# Cortex AI prompt library This article contains prompts for both the [Cortex MCP](https://docs.cortex.io/get-started/mcp) and the [AI Assistant](https://docs.cortex.io/get-started/cortex-ai-assistant-in-slack-private-beta), inspired by how high-performing engineering teams use Cortex every day. The prompt examples in this article represent effective patterns across different roles and workflows. Use them as a starting point for building your own prompt library tailored to your team and organization. Remember: * **Be specific** - Instead of ***Tell me about services.***, you could say, ***Show me all critical services failing the Production Readiness Scorecard***. This provides you with more actionable information. * **Combine multiple questions when context helps** - Cortex handles complex prompts like ***Who owns orders-api, when was it last deployed, and are there any open incidents?*** You receive richer context in response to one question instead of piecing together three separate queries. * **Reference your organization's specific constructs** - If you've defined custom Scorecards or Initiatives in Cortex, reference them by name. Cortex understands your organization's specific standards and can query against them directly. * **Use follow-up questions to drill down** - Start broad, then go narrow. ***Show me services with failing Scorecards***, followed by ***What specific checks is checkout-service failing?*** moves you from landscape view to action items. * **Build a library of your most-used prompts** - If you ask the same question every Monday morning, save it. Some teams maintain shared prompt libraries so everyone can benefit from patterns that work. ## Use-case based prompts ### Incident response | Prompt | What it does | | --------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | ***Who owns payments-api and who's currently on-call?*** | Gets you the right contact immediately so you can escalate or start investigating. | | ***What changed in checkout-service in the last 24 hours?*** | Most incidents trace back to a recent change, so this is usually the fastest path to identifying the root cause. | | ***Which services depend on user-auth? Who do I need to loop in?*** | Understanding the blast radius of an incident helps you get the right teams involved before downstream impact compounds. | | ***What are the top P1 incident drivers on my team this quarter?*** | Surfaces patterns across incidents so you can address systemic causes rather than treating each one as isolated. | | ***How is our mean time to resolution trending compared to last quarter?*** | Gives you a clear signal on whether your reliability investments are actually improving response time. | ### Service ownership | Prompt | What it does | | ------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------- | | ***Which services have no defined owner?*** | Unowned services are the ones most likely to fall through the cracks during an incident, audit, or migration. | | ***Show me all Tier 1 services with no team assigned.*** | Tier 1 services without ownership represent your highest-risk gap. | | ***Which of our upstream dependencies have no on-call rotation configured?*** | A dependency without on-call coverage means there's no clear path to resolution if it goes down after working hours. | | ***If the data-platform team goes on a code freeze, which of our services are affected?*** | Helps you proactively identify risk and communicate impact before a freeze causes surprises. | ### Production readiness | Prompt | What it does | | --------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ | | ***Which of my team's services are failing the Production Readiness scorecard?*** | Gives you a prioritized view of which services need attention before gaps become incidents. | | ***Which services are Tier 1 but haven't passed Production Readiness?*** | Your most critical services should meet the highest bar; this tells you exactly where that's not the case. | | ***What are the most common gaps across my team's services?*** | Identifying patterns in failures helps you address systemic issues rather than fixing services one by one. | | ***Which services have no runbook, no on-call rotation, or no defined owner?*** | These three gaps together represent a service that no one can reliably respond to when something goes wrong. | ### Engineering health and trends | Prompt | What it does | | ---------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | | ***What are the incident patterns on my team over the last two quarters?*** | Reveals whether your reliability posture is improving over time or if the same failure modes keep recurring. | | ***Has PR size increased recently? Does that correlate with longer review times?*** | Large PRs slow down review cycles and introduce more risk. This tells you whether the two are connected on your team. | | ***Which teams have improved their deploy frequency the most this quarter?*** | Deployment frequency is a leading indicator of team velocity and confidence, so knowing who's improving helps you identify what's working. | | ***What's the overall operational maturity trend for my org over the last 6 months?*** | A high-level view of whether your implementation investments are moving the needle across the organization. | | ***Summarize the key engineering health metrics for my org — I need this for a leadership review.*** | Pulls together the data you'd otherwise spend hours assembling from dashboards, spreadsheets, and status updates. | ### New hire onboarding | Prompt | What it does | | ---------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- | | ***What dependencies does my team's services have and who owns them?*** | The fastest way to understand your team's scope of responsibility without waiting for someone to walk you through it. | | ***Which of our services have open action items or are failing their Scorecard?*** | Surfaces the most pressing work on your team so you can start contributing without needing a full handoff. | | ***Give me a summary of what my team has shipped in the last 90 days.*** | Gets you up to speed on recent deployments so you can have informed conversations with your team from day one. | ### Migration tracking | Prompt | What it does | | --------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | | ***Which services have been migrated to \[NEW PLATFORM] and which are still pending?*** | Gives you a real-time view of migration progress without chasing teams for status updates. | | ***Which teams haven't completed the migration yet and what's blocking them?*** | Surfaces where the migration is stalling so you can direct support to the right places before deadlines slip. | | ***Which migrated services are failing their scorecard since the cutover?*** | Catches regressions introduced by the migration before they turn into incidents or compliance gaps. | | ***What's the migration completion rate across the org this quarter?*** | Tracks overall migration progress across the org so you know whether you're on pace to hit your target or need to intervene. | ## Role-based prompts ### Prompts for engineers The best prompts for engineers eliminate context switching at the moments when focus matters most. #### Understanding unfamiliar services | Prompt | What it does | | ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | ***Tell me about the \[SERVICE NAME] service, including who owns it, what it does, and where the documentation lives.*** | Pulls everything from your [Cortex catalog](https://www.cortex.io/products/service-catalog) at once. You get ownership, a description of what the service does, links to documentation, and the team's communication channels. Instead of hunting across wikis, Slack, and GitHub, you have the context you need to start working. | | ***Show me the dependencies for \[SERVICE NAME]. Which services does it depend on, and which services depend on it?*** | Understanding the dependency graph is critical when planning changes with potential downstream impact. This prompt reveals what might break and which teams need to be in the conversation before you make a move. | | ***Which Scorecard is \[SERVICE NAME] failing, and what do I need to fix?*** | Transforms maintenance from reactive to proactive. Instead of waiting for your platform team to flag issues or discovering gaps during an incident, you see exactly which Scorecards are failing and what specific checks need attention. You can address production readiness, security, or documentation gaps on your own schedule, before they become blockers. | #### During code review | Prompt | What it does | | ---------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Check the Scorecards for \[SERVICE NAME]. Does this service meet our production readiness standards?*** | Starting here when you're unfamiliar with a service changes the conversation. If the service is already failing key Scorecards, you'll know which questions to ask and where the risks actually are. | | ***Show me recent incidents for \[SERVICE NAME].*** | Past incidents tell you where a service has been fragile. When you see that history before approving changes, you can evaluate whether the PR addresses root causes or introduces new failure modes. | #### Tracking work | Prompt | What it does | | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***What Initiatives are assigned to the Engineering team, and what's the status of each?*** | Condenses your weekly status check into a single query. Run it at the start of your week or during standup and you get a complete picture of your Initiative commitments and their current state. Instead of navigating to the Cortex web UI or mentally tracking what you're responsible for, you see everything assigned to you without leaving your IDE or chat interface. | | ***Show me the details for \[INITIATIVE NAME]. What still needs to be done?*** | When you're ready to make progress on a specific Initiative, this surfaces the remaining tasks and their current state. You know exactly what's left and where to focus. | ### Prompts for engineering leaders The best prompts for engineering leaders are about trends, patterns, and the health of systems; these prompts surface the signals that inform strategic decisions. #### Understanding team health | Prompt | What it does | | ------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Show me MTTR trends over the last quarter. How has it changed?*** | Incident response either gets faster or it doesn't. If MTTR is climbing, something in your system has degraded. This prompt gives you the trend line and a clear signal to investigate process or tooling gaps. | | ***Which teams have the most failing Scorecards right now?*** | Surfaces which teams are struggling with compliance or buried in technical debt. The answer reveals where support and resources should flow. Instead of waiting for teams to escalate problems or discovering issues through incident patterns, you have a clear view of which teams need help right now. That visibility lets you have proactive conversations about priorities, staffing, or process changes before compliance gaps become production incidents. | | ***How has deployment frequency changed over the last six months for the Platform team?*** |

Deployment frequency serves as a proxy for both velocity and confidence. When you track this metric over time, you get clear evidence of whether your investments in tooling and process improvements are actually working.

If deployment frequency is climbing, teams are shipping faster and feel confident doing it. If it's flat or declining despite investments, you need to investigate whether new tools are adding friction, whether processes are getting in the way, or whether something else is slowing teams down. The trend line tells you whether to double down on your current approach or change course.

| #### Tracking AI adoption impact | Prompt | What it does | | --------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***How has AI adoption impacted MTTR and deployment frequency over the last quarter?*** |

Connects AI spending directly to concrete business outcomes. When you run this query, you're comparing metrics before and after AI tool adoption. If MTTR dropped and deployment frequency increased after rolling out Copilot or similar tools, you have hard data to justify continued investment and potentially expand the rollout.

If the metrics haven't moved despite adoption, you need to ask different questions: Are teams actually using the tools? Do they need more training? Are the tools solving the wrong problems? The comparison gives you evidence to either double down on your AI strategy or course-correct before spending more.

| | ***Which teams have adopted AI tools, and how does their velocity compare to teams that haven't?*** |

Reveals whether AI adoption is actually delivering the productivity gains you expected. The comparison between adopters and non-adopters gives you a clear control group to measure impact. If teams using AI tools show meaningfully higher velocity, you have validation to expand the rollout and invest more.

If there's no significant difference, or if adopters are actually slower, you need to understand why. Maybe teams need better training on how to use the tools effectively. Maybe the tools work better for certain types of work than others. Maybe adoption is superficial and teams aren't integrating the tools into their actual workflows. The data points you toward the right interventions.

| #### Spotting bottlenecks | Prompt | What it does | | ------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Where are the biggest bottlenecks slowing down the Checkout team?*** | When a team's velocity drops unexpectedly, this surfaces the patterns that sprint metrics miss: services with high incident rates, missing documentation, or blocked Initiatives. You get data, not speculation. | | ***Show me services with the highest incident rates in the last month.*** | High incident rates point to deeper reliability issues. This tells you where to invest in stability before those services become everyone's problem. | ### Prompts for platform teams The best prompts for platform teams show you where adoption is working, where it's stalled, and which teams need support. #### Tracking standards adoption | Prompt | What it does | | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Show me how teams are performing on the Production Readiness Scorecard. Which services are failing?*** | Gives you a complete view of compliance across the organization without manually checking each team's services. You see which teams are struggling to meet standards and which services create the most risk. The answer tells you where to focus your enablement efforts and which conversations to prioritize. Instead of discovering compliance gaps reactively during incidents or audits, you have a real-time picture of organizational health. | | ***Which services don't have runbooks, and who owns them?*** |

Missing runbooks are incidents waiting to happen. When something breaks at 3 AM, responders need clear guidance to restore service quickly. This prompt shows you exactly which services lack that critical documentation and who's responsible for creating it.

With this information, you can prioritize outreach based on service criticality. A critical payment service without a runbook demands immediate attention, while a lower-tier internal tool might wait. Instead of discovering documentation gaps during an active incident when every minute counts, you can systematically close them before they cost you hours of downtime.

| | ***Show me AI maturity Scorecard results across all teams. Where are the biggest gaps?*** | If you're driving AI adoption, this reveals which aspects of maturity need attention. The gaps tell you whether teams need training, tooling, process changes, or something else entirely. | #### Managing Initiatives | Prompt | What it does | | ---------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Which services are blocking completion of the \[INITIATIVE NAME]?*** | When an initiative stalls, this identifies exactly which services or teams are holding things up. Now you know where to focus your attention and who needs support. | | ***Show me progress on the Kubernetes Migration Initiative. Which teams are on track, and which are falling behind?*** | Surfaces real-time status across every team involved in the initiative without sending Slack messages or requesting manual updates. You get an immediate picture of which teams are making progress, which are stuck, and which haven't started. That visibility lets you direct support and resources to the teams that need it most, rather than treating every team the same or discovering delays only when deadlines slip. | | ***Give me a plan to get the Checkout team back on track with production readiness.*** | Once you've identified a team falling behind, this generates a concrete action plan based on the specific gaps in their Scorecards and service metadata. You move straight to solutions. | #### Gap analysis | Prompt | What it does | | ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Which critical services are missing SLOs?*** | SLOs are foundational to reliability. This scopes the gap and identifies which services should be prioritized based on business impact before an incident forces the conversation. | | ***Show me services without proper monitoring. What's missing?*** | Monitoring gaps are blind spots waiting to bite you during incidents. This surfaces which services need instrumentation and what specific monitoring is absent, so you can build a targeted remediation plan. | ### Prompts for SREs The best prompts for SRE teams focus on proactive incident prevention or responding quickly to a incident in progress. #### During incidents | Prompt | What it does | | ----------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | ***Who's on call for \[SERVICE NAME] right now, and when was it last deployed?*** | The first question in almost every incident. One prompt gets you the owner, the on-call contact, and recent deployment history. You can escalate or start investigating without hunting through five different systems. | | ***Show me recent deploys and changes for \[SERVICE NAME].*** | Most incidents trace back to recent changes. This gives you a timeline pointing to likely culprits so you can focus your investigation on what actually changed. | | ***Show me the incident readiness Scorecard for \[SERVICE NAME]. Are we prepared to respond?*** | Not all services are equally ready for incidents. This tells you whether runbooks exist, whether monitoring is in place, and whether escalation paths are documented. You know what tools you have before you need them. | #### Proactive reliability work | Prompt | What it does | | -------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | ***Show me services with the highest MTTR in the last month.*** | High MTTR means certain services are consistently difficult to debug or restore. This tells you where reliability improvements will have the biggest impact on your time and your team's sanity. | | ***Which critical services have had the most incidents recently?*** | Frequent incidents signal deeper problems that incident response won't fix. This helps you spot patterns and prioritize services that need architectural investigation, not just patches. | | ***Show me services that are missing runbooks or escalation procedures.*** | When incidents happen, responders need clear guidance. This identifies documentation gaps that will slow response time before they cost you hours during an outage. | ### Prompts for security engineering teams The best prompts for security engineers help them monitor, audit, and enforce security posture across services. #### Compliance monitoring | Prompt | What it does | | ----------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Which services are failing our SOC-2 Scorecard?*** | Gives you a view of SOC-2 compliance across the organization without manually checking each team's services. The answer tells you where to focus your efforts and which conversations to prioritize. Instead of discovering compliance gaps reactively during incidents or audits, you have a real-time picture of organizational health. | #### Proactive security health | Prompt | What it does | | ---------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | ***Which services have no on-call rotation configured in PagerDuty?*** | When incidents happen, it's important to have on-call information readily available to ensure a fast response time. | | ***What is the progress on my Security Initiative and what are some quick wins?*** | Surfaces real-time status for an Initiative without requesting manual updates from team members. You get an immediate picture of which entities are making progress and which are not. That visibility lets you direct support and resources to the teams that need it most. | | ***List all services with open vulnerabilities labeled CRITICAL or HIGH.*** | Helps determine which services need attention. | ### Prompts for product managers The best prompts for product managers focus on visibility, delivery health, and compliance to engineering standards that affect product velocity and quality. #### Delivery and health metrics | Prompt | What it does | | ---------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- | | ***Which services in the \[PRODUCT AREA] domain are failing their DORA metrics?*** | Gives quick insight into which services in that product area domain are failing DORA metrics. | #### Initiatives and adoption tracking | Prompt | What it does | | ------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------ | | ***Give me all currently active initiatives and ideas for how I can improve them.*** | Helps track progress on key initiatives and ensure teams are moving toward business goals. | | ***Give me links to the docs and runbooks for \[REPOSITORY].*** | Helps find the documentation for a feature's related repository. | --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.cortex.io/get-started/library.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.