> For the complete documentation index, see [llms.txt](https://docs.datasentinel.io/manual/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasentinel.io/manual/ai-connector/analyze-and-tune-workloads/what-you-can-analyze.md).

# What you can analyze

Almost any analysis you can phrase is possible: these guides are starting points, not a catalog.

The guides in this section are worked examples, **not an exhaustive list**. Because the assistant reasons over the full range of metrics Datasentinel collects, almost every type of analysis you can phrase becomes a use case. Pick the guide closest to your question and adapt it to your own instances and scenarios.

## Browse the guides by goal

#### <i class="fa-compass" style="color:$primary;">:compass:</i> Start here

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><h4><i class="fa-keyboard" style="color:$primary;">:keyboard:</i></h4></td><td><strong>Skill commands reference</strong></td><td>Every command the Skill answers to, what it does, and what it needs.</td><td><a href="/manual/ai-connector/use-the-assistant/skill-commands.md">Skill commands reference</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-88f6eff0c22c95c04f1db3cdabef4a304d0ef603%2Fcard-skill-commands.jpg?alt=media">card-skill-commands.jpg</a></td></tr><tr><td><h4><i class="fa-file-lines" style="color:$primary;">:file-lines:</i></h4></td><td><strong>Generate and share reports</strong></td><td>Get a platform PDF or an assistant-built HTML or Markdown report of any analysis.</td><td><a href="/manual/ai-connector/use-the-assistant/generate-reports.md">Generate and share reports</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-f074e2f704b0723a0078f2ad1fe30249515aa801%2Fcard-generate-reports.jpg?alt=media">card-generate-reports.jpg</a></td></tr></tbody></table>

#### <i class="fa-server" style="color:$primary;">:server:</i> Navigate your fleet and platforms

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><h4><i class="fa-server" style="color:$primary;">:server:</i></h4></td><td><strong>Browse and navigate your fleet</strong></td><td>Display your monitored inventory at a glance, then narrow it down by tag to one instance.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/browse-your-fleet.md">Browse and navigate your fleet</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-d5a1f6016faac4a0c5e7d6099e2c0377c15c593b%2Fcard-browse-your-fleet.jpg?alt=media">card-browse-your-fleet.jpg</a></td></tr><tr><td><h4><i class="fa-layer-group" style="color:$primary;">:layer-group:</i></h4></td><td><strong>Analyze across multiple instances</strong></td><td>Run cross-instance analyses over a group of servers selected by tag.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/analyze-across-instances.md">Analyze across multiple instances</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-48615129039a8e7b61ee224946c26c724a07fa5d%2Fcard-analyze-across-instances.jpg?alt=media">card-analyze-across-instances.jpg</a></td></tr><tr><td><h4><i class="fa-sitemap" style="color:$primary;">:sitemap:</i></h4></td><td><strong>Work with several platforms</strong></td><td>Connect several Datasentinel platforms to one assistant, switch between them, or get a global view.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/work-with-several-platforms.md">Work with several platforms</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-19e1eafd12c920480a6e8cf422cd1868211edf42%2Fcard-work-with-several-platforms.jpg?alt=media">card-work-with-several-platforms.jpg</a></td></tr></tbody></table>

#### <i class="fa-sliders" style="color:$primary;">:sliders:</i> Tune performance

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><h4><i class="fa-gauge-high" style="color:$primary;">:gauge-high:</i></h4></td><td><strong>Optimize your top queries</strong></td><td>Surface the queries consuming the most time and resources, then act on them.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/optimize-top-queries.md">Optimize your top queries</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-531d7fea9d75dd2a47def4397a0f3e0391708f20%2Fcard-optimize-top-queries.jpg?alt=media">card-optimize-top-queries.jpg</a></td></tr><tr><td><h4><i class="fa-diagram-project" style="color:$primary;">:diagram-project:</i></h4></td><td><strong>Explain execution plans</strong></td><td>Get the plan the planner would choose right now for a statement you paste or a query already analyzed.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/explain-execution-plans.md">Explain execution plans</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-f821a20a5178ae6f412e0af1567932e5259a9a3b%2Fcard-explain-execution-plans.jpg?alt=media">card-explain-execution-plans.jpg</a></td></tr><tr><td><h4><i class="fa-table" style="color:$primary;">:table:</i></h4></td><td><strong>Review tables, indexes and autovacuum</strong></td><td>Review bloat, missing or unused indexes, and whether autovacuum keeps up.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/tables-indexes-and-autovacuum.md">Review tables, indexes and autovacuum</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-41d910132a42d618c9fade9d9f95fe87322efd6f%2Fcard-find-missing-indexes.jpg?alt=media">card-tables-indexes-and-autovacuum.jpg</a></td></tr></tbody></table>

#### <i class="fa-bolt" style="color:$primary;">:bolt:</i> Troubleshoot an instance

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><h4><i class="fa-wave-pulse" style="color:$primary;">:wave-pulse:</i></h4></td><td><strong>Analyze a workload over a time window</strong></td><td>Explain what happened on one instance during a past window: load, waits, queries, tables, blocking.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/analyze-a-workload.md">Analyze a workload over a time window</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-3332b566c407186a017b7d95a97eb3205c7dbdf9%2Fcard-analyze-a-workload.jpg?alt=media">card-analyze-a-workload.jpg</a></td></tr><tr><td><h4><i class="fa-bolt" style="color:$primary;">:bolt:</i></h4></td><td><strong>Diagnose a live performance spike</strong></td><td>Run a real-time analysis to find what is slowing an instance down right now.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/diagnose-live-spike.md">Diagnose a live performance spike</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-138602b052780eb0c9e1b297d533cd54ba517b84%2Fcard-diagnose-live-spike.jpg?alt=media">card-diagnose-live-spike.jpg</a></td></tr><tr><td><h4><i class="fa-lock" style="color:$primary;">:lock:</i></h4></td><td><strong>Investigate a blocking scenario</strong></td><td>Untangle blocking chains, live or in the past: root blockers, objects, queries.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/investigate-blocking-scenarios.md">Investigate a blocking scenario</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-c8e7caa48187e2c61249cdafdad35994b567f57d%2Fcard-investigate-blocking-scenarios.jpg?alt=media">card-investigate-blocking-scenarios.jpg</a></td></tr></tbody></table>

#### <i class="fa-chart-line" style="color:$primary;">:chart-line:</i> Compare and track change

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><h4><i class="fa-chart-line" style="color:$primary;">:chart-line:</i></h4></td><td><strong>Investigate a workload regression</strong></td><td>Compare the workload before and after a change to pinpoint what regressed.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/investigate-workload-regression.md">Investigate a workload regression</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-b84bbd71aa70ec64092a9a3605b14a00a8b4c2e0%2Fcard-investigate-workload-regression.jpg?alt=media">card-investigate-workload-regression.jpg</a></td></tr><tr><td><h4><i class="fa-code-compare" style="color:$primary;">:code-compare:</i></h4></td><td><strong>Compare two workloads</strong></td><td>Compare workloads across time periods, instances, or applications.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/compare-workloads.md">Compare two workloads</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-b3a6dace4cd275ce1631b85a05256ac1f58fcab8%2Fcard-compare-workloads.jpg?alt=media">card-compare-workloads.jpg</a></td></tr><tr><td><h4><i class="fa-binoculars" style="color:$primary;">:binoculars:</i></h4></td><td><strong>Track drift over time</strong></td><td>Proactively spot query, bloat, and configuration drift before it becomes an incident.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/track-drift-over-time.md">Track drift over time</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-b4e1c282092e27a72b5e4341512cf0d62879dc3e%2Fcard-track-drift-over-time.jpg?alt=media">card-track-drift-over-time.jpg</a></td></tr></tbody></table>

#### <i class="fa-arrows-rotate" style="color:$primary;">:arrows-rotate:</i> Scale and automate

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><h4><i class="fa-chart-mixed" style="color:$primary;">:chart-mixed:</i></h4></td><td><strong>Claude Artifact</strong></td><td>Have Claude render your Datasentinel metrics as an interactive dashboard artifact.</td><td><a href="/manual/ai-connector/dynamic-dashboards/claude-artifact.md">Claude Artifact</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-f4c67a4a1a10ec2aa1d87bd91587c2337c21286e%2Fcard-dynamic-dashboard-artifact.jpg?alt=media">card-claude-artifact.jpg</a></td></tr><tr><td><h4><i class="fa-arrows-rotate" style="color:$primary;">:arrows-rotate:</i></h4></td><td><strong>Run recurring analyses</strong></td><td>Schedule repeatable analyses like daily health checks or weekly digests.</td><td><a href="/manual/ai-connector/analyze-and-tune-workloads/recurring-analyses.md">Run recurring analyses</a></td><td><a href="https://196776047-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FDL4xMeOs1Z7fz2LBCNSv%2Fuploads%2Fgit-blob-df6cc8cbb954c33df6e8cd07901313b48b27a1ac%2Fcard-recurring-analyses.jpg?alt=media">card-recurring-analyses.jpg</a></td></tr></tbody></table>

## Analysis areas

The main analysis areas the assistant covers:

| Analysis area             | Examples of what to ask                                                                          |
| ------------------------- | ------------------------------------------------------------------------------------------------ |
| Workload and sessions     | Session load over a window, activity spikes, who was active and when                             |
| Queries                   | Top queries, single-query deep-dive with statistics and execution plan, live plan of a statement |
| I/O, WAL, and checkpoints | I/O-bound windows, WAL volume, checkpoint pressure, slow commits                                 |
| Tables and indexes        | Bloat, sequential scans, unused or missing indexes                                               |
| Locks and blocking        | Blocking chains, root blockers, contended objects, deadlocks                                     |
| Replication               | Standby lag, WAL backlog, paused replay                                                          |
| Configuration and system  | Parameter changes and drift, host CPU, memory, swap, load                                        |
| Live state                | Current sessions, live blocking, VACUUM and index-build progress                                 |
| Comparisons and diagnosis | Two time windows or workloads side by side, broad triage when you don't know what's wrong        |

{% hint style="info" %}
When none of the guides matches your situation, just describe the problem. The assistant runs a broad diagnosis across all these areas, localizes the fault, and routes to the matching deep-dive on its own.
{% endhint %}

Each area also has a named command, such as `datasentinel ash` or `datasentinel locks`, for when you already know which analysis you want. The full list, with what each command needs, is in the [Skill commands reference](/manual/ai-connector/use-the-assistant/skill-commands.md).

## Keep, export, and revisit your analyses

An analysis is not lost once the conversation moves on. AI Connector takes full advantage of the capabilities of the assistant it runs in:

* **Export as a file.** Every analysis can be exported as a self-contained interactive **HTML** report or as a portable **Markdown** file, ready to share or to paste into a ticket, a wiki page, or a pull request. The platform can also generate PDF [reports](https://app.gitbook.com/o/DaDQkGCM7r2TghFSBFLQ/s/yE16Xb3IemPxJWydtPOj/features/key-features/reporting) server-side. See [Generate and share reports](/manual/ai-connector/use-the-assistant/generate-reports.md) for the details of each kind and example prompts.
* **Come back to it later.** The analysis stays in the assistant's conversation history, so you can reopen the session a few days later, re-read the findings, and continue the investigation from where you left off.

## Dynamic charts, where your assistant can draw them

Analyses do not have to stay text-only: the assistant can draw **dynamic charts** of your metrics alongside its findings.

How far that goes depends on the assistant you use and its type:

* **Desktop apps and IDEs** can typically render interactive charts inline with the analysis. Some go further: Claude, for example, can turn an analysis into a full interactive dashboard, as shown in [Claude Artifact](/manual/ai-connector/dynamic-dashboards/claude-artifact.md).
* **CLI assistants** work in a terminal, so charts render as text or not at all. There the assistant presents the same data as equivalent Markdown tables.

Whatever the rendering, the analysis itself is identical: the charts and tables are two views of the same findings, and the exported HTML report keeps its interactive charts in every case.

## On large fleets, tag your instances

Cross-instance analyses select their instances by [tag (TAG)](https://app.gitbook.com/o/DaDQkGCM7r2TghFSBFLQ/s/yE16Xb3IemPxJWydtPOj/features/tips-and-hints/tags): every production server, all instances of an application, a whole datacenter. On a large fleet, the quality of those analyses therefore depends directly on the quality of your tagging.

{% hint style="warning" %}
Before running fleet-wide analyses, make sure every instance carries correct and consistent tags (environment, application, datacenter, and so on). An instance with a missing or misspelled tag silently drops out of every analysis that selects by that tag.
{% endhint %}

See [Analyze across multiple instances](/manual/ai-connector/analyze-and-tune-workloads/analyze-across-instances.md) for cross-instance example prompts.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.datasentinel.io/manual/ai-connector/analyze-and-tune-workloads/what-you-can-analyze.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.