Copilot prompt library
Every prompt shown on the channel, with what it's for and what you must check afterwards.
Reviewing a 12-page raw material specification with Copilot Chat
- 1
Upload documents and extract core parameters
Review attached supplier spec Doc A and site template Doc B. Extract the allergen, microbiological, and storage parameters into a comparison table.You check: Verify all table entries against the original supplier PDF to ensure no figures or qualifiers were misread.
- 2
Identify omissions and vague statements
Highlight any parameters in Doc B that are missing, incomplete, or ambiguous in Doc A (e.g. non-numeric shelf-life or unlisted pathogens).You check: Check whether omitted items are addressed elsewhere in the raw PDF appendices or referenced third-party certifications.
- 3
Draft supplier clarification email
Draft a concise, professional technical email to the supplier querying the highlighted gaps. Request specific numeric limits and clear allergen declarations.You check: Review tone and ensure questions reflect the exact risk criteria set by the site technical management.
- 4
Create sign-off readiness summary
Create an internal technical review memo summarising findings, pending supplier responses, and a hold status for approval.You check: Ensure status is marked as 'Pending' in internal files; do not issue raw material approval until data is verified.
Drafting an unverified fishbone diagram with Copilot
- 1
Upload logs and establish incident timeline
Review the uploaded complaint, batch log, and maintenance records. Draft a chronological timeline for Line 4 between 06:00 and 13:00 on 14/05/2026, noting relevant engineering interventions.You check: Verify all timestamps against the signed production and engineering job sheets to confirm no shifts or missing operational events were omitted.
- 2
Identify conflicting information and evidence gaps
Compare the detection log and maintenance history against the complaint item. List what evidence is missing or unverified regarding hard blue plastic components on this line.You check: Cross-reference against the site's physical foreign body register to see if the blue modular belt or transfer chute guides match the fragment description.
- 3
Draft structured fishbone categories and exploratory questions
Draft an Ishikawa fishbone structure (Man, Machine, Material, Method, Milieu) with 3 exploratory questions per branch to investigate potential entry points for blue plastic.You check: Ensure questions avoid leading conclusions and adapt the technical prompts to reflect actual Line 4 equipment layouts and handling procedures.
- 4
Prepare investigation meeting briefing sheet
Format the timeline, identified evidence gaps, and fishbone questions into a one-page investigation meeting agenda for the production engineer and hygiene lead.You check: Confirm the briefing material contains only anonymised production data and accurately states known physical facts versus hypotheses.
Foreign Body Complaints: Using AI to Spot Missing Evidence
- 1
Upload logs and establish incident timeline
Review the uploaded complaint, batch log, and maintenance records. Draft a chronological timeline for Line 4 between 06:00 and 13:00 on 14/05/2026, noting relevant engineering interventions.You check: Verify all timestamps against the signed production and engineering job sheets to confirm no shifts or missing operational events were omitted.
- 2
Identify conflicting information and evidence gaps
Compare the detection log and maintenance history against the complaint item. List what evidence is missing or unverified regarding hard blue plastic components on this line.You check: Cross-reference against the site's physical foreign body register to see if the blue modular belt or transfer chute guides match the fragment description.
- 3
Draft structured fishbone categories and exploratory questions
Draft an Ishikawa fishbone structure (Man, Machine, Material, Method, Milieu) with 3 exploratory questions per branch to investigate potential entry points for blue plastic.You check: Ensure questions avoid leading conclusions and adapt the technical prompts to reflect actual Line 4 equipment layouts and handling procedures.
- 4
Prepare investigation meeting briefing sheet
Format the timeline, identified evidence gaps, and fishbone questions into a one-page investigation meeting agenda for the production engineer and hygiene lead.You check: Confirm the briefing material contains only anonymised production data and accurately states known physical facts versus hypotheses.
Build an Incident Timeline from Fragmented Records with Copilot
- 1
Upload logs and establish incident timeline
Review the uploaded complaint, batch log, and maintenance records. Draft a chronological timeline for Line 4 between 06:00 and 13:00 on 14/05/2026, noting relevant engineering interventions.You check: Verify all timestamps against the signed production and engineering job sheets to confirm no shifts or missing operational events were omitted.
- 2
Identify conflicting information and evidence gaps
Compare the detection log and maintenance history against the complaint item. List what evidence is missing or unverified regarding hard blue plastic components on this line.You check: Cross-reference against the site's physical foreign body register to see if the blue modular belt or transfer chute guides match the fragment description.
- 3
Draft structured fishbone categories and exploratory questions
Draft an Ishikawa fishbone structure (Man, Machine, Material, Method, Milieu) with 3 exploratory questions per branch to investigate potential entry points for blue plastic.You check: Ensure questions avoid leading conclusions and adapt the technical prompts to reflect actual Line 4 equipment layouts and handling procedures.
- 4
Prepare investigation meeting briefing sheet
Format the timeline, identified evidence gaps, and fishbone questions into a one-page investigation meeting agenda for the production engineer and hygiene lead.You check: Confirm the briefing material contains only anonymised production data and accurately states known physical facts versus hypotheses.
Allergen screening with Copilot: what AI cannot verify
- 1
Upload and compare raw material specifications
Compare these two uploaded specifications for Biscuit Crumb (Old vs New). Provide a table showing differences in ingredient listing, compound ingredients, and declared allergens.You check: Verify every row against the original PDF specifications to confirm no compound ingredient details were overlooked or misparsed.
- 2
Map raw material changes to finished products
Review the attached Site Recipe Matrix. List every finished SKU that uses raw material RM-042 (Biscuit Crumb), showing current label allergens and the impact of the added Egg allergen.You check: Cross-check the SKU list against the live site recipe management database to ensure recipe versioning is current.
- 3
Draft an allergen risk assessment questionnaire
Draft an internal checklist for our technical team to assess factory impacts of introducing Egg via RM-042, covering storage, line segregation, utensil colour-coding, and cleaning verification.You check: Review the checklist against actual factory layout, current allergen profiles on that line, and validated cleaning regimes.
- 4
Draft supplier clarification and internal notification
Draft a formal technical notification to internal NPD and Labelling teams summarising the change to RM-042 and requesting a label update hold on affected SKUs.You check: Ensure the notification reflects agreed site approval workflows and correct internal stakeholders before sending.
Tracing recipe allergen changes across products with Copilot Chat
- 1
Upload and compare raw material specifications
Compare these two uploaded specifications for Biscuit Crumb (Old vs New). Provide a table showing differences in ingredient listing, compound ingredients, and declared allergens.You check: Verify every row against the original PDF specifications to confirm no compound ingredient details were overlooked or misparsed.
- 2
Map raw material changes to finished products
Review the attached Site Recipe Matrix. List every finished SKU that uses raw material RM-042 (Biscuit Crumb), showing current label allergens and the impact of the added Egg allergen.You check: Cross-check the SKU list against the live site recipe management database to ensure recipe versioning is current.
- 3
Draft an allergen risk assessment questionnaire
Draft an internal checklist for our technical team to assess factory impacts of introducing Egg via RM-042, covering storage, line segregation, utensil colour-coding, and cleaning verification.You check: Review the checklist against actual factory layout, current allergen profiles on that line, and validated cleaning regimes.
- 4
Draft supplier clarification and internal notification
Draft a formal technical notification to internal NPD and Labelling teams summarising the change to RM-042 and requesting a label update hold on affected SKUs.You check: Ensure the notification reflects agreed site approval workflows and correct internal stakeholders before sending.
Comparing supplier specification versions using Copilot Chat
- 1
Upload and compare raw material specifications
Compare these two uploaded specifications for Biscuit Crumb (Old vs New). Provide a table showing differences in ingredient listing, compound ingredients, and declared allergens.You check: Verify every row against the original PDF specifications to confirm no compound ingredient details were overlooked or misparsed.
- 2
Map raw material changes to finished products
Review the attached Site Recipe Matrix. List every finished SKU that uses raw material RM-042 (Biscuit Crumb), showing current label allergens and the impact of the added Egg allergen.You check: Cross-check the SKU list against the live site recipe management database to ensure recipe versioning is current.
- 3
Draft an allergen risk assessment questionnaire
Draft an internal checklist for our technical team to assess factory impacts of introducing Egg via RM-042, covering storage, line segregation, utensil colour-coding, and cleaning verification.You check: Review the checklist against actual factory layout, current allergen profiles on that line, and validated cleaning regimes.
- 4
Draft supplier clarification and internal notification
Draft a formal technical notification to internal NPD and Labelling teams summarising the change to RM-042 and requesting a label update hold on affected SKUs.You check: Ensure the notification reflects agreed site approval workflows and correct internal stakeholders before sending.
Prepare an audit closing meeting summary with Copilot Chat
- 1
Input anonymised closing notes
Here are raw notes from today's internal audit closing meeting. Structure them into a professional summary table: Area, Finding, Immediate Correction, Preventive Action, Owner, Target Date.You check: Confirm that the technical intent of each finding and agreed action is preserved without altered context.
- 2
Separate open actions from closed-out items
Split the table into two sections: 1. Actions requiring completion (with owner and deadline), and 2. Rectified on-site during the audit. Keep descriptions brief and factual.You check: Verify that items marked closed were genuinely verified before signing off.
- 3
Draft covering distribution text
Draft a concise 3-sentence closing email to department attendees. Request review and formal agreement on owners and deadlines by midday tomorrow.You check: Ensure names, shift roles, and deadlines align with site escalation timelines.
- 4
Final technical verification
Check the drafted actions table and flag any missing target dates or ambiguous action owners.You check: Read the entire draft against your original notepad to confirm no verbal caveats or nuances were lost.
Pasting CCP Logs into Copilot: 3 Data Hygiene Rules
- 1
Confirm work account sign-in
Review this test line: 'System check only'. Confirm enterprise data protection applies to this session.You check: Ensure the green work profile or shield icon is visible in the browser, not a personal Microsoft account.
- 2
Anonymise sensitive identifiers before pasting
Analyse these anonymised deviation notes: Date, Line_ID, Issue, Action. Line A: seal temp 168C, reset to 175C. Line B: cook temp 73C, cook extended to 75C. Group by deviation type.You check: Confirm all operator names, raw supplier codes and identifiable customer details were removed before submission.
- 3
Request a structured summary table
Format these grouped deviations into a 3-column table: Deviation Category, Count, Summary of Corrective Action Taken.You check: Check the counts and corrective actions against the original source log to ensure nothing was added or omitted.
- 4
Verify drafted text against physical records
Draft a 2-sentence summary note for a weekly QA meeting based strictly on this table, without adding assumptions.You check: The QA coordinator reviews the wording for technical accuracy and signs off the summary before distributing it to the team.
Checking audit records against clause requirements with Copilot
- 1
Set the context and task boundary
Act as a compliance assistant. I will provide a standard requirement intent and an internal record. Analyse what the record demonstrates and what it fails to demonstrate.You check: Ensure no company-confidential identifiers or real operative names were entered into the session.
- 2
Supply the requirement intent and the record text
Intent: Verify systems are implemented and effective. Record: 'Walked line during changeover. Operatives had completed sign-off sheet. Clean down seen. Complete.' What is shown and what is missing?You check: Confirm that the gaps identified align with the actual scope of the procedure being audited.
- 3
Request specific gap-closing prompt for future records
List 3 specific objective evidence questions an auditor should answer in the record to demonstrate system effectiveness for an allergen changeover.You check: Select only questions that reflect the site's documented changeover and cleaning procedures.
- 4
Document the coaching point for the internal auditor
Draft a concise 2-sentence feedback note for the internal auditor explaining how to record objective evidence of effectiveness rather than just activity.You check: Review tone and ensure the feedback is constructive and supported by technical management.
Find missing information in draft procedures with Copilot Chat
- 1
Upload document to Copilot Chat
Review this uploaded draft glass control procedure. List standard food manufacturing sections that are missing or incomplete.You check: Confirm whether the identified gaps are truly missing or handled within a separate existing site procedure.
- 2
Evaluate document control attributes
Check this procedure against standard document control expectations. What metadata, review dates, or approval fields are missing?You check: Verify against site quality management system templates to confirm required header and footer fields.
- 3
Review record completion requirements
What specific record-keeping instructions or referenced forms are omitted in the breakage response section?You check: Check that the required breakage record aligns with physical log sheets used on the production floor.
- 4
Synthesise review action list
Summarise these gaps into a concise checklist for the Technical Manager to address before the HACCP meeting.You check: Authorise the final additions to the procedure before presenting the draft to the wider HACCP team.
Reviewing CAPA Effectiveness Checks with Copilot Chat
- 1
Upload spreadsheet and cluster recurring defects
Analyse the attached non-conformance register. Group recurring packaging defects by line and issue description, providing a count for each group.You check: Verify that distinct engineering issues have not been inappropriately merged into a single generic cluster.
- 2
Identify deficient preventive actions and missed reviews
Review the Line 2 seal defect records. Flag rows where Preventive_Action repeats Immediate_Correction or where Effectiveness_Review_Date is blank.You check: Cross-check flagged rows against the raw register to ensure data was not misread or blank cells hallucinated.
- 3
Analyse shift and timeline trends
For the identified Line 2 seal records, summarise occurrences by date and shift. Note whether the recurrence links to specific shift patterns.You check: Review production shift logs for those dates to confirm whether tooling changes or maintenance handover logs correlate with the findings.
- 4
Draft weekly quality meeting brief
Draft 3 concise bullet points for the quality meeting summarising Line 2 recurring seal issues, showing why previous CAPAs failed and proposing next review steps.You check: Check tone and accuracy against actual site engineering terms and ensure no unverified assumptions are presented as fact.
Identify CAPAs with no preventive action using Copilot
- 1
Upload spreadsheet and cluster recurring defects
Analyse the attached non-conformance register. Group recurring packaging defects by line and issue description, providing a count for each group.You check: Verify that distinct engineering issues have not been inappropriately merged into a single generic cluster.
- 2
Identify deficient preventive actions and missed reviews
Review the Line 2 seal defect records. Flag rows where Preventive_Action repeats Immediate_Correction or where Effectiveness_Review_Date is blank.You check: Cross-check flagged rows against the raw register to ensure data was not misread or blank cells hallucinated.
- 3
Analyse shift and timeline trends
For the identified Line 2 seal records, summarise occurrences by date and shift. Note whether the recurrence links to specific shift patterns.You check: Review production shift logs for those dates to confirm whether tooling changes or maintenance handover logs correlate with the findings.
- 4
Draft weekly quality meeting brief
Draft 3 concise bullet points for the quality meeting summarising Line 2 recurring seal issues, showing why previous CAPAs failed and proposing next review steps.You check: Check tone and accuracy against actual site engineering terms and ensure no unverified assumptions are presented as fact.
Spotting repeat non-conformances across shifts using Copilot Chat
- 1
Upload spreadsheet and cluster recurring defects
Analyse the attached non-conformance register. Group recurring packaging defects by line and issue description, providing a count for each group.You check: Verify that distinct engineering issues have not been inappropriately merged into a single generic cluster.
- 2
Identify deficient preventive actions and missed reviews
Review the Line 2 seal defect records. Flag rows where Preventive_Action repeats Immediate_Correction or where Effectiveness_Review_Date is blank.You check: Cross-check flagged rows against the raw register to ensure data was not misread or blank cells hallucinated.
- 3
Analyse shift and timeline trends
For the identified Line 2 seal records, summarise occurrences by date and shift. Note whether the recurrence links to specific shift patterns.You check: Review production shift logs for those dates to confirm whether tooling changes or maintenance handover logs correlate with the findings.
- 4
Draft weekly quality meeting brief
Draft 3 concise bullet points for the quality meeting summarising Line 2 recurring seal issues, showing why previous CAPAs failed and proposing next review steps.You check: Check tone and accuracy against actual site engineering terms and ensure no unverified assumptions are presented as fact.
Draft a Risk-Based Internal Audit Checklist with Copilot Chat
- 1
Upload previous audit report and extract open or recurring themes
Here is our 2025 internal audit report for goods-in. List all non-conformances and observations, their root causes if stated, and specify which areas require verification during this year's visit.You check: Verify that all findings from the original 2025 document were captured and no findings were omitted or misclassified.
- 2
Cross-reference with open CAPA tracker
Upload open CAPA tracker. Compare with the previous audit summary. Which actions relevant to goods-in and storage remain open or overdue, and who is accountable?You check: Check internal QMS to confirm whether overdue actions were formally extended or closed out since the last export.
- 3
Analyse intake rejections to identify operational failure patterns
Upload Q1 rejection log. Identify the top three recurring causes of rejection and any supplier-specific trends that should be checked during live intake inspection.You check: Ensure intake figures align with technical site experience and that supplier details match the current approved supplier register.
- 4
Draft targeted risk-based audit checklist and sampling guide
Draft an audit checklist for goods-in focusing on intake documentation, allergen segregation, and temperature monitoring. Include 6 direct questions and objective evidence to review.You check: Review the drafted questions against the site's written intake procedures and amend the sampling depth based on current production volumes.
Extract previous audit findings for internal audits using Copilot
- 1
Upload previous audit report and extract open or recurring themes
Here is our 2025 internal audit report for goods-in. List all non-conformances and observations, their root causes if stated, and specify which areas require verification during this year's visit.You check: Verify that all findings from the original 2025 document were captured and no findings were omitted or misclassified.
- 2
Cross-reference with open CAPA tracker
Upload open CAPA tracker. Compare with the previous audit summary. Which actions relevant to goods-in and storage remain open or overdue, and who is accountable?You check: Check internal QMS to confirm whether overdue actions were formally extended or closed out since the last export.
- 3
Analyse intake rejections to identify operational failure patterns
Upload Q1 rejection log. Identify the top three recurring causes of rejection and any supplier-specific trends that should be checked during live intake inspection.You check: Ensure intake figures align with technical site experience and that supplier details match the current approved supplier register.
- 4
Draft targeted risk-based audit checklist and sampling guide
Draft an audit checklist for goods-in focusing on intake documentation, allergen segregation, and temperature monitoring. Include 6 direct questions and objective evidence to review.You check: Review the drafted questions against the site's written intake procedures and amend the sampling depth based on current production volumes.
Analyse monthly non-conformance trends with Copilot Chat
- 1
Upload anonymised CSV log and request high-level categorization
Review this non-conformance export. Group the 22 incidents into common technical themes and state the frequency of each theme.You check: Confirm that all 22 rows were included and that the theme boundaries reflect real production issues.
- 2
Cross-tabulate repeat themes by operational variables
For the sealing issues theme, break down occurrences by Line and Shift. Note any repeat patterns.You check: Cross-reference the raw export rows to confirm line and shift attribution matches source log entries.
- 3
Evaluate stated root causes for repeat patterns
Summarise the stated root causes for the Line 1 Night shift sealing failures. Did the investigations identify a common underlying factor?You check: Verify engineering job sheets and physical maintenance logs to validate whether an underlying mechanical fault was missed.
- 4
Draft investigation focus points for the engineering and QA review
Draft three factual review questions for engineering regarding Line 1 Night shift sealing performance based on these records.You check: Technical manager reviews questions for appropriateness before issuing to engineering.
Turn customer complaint trends into targeted engineering questions
- 1
Upload and data profile check
Review the uploaded complaints log. Summarise total complaint count by Production_Line and identify the three most frequent Logged_Category values across the dataset.You check: Cross-check the totals and row count against Excel pivot table figures to ensure no rows were skipped or truncated during upload.
- 2
Free-text theme clustering
Analyse Customer_Comments for Line 2. Group the comments into 4 to 5 common defect themes based on the text descriptions, regardless of the Logged_Category column. List count per theme.You check: Spot-check 5 to 10 source rows within the identified clusters to ensure the free text actually supports the assigned theme and has not been misread.
- 3
Cross-tabulation and anomaly detection
Compare the 'Customer_Comments' themes against 'Logged_Category' for Line 2. Identify any defect type that appears frequently in comments but is split across multiple category labels.You check: Confirm the re-categorised complaints against original intake notes to verify whether site intake staff require retraining on complaint classification.
- 4
Draft meeting summary and investigative prompts
Draft a neutral, factual 3-paragraph summary of the Line 2 seal trend for the monthly operations review. Include 4 targeted investigative questions for the packaging line engineer.You check: Review tone to ensure it remains collaborative and factual, edit technical questions to reflect actual line equipment, and remove any assumed root causes before circulating.
Spotting Hidden Complaint Trends with Copilot Chat
- 1
Upload and data profile check
Review the uploaded complaints log. Summarise total complaint count by Production_Line and identify the three most frequent Logged_Category values across the dataset.You check: Cross-check the totals and row count against Excel pivot table figures to ensure no rows were skipped or truncated during upload.
- 2
Free-text theme clustering
Analyse Customer_Comments for Line 2. Group the comments into 4 to 5 common defect themes based on the text descriptions, regardless of the Logged_Category column. List count per theme.You check: Spot-check 5 to 10 source rows within the identified clusters to ensure the free text actually supports the assigned theme and has not been misread.
- 3
Cross-tabulation and anomaly detection
Compare the 'Customer_Comments' themes against 'Logged_Category' for Line 2. Identify any defect type that appears frequently in comments but is split across multiple category labels.You check: Confirm the re-categorised complaints against original intake notes to verify whether site intake staff require retraining on complaint classification.
- 4
Draft meeting summary and investigative prompts
Draft a neutral, factual 3-paragraph summary of the Line 2 seal trend for the monthly operations review. Include 4 targeted investigative questions for the packaging line engineer.You check: Review tone to ensure it remains collaborative and factual, edit technical questions to reflect actual line equipment, and remove any assumed root causes before circulating.
Grouping free-text complaint logs into themes with Copilot
- 1
Upload and data profile check
Review the uploaded complaints log. Summarise total complaint count by Production_Line and identify the three most frequent Logged_Category values across the dataset.You check: Cross-check the totals and row count against Excel pivot table figures to ensure no rows were skipped or truncated during upload.
- 2
Free-text theme clustering
Analyse Customer_Comments for Line 2. Group the comments into 4 to 5 common defect themes based on the text descriptions, regardless of the Logged_Category column. List count per theme.You check: Spot-check 5 to 10 source rows within the identified clusters to ensure the free text actually supports the assigned theme and has not been misread.
- 3
Cross-tabulation and anomaly detection
Compare the 'Customer_Comments' themes against 'Logged_Category' for Line 2. Identify any defect type that appears frequently in comments but is split across multiple category labels.You check: Confirm the re-categorised complaints against original intake notes to verify whether site intake staff require retraining on complaint classification.
- 4
Draft meeting summary and investigative prompts
Draft a neutral, factual 3-paragraph summary of the Line 2 seal trend for the monthly operations review. Include 4 targeted investigative questions for the packaging line engineer.You check: Review tone to ensure it remains collaborative and factual, edit technical questions to reflect actual line equipment, and remove any assumed root causes before circulating.
Summarising long audit non-conformances with Copilot Chat
- 1
Anonymise finding and extract core summary
Summarise this audit finding into three bullets: 1. Core breakdown, 2. Requirement area, 3. Likely objective evidence expected to close it. Text: [paste anonymised narrative]You check: Verify that Copilot has captured the full factual scope of the observation without omitting critical context.
- 2
Draft corrective and preventive action structure
Draft a practical action summary for the factory team: separate the immediate correction, the root-cause investigation prompt, and the systemic preventive action.You check: Ensure the actions are operationally realistic and align with site governance procedures.
- 3
Define objective evidence checklist
List the specific documents, meeting records, or log entries an auditor will expect to see to verify closure of this action.You check: Confirm that the listed documents match site QMS formats and satisfy clause 3.4 expectations.
- 4
Format for internal corrective action register
Format the output as a single table row: Issue Summary | Immediate Correction | Preventative Action | Required Evidence | Target Date | Owner.You check: Insert genuine departmental owners and agreed realistic target dates; verify no placeholder details remain.
TFCD content is general guidance, not professional advice for your site. Always check requirements against your own licensed copy of the BRCGS Standard and your customers' codes of practice.