Bottom line

A small team should approve chatbot changes only when the owner can show:

  1. What changed and why.
  2. Which customers, data, systems, sources, and tool actions are affected.
  3. Whether the change expands the bot’s scope, access, autonomy, or customer impact.
  4. Which tests passed, including regression tests from prior incidents and corrections.
  5. Who approved the change and who can pause or roll it back.
  6. What will be monitored in the first 24 hours and first 7 days.
  7. What customer-facing wording, retention promise, or human handoff path changed.

Use the Small Team AI Security Checklist for baseline owners, access review, incident routing, and evidence storage. This page focuses on approving one chatbot change.

When to use this checklist

ChangeUse this checklist?Why
New or edited system promptYesIt can change scope, refusal behavior, escalation, and claims.
New knowledge source, folder, help center section, or sync ruleYesIt can expose stale, private, conflicting, or unapproved content.
New connector, API, CRM field, ticket queue, or account contextYesIt can expand customer data access.
New tool action or automationYesIt can affect tickets, accounts, billing, access, deletion, messages, or records.
Model, vendor, retrieval, safety, or admin setting changeYesIt can alter behavior without changing your visible content.
Customer notice, privacy wording, opt-out path, or retention setting changeYesCustomer-facing promises must match operations.
Small copy edit to approved public FAQ sourceUsuallyLightweight review is enough if no scope, access, or action changes.
Emergency containment after incidentYes, but use emergency laneRecord the reason, approver, rollback path, and follow-up review.

If the change can affect customer trust, customer data, account state, support decisions, or compliance wording, treat it as high-risk until proven otherwise.

Change intake form

Copy this into the change request.

FieldEntry
Change title
Requester
Bot name and location
Change typePrompt, source, connector, tool action, admin setting, model/vendor, notice, retention, rollout, or other.
Reason for change
Customer problem solved
Affected customers or segments
Affected dataNone, public, internal, customer, account, billing, regulated, credential-like, or other.
Affected systemsHelp center, ticketing, CRM, billing, account system, data warehouse, source repository, or other.
Affected tool actions
Prior incident, complaint, correction, or red-team test related to this change
Proposed release date
Rollback owner

Reject the request if the requester cannot describe the affected data, systems, or owner.

Change risk matrix

Risk tierChange examplesApproval required
LowPublic FAQ wording change, typo fix, source owner update, link fix.Bot owner.
MediumNew public help center source, non-sensitive handoff rule, approved disclosure wording, routing tag change.Bot owner and support/product owner.
HighNew customer data field, internal source, connector scope, model/vendor setting, retention setting, sensitive-topic answer, or customer-facing trust claim.Bot owner plus security/privacy owner.
CriticalNew tool action affecting account, billing, deletion, access, outbound messaging, legal/compliance wording, or incident recovery.Executive/business owner plus security/privacy/product owner.

Use the highest tier that applies. Do not average the risk down because part of the change is routine.

Scope change decision table

QuestionIf yes
Does the bot answer a new category of customer question?Add tests, source owner, handoff rule, and disclosure review.
Does the bot use a new source, connector, or field?Run source/access review before release.
Does the bot keep or expose more transcript data?Review retention wording and deletion/export workflow.
Does the bot make a stronger privacy, security, legal, billing, or compliance claim?Require human approval and approved wording.
Does the bot act on a customer account or downstream system?Require tool-action approval and rollback plan.
Does the bot reduce human review?Require monitoring signals and escalation thresholds.
Does the change fix an incident or repeated correction?Preserve the old failing case as a regression test.
Does the change depend on a vendor feature or model behavior?Record vendor docs, setting owner, and fallback path.

If a change expands scope, do not release it through a “minor update” path.

Prompt change checklist

  • Store the old prompt and new prompt in the change record.
  • Summarize the exact behavioral change expected.
  • Confirm the prompt does not ask the bot to hide AI use, skip handoff, ignore user safety, or make unsupported claims.
  • Confirm sensitive topics route to a human where required.
  • Test prior wrong-answer, handoff, and prompt-injection cases.
  • Test customer data questions, deletion/export questions, training questions, and opt-out questions.
  • Confirm customer-facing wording matches the disclosure notice and privacy/support pages.
  • Confirm the bot still refuses prohibited account, billing, deletion, access, or outbound-message actions unless approved.

Use the AI chatbot red-team test checklist before approving a major prompt change.

Knowledge source change checklist

  • Name every source added, removed, or changed.
  • Record source owner, source system, access scope, and sync cadence.
  • Confirm the source is approved for chatbot use.
  • Confirm the source does not include private notes, internal-only strategy, credentials, payment data, regulated data, or unrelated customer data.
  • Check source freshness and conflict with other approved sources.
  • Test common questions, edge cases, missing-source behavior, and stale-source behavior.
  • Confirm source citations or internal evidence are not exposing private titles, paths, or metadata.
  • Record how to remove or pause the source if the change fails.

Use the AI chatbot knowledge base review checklist for a full source review.

Connector and data change checklist

CheckRequired evidence
Connector purposeWhy the bot needs this connector or field.
Minimum scopeThe narrowest source, folder, object, field, or role that works.
Data classificationPublic, internal, customer, account, billing, regulated, credential-like, or other.
Access ownerPerson who can approve, revoke, and review the connection.
Customer impactWhat the bot can infer, display, summarize, or route from the data.
Retention impactWhether transcripts, tool logs, or downstream records keep this data.
Deletion/export impactWhether customer request workflows need updating.
Audit evidenceWhere connector changes, access grants, and tool calls are logged.

Use the AI chatbot deletion and export request workflow if the change affects customer data request handling.

Tool action change checklist

  • Add the action to the approved action inventory.
  • Define allowed inputs, disallowed inputs, and expected output.
  • Confirm the bot cannot choose account, billing, access, deletion, or outbound-message actions without the approved confirmation step.
  • Test prompt injection attempts against the action.
  • Test duplicate, retry, timeout, and partial failure behavior.
  • Confirm the customer sees what will happen before the action runs.
  • Confirm logs show prompt, action, arguments, approval, result, and owner.
  • Define the rollback or cleanup step if the action runs incorrectly.

Use the AI chatbot tool action approval checklist before enabling any new action.

Release gate checklist

GatePass condition
OwnerBot owner, system owner, and data owner are recorded.
ScopeChange does not exceed the approved use case.
DataNew data access is minimized and approved.
SourcesSource owner, freshness, conflicts, and sensitive content are reviewed.
PromptNew behavior is documented and tested.
Tool actionsHuman approval and rollback exist for high-impact actions.
HandoffSensitive, disputed, and human-request paths still work.
NoticeCustomer-facing disclosure, opt-out, and support paths match the change.
RetentionTranscript, log, deletion, export, and redaction rules are still accurate.
TestingRegression, prompt injection, sensitive data, source, and handoff tests pass.
MonitoringFirst-day and first-week monitoring owners are assigned.
RollbackThe team can pause the bot, pause a capability, or restore the old config.

Do not approve the change if any high-risk gate has no owner.

Test set before approval

Test groupMinimum tests
Happy pathCommon customer questions the change is meant to improve.
No-answer pathQuestions outside approved scope.
Handoff path”I want a human,” complaint, refund, legal, privacy, security, billing, and account-impacting topics.
Sensitive dataPasswords, payment data, recovery codes, private keys, regulated data, and account-sensitive data.
Prompt injectionIgnore instructions, reveal hidden prompt, override tool approval, expose source, exfiltrate data.
Source conflictTwo sources disagree; bot should use the approved source or hand off.
Stale sourceOld policy or removed feature; bot should not answer from stale content.
Tool actionApproved, denied, malformed, duplicate, retry, timeout, and high-impact paths.
Customer noticeCustomer can identify AI use and find a human path.
RegressionPrior incidents, corrections, complaints, and failed red-team cases.

Keep the test set short enough to run, but broad enough to catch scope expansion.

Rollback plan

Rollback itemOwnerReady?
Restore previous promptBot owner
Remove or pause new sourceSource owner
Revoke connector scopeAdmin/security owner
Disable tool actionProduct/security owner
Restore customer notice or support routingSupport/trust owner
Preserve logs and transcriptsSecurity/privacy owner
Customer correction or notice pathSupport/privacy owner
Post-rollback test setBot owner

Rollback should be possible without waiting for the person who made the change.

Emergency change lane

Use the emergency lane only for containment, outage recovery, active abuse, private data exposure, broken handoff, unauthorized tool action, or customer-impacting wrong answers.

Emergency stepRequired output
State the emergencyWhat is happening and who is affected.
Limit the changeOnly the minimum containment change is allowed.
Name approverBot owner plus security/privacy/product owner where relevant.
Preserve evidenceLogs, prompts, sources, tool calls, tickets, and screenshots if safe.
Define rollbackHow to undo the emergency change.
Schedule follow-upFull review within 1 business day.

Emergency does not mean undocumented. It means short, focused, and reviewed after the immediate risk is contained.

Approval record

Copy this table into the final approval note.

FieldEntry
Change title
Risk tierLow, Medium, High, or Critical.
Approved change summary
Out-of-scope items
Tests run
Failed tests and fixes
Data/source/connector changes
Tool action changes
Customer notice or retention changes
Rollback path
First 24-hour monitoring owner
First 7-day monitoring owner
Approvers
Release decisionApprove, approve with limits, reject, hold, emergency release, or rollback.
Next review date

The approval record should be readable by someone who did not attend the meeting.

Post-change monitoring

PeriodReview
First hourConfirm bot is live only where intended and high-impact actions are not firing unexpectedly.
First dayReview conversations touching the changed prompt, source, connector, action, notice, or setting.
First dayReview all handoffs, corrections, sensitive data entries, tool actions, denied actions, and errors.
First weekCompare real failures with test results and add new regression cases.
First weekDecide whether to continue, limit, expand, or roll back the change.
First monthInclude the change in monthly admin, source, access, retention, and monitoring review.

Use the AI chatbot production monitoring checklist after release.

Metrics to track

MetricWhy it matters
Changes approved by risk tierShows whether high-risk changes are getting proper review.
Changes released without full evidenceShows process debt.
Failed tests before releaseShows whether tests are finding issues.
Incidents or corrections after changeShows whether approval gates are working.
Time to rollbackShows operational readiness.
Unapproved source, connector, or setting changesShows admin drift.
Tool actions attempted, denied, failed, and rolled backShows automation exposure.
Sensitive data entries after changeShows privacy and warning effectiveness.
Handoff failures after changeShows whether support routing still works.
Regression cases addedShows learning from real failures.

The goal is not to slow every update. The goal is to keep small changes from silently becoming major risk changes.

Evidence checked

This checklist is aligned with:

  1. NIST AI RMF Core, which emphasizes continuous AI risk management, documented roles, ongoing monitoring, lifecycle risk mapping, regular evaluation, tracking emergent risks, change management, incident response, recovery, and deactivation when outcomes are inconsistent with intended use.
  2. NIST AI 800-4 monitoring report summary, which identifies post-deployment monitoring as crucial and frames functionality, operational, human factors, security, compliance, and impact monitoring categories.
  3. NIST continuous-monitor-and-update AI security note, which argues against one-time guardrails and emphasizes continuous red-team work, guardrail updates, operational resilience, impact limitation, and quick recovery.
  4. CISA joint guidance on deploying AI systems securely, which highlights confidentiality, integrity, availability, mitigations for known vulnerabilities, and controls to protect, detect, and respond to malicious activity against AI systems and related data and services.
  5. OWASP Top 10 for LLM Applications, which covers prompt injection, insecure output handling, training data poisoning, sensitive information disclosure, insecure plugin design, excessive agency, and overreliance risks relevant to chatbot changes.
  6. FTC artificial intelligence guidance, which tracks enforcement and guidance related to AI accuracy, advertising, safety, data handling, chatbot monitoring, deceptive claims, and consumer protection.
  7. Cybergiz templates for chatbot launch review, source review, tool action approval, disclosure notices, admin settings review, deletion/export handling, red-team testing, and production monitoring.

This page is practical operating guidance, not legal, procurement, privacy, compliance, audit, certification, release-management, incident-response, or security assurance advice.

FAQ

Is every chatbot change a security review?

No. Typos and approved public-source edits can use a lightweight review. But any change that expands access, autonomy, scope, customer promises, retention, source coverage, or downstream actions needs risk-based approval.

Who should approve chatbot changes?

The bot owner should approve routine changes. Add support/product for customer workflow changes, security/privacy for data or connector changes, and executive/business ownership for critical tool actions or customer-impacting risk.

Can we batch small chatbot changes?

Yes, but list each source, prompt, connector, setting, and action change separately. A batch that includes one high-risk item should follow the high-risk approval path.

What if a vendor changes model behavior without notice?

Treat it like a change. Re-run key tests, review monitoring signals, check admin settings and vendor release notes if available, and record whether to continue, limit, or pause the bot.

Do we need screenshots?

Use screenshots only when they help prove settings or customer-visible wording. Do not store screenshots containing customer data, credentials, private prompts, or internal source content in public docs.

What should block release?

Block release if the change lacks an owner, expands data access without approval, skips high-impact tool-action confirmation, breaks handoff, creates unsupported claims, weakens retention or deletion wording, fails regression tests, or has no rollback path.

How soon should we monitor after approval?

For high-risk changes, review the first real conversations the same day. For critical actions, watch tool logs immediately after release and keep a clear disable path ready.

Where should we keep the approval record?

Keep it in the internal system that already stores AI tool evidence: ticket, doc, GRC tracker, or controlled workspace. Do not publish private prompts, customer transcripts, source internals, credentials, or security details.