diff --git a/docs/Admin-and-data/Catalog/catalog.md b/docs/Admin-and-data/Catalog/catalog.md index ea3cb1f..d15a6ac 100644 --- a/docs/Admin-and-data/Catalog/catalog.md +++ b/docs/Admin-and-data/Catalog/catalog.md @@ -2,6 +2,8 @@ The Service Catalog is a persistent record of everything you run - your services and the infrastructure they depend on. Unlike the Services overview, which only shows what is currently sending telemetry, the catalog tracks entries whether they are active or quiet. It gives every service an owner, a tier, and a home, so when something breaks at 2am, nobody has to guess who to contact or what is affected. +The catalog is also the brain behind Coworker. When Coworker investigates an alert or runs a check, it draws on catalog entries to understand what a service does, who owns it, what it depends on, and what has happened to it before. That pre-loaded context means Coworker spends fewer AI Tokens rediscovering information it could already know - and produces better investigations as a result. The more complete your catalog, the more effective Coworker becomes. + The catalog also powers incident response: affected services on an incident link directly to their catalog entries, runbooks surface based on catalog service matches, and Analytics surfaces which catalog entries appear most frequently in incidents. ![!Screenshot](../../Data-insights/Features/Incidents/images/catalog-list.png) diff --git a/docs/Coworker/budget-settings.png b/docs/Coworker/budget-settings.png new file mode 100644 index 0000000..5812814 Binary files /dev/null and b/docs/Coworker/budget-settings.png differ diff --git a/docs/Coworker/change-what-see.png b/docs/Coworker/change-what-see.png new file mode 100644 index 0000000..2ed184d Binary files /dev/null and b/docs/Coworker/change-what-see.png differ diff --git a/docs/Coworker/cost-optimize.png b/docs/Coworker/cost-optimize.png new file mode 100644 index 0000000..7d67f67 Binary files /dev/null and b/docs/Coworker/cost-optimize.png differ diff --git a/docs/Coworker/coworker-activity.png b/docs/Coworker/coworker-activity.png new file mode 100644 index 0000000..d3195dd Binary files /dev/null and b/docs/Coworker/coworker-activity.png differ diff --git a/docs/Coworker/coworker-behaviour.png b/docs/Coworker/coworker-behaviour.png new file mode 100644 index 0000000..1bad9a2 Binary files /dev/null and b/docs/Coworker/coworker-behaviour.png differ diff --git a/docs/Coworker/coworker.png b/docs/Coworker/coworker.png new file mode 100644 index 0000000..7a4df7d Binary files /dev/null and b/docs/Coworker/coworker.png differ diff --git a/docs/Coworker/create-event-source.png b/docs/Coworker/create-event-source.png new file mode 100644 index 0000000..fe8c972 Binary files /dev/null and b/docs/Coworker/create-event-source.png differ diff --git a/docs/Coworker/create-event.png b/docs/Coworker/create-event.png new file mode 100644 index 0000000..6fe5957 Binary files /dev/null and b/docs/Coworker/create-event.png differ diff --git a/docs/Coworker/create-task.png b/docs/Coworker/create-task.png new file mode 100644 index 0000000..f207e90 Binary files /dev/null and b/docs/Coworker/create-task.png differ diff --git a/docs/Coworker/dashboard.png b/docs/Coworker/dashboard.png new file mode 100644 index 0000000..cec2e5c Binary files /dev/null and b/docs/Coworker/dashboard.png differ diff --git a/docs/Coworker/getting-started.png b/docs/Coworker/getting-started.png new file mode 100644 index 0000000..c527bbb Binary files /dev/null and b/docs/Coworker/getting-started.png differ diff --git a/docs/Coworker/hide-insights.png b/docs/Coworker/hide-insights.png new file mode 100644 index 0000000..d50d178 Binary files /dev/null and b/docs/Coworker/hide-insights.png differ diff --git a/docs/Coworker/hide-similar.png b/docs/Coworker/hide-similar.png new file mode 100644 index 0000000..9c01c93 Binary files /dev/null and b/docs/Coworker/hide-similar.png differ diff --git a/docs/Coworker/knowledge.gif b/docs/Coworker/knowledge.gif new file mode 100644 index 0000000..51276de Binary files /dev/null and b/docs/Coworker/knowledge.gif differ diff --git a/docs/Coworker/knowledge.png b/docs/Coworker/knowledge.png new file mode 100644 index 0000000..e0cc8ed Binary files /dev/null and b/docs/Coworker/knowledge.png differ diff --git a/docs/Coworker/looking-good.png b/docs/Coworker/looking-good.png new file mode 100644 index 0000000..7568421 Binary files /dev/null and b/docs/Coworker/looking-good.png differ diff --git a/docs/Coworker/new-thread.png b/docs/Coworker/new-thread.png new file mode 100644 index 0000000..972f9de Binary files /dev/null and b/docs/Coworker/new-thread.png differ diff --git a/docs/Coworker/onboarding1.png b/docs/Coworker/onboarding1.png new file mode 100644 index 0000000..17a052b Binary files /dev/null and b/docs/Coworker/onboarding1.png differ diff --git a/docs/Coworker/onboarding2.png b/docs/Coworker/onboarding2.png new file mode 100644 index 0000000..4bfb0e5 Binary files /dev/null and b/docs/Coworker/onboarding2.png differ diff --git a/docs/Coworker/onboarding3.png b/docs/Coworker/onboarding3.png new file mode 100644 index 0000000..948247b Binary files /dev/null and b/docs/Coworker/onboarding3.png differ diff --git a/docs/Coworker/onboarding4.png b/docs/Coworker/onboarding4.png new file mode 100644 index 0000000..c531f66 Binary files /dev/null and b/docs/Coworker/onboarding4.png differ diff --git a/docs/Coworker/op-alerts.png b/docs/Coworker/op-alerts.png new file mode 100644 index 0000000..045e455 Binary files /dev/null and b/docs/Coworker/op-alerts.png differ diff --git a/docs/Coworker/optimize-accept.png b/docs/Coworker/optimize-accept.png new file mode 100644 index 0000000..099942e Binary files /dev/null and b/docs/Coworker/optimize-accept.png differ diff --git a/docs/Coworker/optimize-alert.png b/docs/Coworker/optimize-alert.png new file mode 100644 index 0000000..2380e12 Binary files /dev/null and b/docs/Coworker/optimize-alert.png differ diff --git a/docs/Coworker/optimize.png b/docs/Coworker/optimize.png new file mode 100644 index 0000000..4f2c679 Binary files /dev/null and b/docs/Coworker/optimize.png differ diff --git a/docs/Coworker/overview1.png b/docs/Coworker/overview1.png new file mode 100644 index 0000000..b856f38 Binary files /dev/null and b/docs/Coworker/overview1.png differ diff --git a/docs/Coworker/per-task-usage.png b/docs/Coworker/per-task-usage.png new file mode 100644 index 0000000..dd6d431 Binary files /dev/null and b/docs/Coworker/per-task-usage.png differ diff --git a/docs/Coworker/preferences.png b/docs/Coworker/preferences.png new file mode 100644 index 0000000..f483e91 Binary files /dev/null and b/docs/Coworker/preferences.png differ diff --git a/docs/Coworker/rerun-onboarding.png b/docs/Coworker/rerun-onboarding.png new file mode 100644 index 0000000..33a9872 Binary files /dev/null and b/docs/Coworker/rerun-onboarding.png differ diff --git a/docs/Coworker/restart-chat.png b/docs/Coworker/restart-chat.png new file mode 100644 index 0000000..1f8c300 Binary files /dev/null and b/docs/Coworker/restart-chat.png differ diff --git a/docs/Coworker/scheduled-task.png b/docs/Coworker/scheduled-task.png new file mode 100644 index 0000000..ce4c9c2 Binary files /dev/null and b/docs/Coworker/scheduled-task.png differ diff --git a/docs/Coworker/settings-budget.png b/docs/Coworker/settings-budget.png new file mode 100644 index 0000000..aebb2de Binary files /dev/null and b/docs/Coworker/settings-budget.png differ diff --git a/docs/Coworker/triage.png b/docs/Coworker/triage.png new file mode 100644 index 0000000..b8e8dd0 Binary files /dev/null and b/docs/Coworker/triage.png differ diff --git a/docs/Coworker/usage-ai-token.png b/docs/Coworker/usage-ai-token.png new file mode 100644 index 0000000..d16dee4 Binary files /dev/null and b/docs/Coworker/usage-ai-token.png differ diff --git a/docs/Coworker/usage-report.png b/docs/Coworker/usage-report.png new file mode 100644 index 0000000..b942628 Binary files /dev/null and b/docs/Coworker/usage-report.png differ diff --git a/docs/Coworker/usage1.png b/docs/Coworker/usage1.png new file mode 100644 index 0000000..8288b0a Binary files /dev/null and b/docs/Coworker/usage1.png differ diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/faq.md b/docs/Data-insights/Features/OpsPilot/Coworker/faq.md new file mode 100644 index 0000000..8cd2724 --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/faq.md @@ -0,0 +1,183 @@ +# Coworker FAQ + +## Getting started + +### How do I get started with Coworker? + +When you first open Coworker, a [guided setup conversation](overview.md#getting-started) walks you through setting your preferences and creating your first task. The quickest way to get value is to enable [OpsPilot Alerts](overview.md#opspilot-alerts), which connects Coworker to your existing alert rules so it automatically investigates whenever one fires. + +### Can I have more than one Coworker? + +No. Each user has one Coworker. Your feed and preferences are personal to you, but tasks and investigations are shared across your organisation — everyone on the team can see what Coworker has raised. + +### Can my team share a Coworker? + +Tasks and investigations are already shared across your organisation. Use the **Just for me** dropdown at the top of the dashboard to toggle between your personalised feed and the full team view. + +### Can I restart the setup? + +Yes. Click the settings icon on the Coworker dashboard, select **Reset onboarding**, and click **Open onboarding** to walk through the setup flow again. Re-running does not delete anything you already have. + +![!Screenshot](../../../../Coworker/rerun-onboarding.png) + +--- + +## Tasks + +### How many tasks should I create? + +Start with one or two [scheduled tasks](overview.md#scheduled-tasks) covering your most critical services, and enable [OpsPilot Alerts](overview.md#opspilot-alerts). Add more tasks over time as you identify gaps. Too many tasks running frequently can increase AI Token usage. + +### How often should I run scheduled tasks? + +Daily is the most common cadence and a good starting point. Every 6 hours works well for services that need closer attention. Weekly is often enough for higher-level system reviews. + +If you find yourself wanting very frequent checks on a specific pattern, a [monitoring task](tasks.md#monitoring-tasks) is usually a better fit than a high-frequency scheduled task. If something needs near-real-time response, connecting an alert rule via OpsPilot Alerts will be more effective and much cheaper. + +!!! info "Learn more" + [Scheduled tasks](overview.md#scheduled-tasks) + +### Why isn't my task finding anything? + +It may take a few runs for Coworker to build enough context to surface meaningful insights. If a task consistently finds nothing, consider adjusting the description to be more specific about what you want it to investigate. + +### What is the difference between a scheduled task and a monitoring task? + +A [scheduled task](overview.md#scheduled-tasks) runs on a recurring interval and produces a general report of findings. A [monitoring task](overview.md#monitoring-tasks) is focused on a specific pattern or issue (created from an insight) and tracks whether that pattern is improving, worsening, or stable over time. + +--- + +## Insights + +### What is the difference between Resolve and Ignore? + +**Resolve** marks an insight as handled and it will appear in your resolved insights history. **Ignore** dismisses it from your priority list without marking it as resolved. Use Resolve when you've taken action; use Ignore when the insight isn't relevant to you. + +!!! info "Learn more" + [Insights](overview.md#insights) + +### Why am I seeing the same insight repeatedly? + +If the underlying issue hasn't been fixed, Coworker will continue to surface it. The occurrence history on each insight shows whether it is a recurring pattern. Use **Watch** to create a [monitoring task](overview.md#monitoring-tasks) that tracks whether the issue improves. + +### How do I change what types of insights I see? + +Click **Change what I show you** on the dashboard to adjust your severity and category preferences (Errors, Performance, Notable, Coverage), or use **Update via chat** to describe your preferences in plain language. + +!!! info "Learn more" + [Preferences](overview.md#preferences) + +--- + +## Costs + +### What are OpsPilot AI Tokens? + +OpsPilot AI Tokens are the usage allowance for Coworker's AI-powered work, including chat, alert investigations, scheduled checks, telemetry analysis and recommendations. Your plan includes a fixed monthly allowance, and OpsPilot gives you clear usage visibility, forecasting and controls so there are no surprises. + +!!! info "Learn more" + [Understanding OpsPilot AI Tokens](usage.md#understanding-opspilot-ai-tokens) + +### What uses AI Tokens? + +AI Tokens are used whenever Coworker performs AI-powered work: + +- Answering questions in chat +- Investigating alerts and situations +- Triaging and performing background checkups on open situations +- Analysing telemetry and service behaviour +- Running scheduled checks +- Generating recommendations, suggested fixes and debriefs +- Updating situations and producing findings + +### Does every Coworker action use the same number of AI Tokens? + +No. Usage depends on the amount of telemetry, context and reasoning required. A simple chat question typically uses fewer AI Tokens than a deeper investigation that reviews metrics, logs, prior findings and service context before generating a recommendation. + +### Can I forecast my AI Token usage? + +Yes. The **Projected monthly** metric in the Usage view estimates your end-of-month AI Token consumption based on current usage patterns, so you can see whether you are on track to stay within your plan allowance. + +!!! info "Learn more" + [Activity tab](usage.md#activity-tab) + +### How much does Coworker cost to run? + +Cost depends on several factors: + +- How many tasks you have and how frequently they run +- The [model tier](tasks.md#model-tier) selected (Thorough uses more AI Tokens than Efficient) +- The number of events received from your event sources - the more alerts that fire, the more investigations Coworker runs +- The number of open situations - more open situations means more background checkups running continuously + +You can set a monthly task allowance to control spend, with configurable warning and halt thresholds to prevent overruns. + +!!! info "Learn more" + [Cost and Optimisation](usage.md) + +### How do I reduce AI Token usage? + +- Review **Optimization Suggestions** in the [AI Tokens tab](usage.md#optimization-suggestions); these appear automatically after a task has run a few times and Coworker detects ways it could be improved +- **Apply** an optimisation suggestion to apply the recommended change immediately +- Click **Analyse & Optimise** to trigger an on-demand optimisation review at any time +- Switch high-volume or routine tasks to the [Efficient model tier](tasks.md#model-tier) +- Reduce the frequency of scheduled tasks that run often but find little +- Review the **AI Token Breakdown** table to identify the most expensive tasks and consolidate or adjust them +- If noisy alerts are driving up costs, consider disabling Coworker from investigating them. Click on the **OpsPilot Alerts** event source in the sidebar and sort by **Most events** to see which alert rules are firing most frequently - those are the best candidates to review or exclude + +### What happens when I reach my task allowance? + +Coworker will stop running tasks once spend reaches the **Halt threshold**, which by default is set to 100% of your task allowance. You can lower this threshold to stop tasks earlier and protect your allowance. A separate **Warning threshold** notifies you before the halt is reached. + +!!! info "Learn more" + [Allowance](usage.md#ai-token-allowance) + +### Can I get warned before hitting my allowance limit? + +Yes. The **Warning threshold** in Settings > Budget & cost triggers a notification when your spend reaches a set percentage of your task allowance (e.g. 80%). This gives you time to adjust tasks or increase your allowance before tasks are halted. + +!!! info "Learn more" + [Allowance](usage.md#ai-token-allowance) + +### How do I accept or dismiss an optimisation suggestion? + +Open the **AI Tokens** tab in Usage and scroll to **Optimization Suggestions**. Expand any suggestion to see the reasoning under **Why this suggestion** and the proposed change under **Instruction changes**. Click **Apply** to apply it immediately, or **Dismiss** to ignore it. + +!!! info "Learn more" + [Optimization Suggestions](usage.md#optimization-suggestions) + +### What is the difference between Thorough and Efficient model tiers? + +**Thorough** handles any task and is more capable. Use it for critical alerts and complex investigations where depth matters. **Efficient** is suited to simpler, focused tasks and costs less. Use it for routine or high-volume tasks to keep spend down. You can set the model tier per task or per event source. + +!!! info "Learn more" + [Model tier](tasks.md#model-tier) + +### Why use AI Tokens instead of unlimited AI? + +AI-powered investigations consume compute and reasoning resources. OpsPilot AI Tokens give your team a predictable, fixed allowance for Coworker's work, with full visibility into what was used and what it delivered. This keeps AI usage transparent and controllable for both teams and budgets. + +--- + +## Memory + +### How long does it take for Coworker to become useful? + +Coworker starts providing value immediately, but becomes noticeably smarter after a few days of running tasks. As it builds [memory](overview.md#memory) about your services and patterns, its insights become more relevant and its task analysis more accurate. + +### Can I clear Coworker's memory? + +Please contact support if you need to reset Coworker's [memory](overview.md#memory). + +--- + +## Privacy and data + +### What data does Coworker have access to? + +Coworker has access to the observability data in your OpsPilot account: metrics, logs, traces, and alert rules. It does not have access to data outside your organisation's account. + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/getting-started.md b/docs/Data-insights/Features/OpsPilot/Coworker/getting-started.md new file mode 100644 index 0000000..b9baa0e --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/getting-started.md @@ -0,0 +1,100 @@ +# Getting started with Coworker + +## Onboarding + +When you first access Coworker, a short guided setup walks you through personalising your experience. You can skip it at any time and still get a working Coworker, though you'll see a broader, less tailored view until you configure your preferences. + +### Step 1: Introduction + +Step 1 introduces what Coworker does and how it works, with four cards showing the flow: something fires, Coworker investigates, you get a clear story, and it keeps checking back. Click **Quick start** to begin, or **Skip** to go straight to the dashboard. + +![!Screenshot](../../../../Coworker/onboarding1.png) + +--- + +### Step 2: Your role + +![!Screenshot](../../../../Coworker/onboarding2.png) + +Coworker asks which role best describes you. This sets the defaults for which kinds of situations are surfaced to you first: + +| Role | Description | +|---|---| +| **Developer** | Building features, owning services | +| **SRE / DevOps** | On-call, infra, reliability | +| **Tech lead** | Leading a team, mostly hands-on | +| **Manager / leadership** | Team or org-level visibility | +| **Something else…** | Tell me in your own words | + +Pick the closest fit. Select **Skip - I'll come back later** to proceed without setting a role. + +--- + +### Step 3: What do you want me to help with? + +![!Screenshot](../../../../Coworker/onboarding3.png) + +Select as many as apply: + +| Option | Description | +|---|---| +| **Surface critical issues** | Stay quiet most of the time; get loud when something's actually breaking | +| **Filter alert noise** | I get a lot of alerts already - only show me the ones that matter | +| **Catch cascading issues** | Spot when several small problems are really one big one across services | +| **Run regular checks** | Watch specific services or metrics on a cadence and flag what looks off | +| **Give me regular reports for the team** | Uptime, SLO burn, incident counts, deploy frequency - the kinds of numbers you have to share up | +| **Verify deploys** | After each deploy, check things look healthy and tell me if anything regressed | +| **Brief me on my shift** | Tell me what happened while I was away, what's still open, what's resolved | +| **Take action on routine stuff** | Run scripts, kick off jobs, hit endpoints - automate the small stuff I'd otherwise context-switch for | + +Click **Continue** when done, or **Skip** to proceed without selecting any. + +--- + +### Step 4: Which of these matter most to you? + +![!Screenshot](../../../../Coworker/onboarding4.png) + +The final step. Select the domains you want Coworker to prioritise in your feed: + +| Area | What it covers | +|---|---| +| **Errors and exceptions** | Crashes, failed requests, exception spikes | +| **Application performance** | Slow endpoints, latency spikes, throughput dips | +| **Infrastructure and runtime** | Hosts, containers, pods, CPU / memory / disk | +| **Databases and data stores** | Queries, connections, replication, cache health | +| **Data pipelines and quality** | DAG failures, freshness, schema drift, model output | +| **Deploys and releases** | Rollouts, regressions, config changes | +| **Team and delivery health** | Cross-service stability, release confidence, incident rate | +| **Reliability and SLOs** | Burn rate, availability, alert noise | +| **Cost and capacity** | Spend anomalies, quota limits, overprovisioning | +| **Security and auth** | Auth failures, suspicious traffic, IAM, secrets | + +Select as many as apply. These can be updated at any time from **Settings > Your preferences**. + +--- + +## Configuring your view + +Whether set during onboarding or later from Settings, three controls decide what appears in your Coworker feed: + +| Setting | Description | +|---|---| +| **Focus services** | The specific services you own or care about, by name or glob pattern (e.g. `payments-*`). Situations touching these are prioritised in your feed. | +| **Focus areas** | The domains you want prioritised: Errors and exceptions, Application performance, Infrastructure and runtime, Databases and data stores, Data pipelines and quality, Deploys and releases, Team and delivery health, Reliability and SLOs, Cost and capacity, Security and auth. | +| **Custom keywords** | Any terms beyond the focus areas above - a library, technology, or feature name specific to your stack. A match nudges related situations into your feed. | + +None of these change what Coworker investigates or raises across your organisation. They only change what reaches your personal feed. + +--- + +## Settings + +Open **Settings** from the Coworker dashboard to access your preferences, check-in cadence, behaviour, and budget controls. You don't need to configure all of this up front — sensible defaults are in place, and you can ask Coworker directly in any chat to update your preferences conversationally. + +See [Settings](settings.md) for full details. + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/knowledge.md b/docs/Data-insights/Features/OpsPilot/Coworker/knowledge.md new file mode 100644 index 0000000..3e85036 --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/knowledge.md @@ -0,0 +1,51 @@ +# Knowledge + +Coworker builds a growing understanding of your systems, your team, and your preferences over time. Everything it does - investigating alerts, running tasks, talking to you - adds to this knowledge and carries forward into future investigations. + +Click the **Knowledge** button on the Coworker dashboard to explore what Coworker has learned. + +The header shows a live count of total memories, observations, nodes, and links across your organisation. + +## Memory types + +| Memory type | What it holds | +|---|---| +| **System-wide** | How your services fit together, what's normal, and what tends to break. Shared across your whole organisation, so what Coworker learns helping one person makes it smarter for everyone | +| **Task-specific** | What recurring checks have turned up before and the patterns that matter. Can reduce token costs by up to 50% on long-running tasks | +| **Team** | Who owns what, where the runbook lives, what each channel is for | +| **User** | Your personal preferences and the way you like to work, learned from your conversations | + +--- + +## Graph view + +A visual map of everything Coworker knows. Nodes represent entities (services, databases, concepts) and links between them show relationships. Node size reflects how frequently an entity is referenced. + +![!Screenshot](../../../../Coworker/knowledge.gif) + +The **Entities** panel on the right lists every entity ranked by reference count. Use the search box to find a specific one. + +--- + +## List view + +A searchable, filterable list of individual memories. + +| Control | Description | +|---|---| +| **Search memories** | Find specific facts by keyword | +| **Filter by entity** | Scope the list to a particular service or concept | +| **Sort** | Order by newest or oldest | + +Each memory shows the fact Coworker recorded, when it was added, and any entity tags attached to it. + +--- + +## Correcting Coworker + +When Coworker raises something that isn't a problem, dismiss it with a quick reason, such as "this is expected" or "too noisy". Coworker turns your correction into a lasting fact: next time it sees the same pattern on the same service, it remembers and won't raise it again. A few early corrections go a long way towards tuning Coworker to your reality. + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/overview.md b/docs/Data-insights/Features/OpsPilot/Coworker/overview.md new file mode 100644 index 0000000..e70ed3f --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/overview.md @@ -0,0 +1,175 @@ +# Coworker + +Coworker is the connective layer that binds your observability data, alerting, service knowledge, and incident response into one place. Rather than switching between dashboards, alert feeds, and runbooks, you get a single AI operations partner that watches your systems, investigates what it finds, and hands you a clear, prioritised picture of what needs attention - so your team spends less time fighting tools and more time fixing problems. + +Each user gets their own personalised Coworker that learns what's relevant to them. It talks to you in the first person, remembers context, and keeps working between your visits. + +![!Screenshot](../../../../Coworker/co1.png) + +## How to think about it + +Think of Coworker as a single teammate rather than a monitoring tool. Behind that one voice it is doing several jobs at once: watching for signals, investigating them, writing down what it finds, and deciding what to tell you. You don't need to think about those internal jobs. You just get one Coworker who keeps you informed. + +Coworker also shows you what it cannot see. Coverage gaps in your telemetry, unconnected alert rules, uncatalogued services - these surface in your feed so you know exactly what to fix to make Coworker more effective. The onboarding experience is not just setup; it is a diagnostic that tells you where your observability has blind spots. + +## What Coworker does + +| Capability | Description | +|---|---| +| **Insights** | The core of Coworker - atomic findings written every time Coworker investigates something, forming the foundation for everything it surfaces | +| **Situations** | Insights grouped into coherent stories with severity, evidence, and recommended actions - the thing you triage | +| **Continuous monitoring** | Watches your systems around the clock and re-investigates open situations on a regular cadence | +| **Alert response** | Automatically investigates firing alerts and posts one clean situation instead of a stream of raw alert noise | +| **Tasks** | Scheduled, monitoring, and webhook-driven jobs that run recurring analysis and report back proactively | +| **Memory** | Builds a growing understanding of your systems, your team, and your preferences over time | +| **Cost management** | Allowance tracking and optimisation suggestions to keep AI Token spend under control | + +--- + +## Insights and situations + +**Insights are the core of Coworker.** Everything Coworker does - investigating alerts, running scheduled checks, responding to webhooks - produces insights. An insight is one atomic finding: one observation, one anomaly, one error pattern. Each has a severity, a category, an affected service, and a short description with supporting evidence. Insights are how Coworker records what it has seen and reasoned about. + +**Situations** are the editorial layer built on top of insights. Coworker groups related insights into one coherent story: a title, a plain-language summary, the affected service, severity, and impact. Situations are what you triage. Insights are how Coworker writes them up; situations are what it hands you. + +A situation is not a static record. As new insights arrive, Coworker decides whether to extend an existing situation, merge it with another, escalate or de-escalate its severity, or close it out. That continuous editing is the difference between a useful picture of your operations and a noisy alert feed. + +## Severity and status + +Severity and status answer two different questions: + +| | Question | Values | +|---|---|---| +| **Severity** | How bad is this? | Critical, Warning, Info | +| **Status** | Should you act on it right now? | Active, Watching, Resolved | + +These don't always align the way you'd expect. A warning can be active if Coworker thinks you should look now. A critical is active by default, but once it's handled it moves to resolved. Splitting the two lets the page show "important but not urgent" items without either burying them or sounding false alarms. + +--- + +## What runs in the background + +Coworker is never just a snapshot. Three things run continuously: + +**Investigating new signals.** When an alert fires or a task runs, Coworker pulls the relevant metrics, logs, and traces, writes insights, and decides what to do: raise a new situation, attach the finding to an existing one, or note that it looked and found nothing worth raising. Alerts that arrive close together are investigated as a group, so one underlying problem doesn't generate a wall of separate cards. + +**Tidying up.** Every few minutes Coworker sweeps your active situations and consolidates them, merging two that turn out to be the same problem, escalating severity when a new signal warrants it, and attaching stray findings to the situation they belong to. + +**Re-checking what's open.** Every active situation is re-investigated on a cadence that depends on its severity. Criticals are checked roughly every 10–15 minutes at first; warnings and quieter items less frequently. When a situation recovers on its own, Coworker resolves it and tells you why. As a situation stays stable, checks become less frequent; if something shifts, the cadence tightens back up. Once resolved, a situation gets a couple of follow-up checks over the next few hours to confirm the fix held. + +![!Screenshot](../../../../Coworker/overview1.png) + +--- + +## The home page + +The home page is a feed of messages from your Coworker, more like a conversation with a colleague who has been working while you were away than a static dashboard. Everything arrives as a message in that feed: new situations, updates to existing ones, checks that came back clean, and pointers to coverage gaps. + +A **WATCHING** badge in the header confirms Coworker is actively monitoring your environment. + +The interface uses a tab bar across the top. **Home** is always the first tab. Each situation thread or conversation you open appears as an additional tab alongside it, so you can switch between multiple threads without losing context. Click **+** to open a new thread. Tabs with an orange dot indicate an active or critical situation. + +### Your view or the team's + +Use the **Just for me** dropdown at the top of the page to filter the feed to your personalised slice - situations relevant to your services and setup. Switch to a broader view when you're on call, covering someone else's area, or want the full picture across your organisation. + +### How the feed adapts + +Coworker changes how it leads depending on what it has to tell you: + +| State | What you see | +|---|---| +| **Quiet** | An "all clear" note on what Coworker has been doing and watching. Silence means "checked and fine", not "nothing running" | +| **One critical** | A single focus card with the full story: summary, affected service, impact, latest checkup, and evidence | +| **A few criticals** | Prominent rows in urgency order, each with enough detail to triage at a glance | +| **Many criticals** | A status overview showing the count and affected services. When everything is urgent, a wall of full-size cards doesn't help | + +Below the critical items sits the quieter list: warnings and lower-severity items Coworker is watching rather than actively raising. This is where tomorrow's situation often first appears. Recently resolved situations collapse into a short list near the bottom. + +### Other message types + +Alongside situations, the feed contains: + +- **Coverage gaps**: one of Coworker's most useful signals. When it would have investigated something but couldn't - because a service has no telemetry, an alert rule isn't connected, or a catalog entry is missing - it tells you explicitly. Each gap names what's missing and includes a **Help me set this up** button that opens a guided thread. Coverage gaps turn Coworker into a diagnostic for your observability, not just a consumer of it. +- **The digest**: a snapshot Coworker keeps current, summarising the checks it ran and things it handled quietly in the background. +- **Debriefs**: short notes for when Coworker investigated something and concluded there was nothing worth raising, so the work is visible rather than silent. + +### Sidebar + +The right-hand sidebar gives a quick status view alongside the feed: + +| Section | Description | +|---|---| +| **Tasks** | The number of open tasks currently assigned to you, with a link to the full Tasks board | +| **Event sources** | Your connected event sources and their recent activity - showing whether each has been quiet or firing, and when it last triggered | +| **Scheduled** | Your scheduled tasks, showing their run cadence and when they last ran. A green highlight indicates a task that just finished | + +--- + +## Situations and threads + +Every situation opens into a thread: a dedicated conversation about that one problem, with all context already loaded. At the top sits the situation itself; below it runs the history of Coworker's checkups and state changes, interleaved with any messages between you and it. + +From a situation thread you can: + +| Action | Description | +|---|---| +| **Ask follow-ups** | Type any question. Coworker answers with the situation's full context already in hand | +| **Verify now** | Triggers a fresh investigation immediately, rather than waiting for the next scheduled checkup. The result lands in the thread when done | +| **Suggest a fix** | Prompts Coworker to propose concrete remediation steps based on what it has found | +| **Resolve / Dismiss** | Closes the situation. Coworker asks for a quick reason, which also teaches it what not to raise next time | +| **Share** | Copies a shareable link to the thread | +| **Copy** | Copies the full situation as a markdown brief, ready to paste into another tool or hand off to a teammate | + +### Insight shortcuts + +Click **Chat** on any insight for five quick actions: + +| Action | Description | +|---|---| +| **Is this still an issue?** | Checks current state to see if the problem is ongoing or resolved | +| **Investigate root cause** | Kicks off a root cause analysis | +| **Create a ticket** | Creates a ticket for the issue | +| **Suggest a fix** | Recommends remediation steps or best practices | +| **Discuss this insight** | Opens a free-form conversation about the insight | + +These shortcuts are available everywhere insights appear: the priority queue, insight lists, and insight detail views. You can also click **Help me triage** to send your current priority insights and recent activity to Coworker for a prioritisation recommendation. + +--- + +## Chatting outside a situation + +You can start a fresh thread at any time to ask about a service, a recent change, a metric, or anything else Coworker can investigate. Click **+** in the tab bar to open a new thread. + +![!Screenshot](../../../../Coworker/new-thread.png) + +Three shortcuts are offered to get started quickly: + +| Shortcut | Description | +|---|---| +| **Just chat** | Ask anything - running a query, debugging a service, exploring an idea | +| **Set up a task** | Schedule a check, watch a service, or react to a webhook | +| **Update your preferences** | Adjust the categories, services, or severities Coworker highlights for you | + +These free-form chats have the full set of tools: attach images, use voice input, search the web, and pull context from your connected integrations. + +Each task run produces a report with findings, the investigation process, and a final summary. An input field appears below each report (*Ask OpsPilot about this report...*) with the full report already in context, so you can ask follow-up questions without copying anything. + +--- + +## Memory + +Coworker gets smarter over time. Everything it does - investigating alerts, running tasks, talking to you - builds memory that carries forward into every future investigation. + +Click the **Knowledge** button on the dashboard to explore what Coworker has learned. See [Knowledge](knowledge.md) for full details. + +--- + +## Settings + +Click the settings icon on the Coworker dashboard to open the Settings modal. See [Settings](settings.md) for full details on your preferences, check-in cadence, behaviour, and budget controls. + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/settings.md b/docs/Data-insights/Features/OpsPilot/Coworker/settings.md new file mode 100644 index 0000000..7dff56a --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/settings.md @@ -0,0 +1,118 @@ +# Settings + +Click the settings icon on the Coworker dashboard to open the Settings modal. Settings are split into two groups: + +**You** - personal settings that apply only to your Coworker: + +| Setting | Description | +|---|---| +| [**Your preferences**](#your-preferences) | Controls what Coworker weights when deciding what to surface in your feed | +| [**Reset onboarding**](#reset-onboarding) | Walks through the getting-started flow again without losing any existing setup | + +**Your organisation** - settings that apply across your whole team: + +| Setting | Description | +|---|---| +| [**Coworker activity**](#coworker-activity) | Configure what Coworker monitors and how it responds to events | +| [**Coworker behaviour**](#coworker-behaviour) | Adjust how Coworker investigates and communicates | +| [**Budget & cost**](#budget-cost) | Manage your AI Token allowance and cost controls (same as the [AI Tokens tab in Usage](usage.md#ai-token-allowance)) | + +--- + +## Your preferences + +The **Your preferences** panel shapes what reaches your personal feed without changing what Coworker investigates. Coworker still investigates everything - this just controls what surfaces for you versus what stays in the team view. You can also ask Coworker to adjust these from any chat. + +![!Screenshot](../../../../Coworker/preferences.png) + +| Setting | Description | +|---|---| +| **Focus services** | Service names you own or primarily work on. Glob patterns like `opspilot-*` work too. Situations affecting these services are prioritised in your feed | +| **Focus areas** | The kinds of things Coworker should prioritise when filtering your feed: Errors and exceptions, Application performance, Infrastructure and runtime, Databases and data stores, Data pipelines and quality, Deploys and releases, Team and delivery health, Reliability and SLOs, Cost and capacity, Security and auth | +| **Custom keywords** | Anything beyond the domains above. A match nudges related situations into your feed | +| **Advanced - focus area label** | A free-form team or area label that boosts situations tagged with it (e.g. `payments`, `platform infra`). Usually filled in automatically when you mention it during onboarding; set directly here if needed | + +--- + +## Reset onboarding + +Click **Reset onboarding** and then **Open onboarding** to walk through the setup flow again. Useful for adding more scheduled tasks, picking up extra alerts, or refining your preferences. Re-running does not delete anything you already have - your tasks, situations, alert subscriptions, and preferences stay in place. + +![!Screenshot](../../../../Coworker/rerun-onboarding.png) + +--- + +## Coworker activity + +Configure what Coworker monitors and how it responds to events across your organisation. + +### Check-ins + +Controls how often Coworker re-checks each open situation. Four modes are available: + +| Mode | Description | +|---|---| +| **High Attention** | Re-checks more often. Best for busy or sensitive environments | +| **Balanced** | Eager early, quick to back off. Recommended for most teams (default) | +| **Light Touch** | Slower checks with lower token usage | +| **Quiet** | Lowest check frequency. Critical situations are still checked | + +Each mode shows the First / Mid-walk / Steady check intervals for Critical, Warning, and Info situations. + +![!Screenshot](../../../../Coworker/coworker-activity.png) + +### Home digest refresh + +Controls how often the standup line on your home page is rewritten. Options: every 6h, every 12h, or every 24h. + +--- + +## Coworker behaviour + +Adjust how Coworker investigates and communicates across your organisation. + +![!Screenshot](../../../../Coworker/coworker-behaviour.png) + +### Report detail + +Controls how much Coworker writes when it reports a finding. Applies to every task in your organisation. + +| Mode | Description | +|---|---| +| **Concise** | Just the headlines and what matters. Less reading, faster scan | +| **Standard** | Balanced detail - context, key signals, and what to do next | +| **Detailed** | Full reasoning, every relevant signal, every step Coworker took | + +### Optimisation suggestions + +When Coworker spots a way to make a task cheaper or more reliable, it can either propose the change for your review or apply it automatically. + +**Auto-accept optimisation suggestions** - apply suggested changes immediately. Off by default; most teams prefer to review each one first. + +--- + +## Budget & cost + +Set the monthly token budget for tasks and webhook investigations. Coworker pauses new task runs when the halt threshold is hit. + +![!Screenshot](../../../../Coworker/settings-budget.png) + +| Control | Description | +|---|---| +| **Plan allowance** | Your organisation's total monthly token allowance (read-only) | +| **Monthly task budget** | The share of your plan allowance allocated to tasks. Set as a percentage: 5%, 10%, 20%, 50%, 80%, or 100% | +| **Warning threshold** | Sends a notification when spend reaches this percentage of your task budget | +| **Halt threshold** | Stops new task runs when spend reaches this percentage of your task budget. Defaults to 100% | + +See [AI Tokens](usage.md#ai-token-allowance) for full usage details and optimisation suggestions. + +--- + +## Hiding insight types + +To suppress a type of insight from your view, click **Hide similar** on any insight card. This opens a modal where you can match by category, severity, label, or title pattern. Coworker will stop surfacing insights that match your conditions. + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/tasks.md b/docs/Data-insights/Features/OpsPilot/Coworker/tasks.md new file mode 100644 index 0000000..32380f3 --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/tasks.md @@ -0,0 +1,127 @@ +# Tasks + +Tasks are the standing jobs you give Coworker to run in the background. Rather than filling in forms or learning configuration options, you describe what you want in plain language and Coworker shapes it into a task through conversation. + +Coworker is not limited to your observability data. As an LLM, it can also search the web as part of an investigation, bringing in external context (documentation, known issues, best practices) alongside your metrics, logs, and traces. + +!!! info + Tasks are currently configured at the organisation level. + +--- + +## Task types + +### Scheduled tasks + +Run on a recurring schedule you choose: hourly, daily, weekly, monthly, or a custom interval. Each run produces a report summarising what Coworker found. These are the core of Coworker's continuous analysis. Scheduled tasks run until you turn them off, and they're quiet unless there's something worth telling you. + +Run any scheduled task on-demand with the **Run now** button, and view the full execution history to see what it found on each run. + +![!Screenshot](../../../../Coworker/scheduled-task.png) + +### Monitoring tasks + +Monitoring tasks are temporary. They run repeatedly for a limited window to keep an eye on one specific thing and report back as they go. For example, "keep checking the checkout error rate through this rollout" or "watch database connections for the next few hours while we drain the node." + +You get progressive updates as the task runs. Once its window is up, the task winds down on its own. Use monitoring tasks when you want focused attention on something for a while rather than forever. + +### Event sources + +Event sources react to webhooks from external systems. Instead of running on a schedule, they wait for an event (a deploy notification, an incident raised in another tool, an alert from an external service) and immediately kick off an investigation each time. + +--- + +## Creating tasks + +To create a task, open a new thread and select **Set up a task**. Coworker asks *"What are you trying to achieve?"* and guides you through setup conversationally, with no forms to fill in. Suggested shortcuts help you get started: + +- *"Create a scheduled task to check error rates every hour"* +- *"Watch a service and tell me when something looks off"* +- *"Listen to a webhook and run a check on every event"* + +To edit an existing task, click **Configure** from the task panel in the sidebar. + +--- + +## What every task run does + +Every task run does two things at once: + +1. **Produces the report** you set the task up for (a weekly resource review, a daily error summary, a post-deploy health check) which lands in the task's run history. +2. **Surfaces anything else worth flagging.** While it's working, Coworker notices other issues and turns them into insights that flow into your feed as situations, just like findings from an alert. + +This means you can aim a task either at a report you want kept current, or purely at finding problems, and have Coworker proactively raise what it spots without an alert needing to fire at all. + +![!Screenshot](../../../../Coworker/usage-report.png) + +--- + +## OpsPilot Alerts + +One event source is always present for every user: **OpsPilot Alerts**. Connecting it is the single most valuable thing you can do, letting Coworker investigate your alerts the moment they fire, checking metrics and logs, working out what changed, and posting one clean situation instead of a stream of raw alert noise. + +You're offered this during onboarding, but you can connect it at any time by opening the tasks panel, going to **Event Sources**, clicking **OpsPilot Alerts**, and then **Configure**. + +From then on, every watched alert gets investigated automatically and shows up in your feed as a situation. + +Use the toggle at the top to enable or disable OpsPilot Alerts entirely. Click **Done** to save and close the panel. + +If Coworker has optimisation suggestions for your alert setup, a banner appears at the top of the configure panel showing the estimated monthly saving. Click **View** to see the suggestion. + +Under **Alert Rules**, you can: + +- Search alerts by name +- Filter by **All**, **Enabled**, or **Firing** +- **Enable All** or **Disable All** in bulk +- Toggle individual alerts on or off +- Expand an alert to add specific instructions (e.g. *"Check the Redis connection pool first"*) + +You can also add **General Alert Instructions** that apply to every alert investigation - useful for pointing Coworker at common starting points or known patterns. These sit below the alert rules list. + +--- + +## Model tier + +Every task and event source has a **Model Tier** setting that controls how Coworker analyses the data: + +| Tier | Description | +|---|---| +| **Thorough** | Best for critical alerts and complex events that need deep analysis | +| **Efficient** | Best for high-volume, routine events like health checks and simple notifications | + +Use **Thorough** for critical alerts and complex investigations where depth matters. Use **Efficient** for routine or high-volume tasks to keep token costs down. + +--- + +## Creating an event source + +To set up a new event source, open a new thread, select **Set up a task**, and describe the webhook you want to connect. + +| Field | Description | +|---|---| +| **Type** | The webhook type, e.g. Generic Webhook | +| **Name** | A name for the event source (e.g. Production Alerts) | +| **Description** | What events this webhook will receive | +| **Custom Instructions** (optional) | Guides how events are investigated, e.g. *"Focus on database-related issues and suggest query optimisations"* | +| **Model Tier** | Controls how the event is investigated. **Thorough** for critical or complex events; **Efficient** for high-volume, routine events | +| **Monthly Budget** (optional) | A token budget for this event source. If not set, the org budget is the only cap. | + +--- + +## Managing tasks + +The right-hand sidebar shows your active tasks, split into **Event Sources** and **Scheduled** sections. Each task shows its name, schedule, and when it last ran. Click **Manage all tasks** to open the full task management panel. + +The **All tasks** panel lets you view and manage everything Coworker runs: + +- Click **Preferences** to update your monitoring preferences, or **+ Create Task** to create a new task +- Filter using the tabs: **All**, **Scheduled**, **Monitoring**, **Event Sources** - each tab shows the count of tasks in that category +- Search tasks by name using the search bar +- The **SYSTEM** section shows built-in tasks such as **OpsPilot Alerts**. A badge shows the current state (e.g. *No alerts yet* if none are connected, or a watch count once alerts are enabled) +- The **ACTIVE** section lists your enabled tasks with their schedule, next run time, and last run date. Each task has a **Run** button to trigger it immediately, a toggle to disable it, and a delete button +- The **DISABLED** section lists tasks that have been turned off. They retain their configuration and can be re-enabled at any time using the toggle + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/OpsPilot/Coworker/usage.md b/docs/Data-insights/Features/OpsPilot/Coworker/usage.md new file mode 100644 index 0000000..ceda1d8 --- /dev/null +++ b/docs/Data-insights/Features/OpsPilot/Coworker/usage.md @@ -0,0 +1,137 @@ +# Usage + +Click **Usage** from the top right of the Coworker dashboard to open the Usage panel. It has two tabs: **Activity** and **AI Tokens**. + +--- + +## Understanding OpsPilot AI Tokens + +Your OpsPilot plan includes a monthly allowance of **OpsPilot AI Tokens**. These are the usage allowance for Coworker's AI-powered work. Every time Coworker investigates an alert, runs a scheduled check, analyses telemetry, generates a recommendation or answers a question in chat, it uses AI Tokens from your allowance. + +Usage varies depending on the amount of context, telemetry and reasoning required. A simple chat question uses a small number of AI Tokens. A deeper investigation that reviews telemetry, prior findings, service context and generates recommended actions uses more. + +### What uses AI Tokens + +| Source | Description | +|---|---| +| **Chat** | AI Tokens used by direct questions and conversations with Coworker | +| **Coworker investigations** | AI Tokens used when Coworker investigates alerts, situations, telemetry patterns or service behaviour | +| **Scheduled checks** | AI Tokens used by recurring Coworker tasks, such as daily error checks, performance reviews or resource usage analysis | +| **Recommendations** | AI Tokens used to generate suggested fixes, explanations and next steps | + +--- + +## Activity tab + +The **Activity** tab shows what Coworker has done over a selected time range. Use the **Plan period** selector in the top right to switch between plan years, and the **Last 30 days / Last 90 days / Full period** toggle to adjust the window within that period. + +![!Screenshot](../../../../Coworker/usage1.png) + +Four summary metrics are shown at the top: + +| Metric | Description | +|---|---| +| **Runs** | Number of task executions completed in the selected period | +| **AI Tokens used** | Total AI Tokens consumed in the selected period | +| **New findings** | Number of new findings generated across all runs | +| **Situations raised** | Number of situations Coworker raised in the selected period | + +A **Runs over time** chart shows task execution frequency across the period. + +The **By task** table breaks down activity per task: + +| Column | Description | +|---|---| +| **Task** | The task name | +| **Kind** | The task type (Scheduled, Monitoring, or Event source) | +| **Runs** | Number of executions in the selected period | +| **New findings** | Number of new findings generated by that task | + +OpsPilot always shows the operational work Coworker delivered alongside AI Token usage, so you can see what your allowance funded. AI Token usage is never shown in isolation. + +--- + +## AI Tokens tab + +The **AI Tokens** tab gives you full visibility into AI Token spend and the controls to manage it. + +![!Screenshot](../../../../Coworker/usage-ai-token.png) + +!!! tip + One of the most effective ways to reduce AI Token usage over time is simply to let tasks run. As [task-specific memory](overview.md#memory) builds up, Coworker re-uses context it already knows rather than fetching it fresh on every run, reducing usage by up to 50% in some cases. + +### AI Token Allowance + +The **AI Token Allowance** bar at the top shows your current spend against your plan allowance (e.g. 94 / 20,000 AI Tokens used). The **Allocation** figure shows how much of your plan allowance is assigned to tasks (e.g. 16,000 — 80%). A **Projected within allowance** status confirms whether your current usage trajectory is on track. + +Below the bar, a legend breaks down usage by source: + +- **Chat**: AI Tokens used by direct conversations +- **Coworker**: AI Tokens used by task runs +- **Projected period usage**: estimated total by end of the current period + +Click **Configure** to go to **Settings > Allowance & cost**. + +Your **Plan allowance** is shown as a fixed value set by your plan (e.g. 5,000 tokens/month). The remaining settings are configurable: + +| Setting | Description | +|---|---| +| **Monthly task allowance** | The percentage of your plan allowance allocated to tasks and webhook investigations. Select a preset (5%, 10%, 20%, 50%, 80%, 100%) or use the slider | +| **Warning threshold** | The percentage of your task allowance at which Coworker warns you about spend (e.g. "Warn at 50% of allowance") | +| **Halt threshold** | The percentage at which Coworker stops running tasks (e.g. "Stop tasks at 50% of allowance") | + +Click **Save** to apply your changes. Coworker pauses new task runs when the halt threshold is reached. Click **Save** to apply your changes. + +### AI Token usage over time + +A bar chart showing AI Token consumption per day across the selected period. Use the **Last 30 days / Last 90 days / Full period** toggle to adjust the window. The chart legend identifies spend by task and includes a **Background work** category for AI Token usage from Coworker's continuous monitoring activity (situation re-checks, tidying, and debriefs) that runs outside of named tasks. + +### AI Token Breakdown + +The **AI Token Breakdown** table has two sub-tabs: + +**Tasks** — shows your named tasks. Each row shows: + +| Column | Description | +|---|---| +| **Task** | The task name | +| **Schedule** | How often the task runs | +| **Runs** | Number of executions in the selected period | +| **New findings** | Findings generated by this task in the period | +| **Period total** | Total AI Tokens consumed by this task in the period | + +**Background** — shows AI Token usage from Coworker's continuous monitoring work that runs outside of named tasks. Each row shows the activity type, period total, and projected monthly cost: + +| Activity | Description | +|---|---| +| **Following up on situations** | Re-checking open situations on a regular cadence | +| **Writing your daily summary** | Generating the digest of what Coworker handled | +| **Triaging new alerts** | Initial investigation of incoming alerts | +| **Tidying the inbox** | Consolidating, merging, and closing situations | + +### Optimization Suggestions + +Optimization suggestions appear at the bottom of the AI Tokens tab. Each suggestion shows a title, a plain-language explanation of the proposed change, and an estimated monthly AI Token saving (e.g. *Est. save 115 tokens/mo*). Click the chevron to expand the full detail, which includes: + +- **Why this suggestion** - Coworker's reasoning, including the pattern it observed and the estimated reduction per run +- **Instruction changes** - the exact proposed instructions that would be applied, so you can review the change before accepting + +From an expanded suggestion you can: + +- **Apply**: apply the change immediately +- **Dismiss**: ignore it. Coworker won't keep pushing the same suggestion. + +Suggestions never come at the expense of monitoring quality. Coworker won't suggest anything that would reduce its ability to catch real problems. Where a task is already running efficiently, it will say so. + +Toggle **Auto-apply optimization suggestions** to have Coworker automatically apply future suggestions as they are generated. This is off by default. + +### On-demand analysis + +Click **Analyse & Optimise** to trigger an on-demand optimisation review at any time. If no optimisations are needed, you'll see a **Looking good!** confirmation. + +![!Screenshot](../../../../Coworker/per-task-usage.png) + +--- + +!!! question "Need more help?" + Contact support in the chat bubble and let us know how we can assist. diff --git a/docs/Data-insights/Features/overview.md b/docs/Data-insights/Features/overview.md index 9bba3ca..8590b09 100644 --- a/docs/Data-insights/Features/overview.md +++ b/docs/Data-insights/Features/overview.md @@ -12,6 +12,22 @@ Once your environment is sending data, the Overview page shows a full observabil ![!Screenshot](../../Data-insights/Features/images/Active-account-overview.png) +## Customising your dashboard + +Click the **My dashboard** icon in the top right of the Overview to choose which sections are visible. Tick or untick any section to show or hide it: + +- Coworker +- Services +- Services by latency +- Servers +- Servers by latency +- Applications +- Applications by latency +- Alerts +- Anomaly Detection + +Click **Reset to org defaults** to restore the default layout. + ### Services The **Services** section displays key performance metrics aggregated across all your monitored services for the last hour. Use the **Overview show as** dropdown to change the aggregate function applied to the stat values: @@ -47,6 +63,24 @@ Below the summary metrics, **Services by latency** lists your top 10 services ra Click any service card to drill into that service's detailed performance data. +### Coworker + +The **Coworker** panel gives you a summary of your AI teammate's activity over the last 30 days, directly from the Overview page. + +| Element | Description | +|---|---| +| **Critical Insights** | Number of critical insights currently needing attention, with a percentage trend indicator and total insight count. Click to expand a list of the current critical insights. | +| **Optimisation suggestions** | Shows the number of pending cost optimisation suggestions. Click it to open the Cost & Optimisation panel directly. | +| **Recent Activity** | A feed of the latest task runs and alert checks, showing what Coworker has been investigating and when. Click **7 more** to expand the full list. | + +Click **Ask** to open a quick-action menu with chat shortcuts: + +- **Catch me up** +- **What needs attention?** +- **What keeps recurring?** + +Select one to send it directly to Coworker. Click **Coworker →** to go to the full Coworker dashboard. + ### Servers The **Servers** section provides a summary of all servers running a FusionReactor agent, including: diff --git a/docs/stylesheets/extra.css b/docs/stylesheets/extra.css index a475d24..8edd5b2 100644 --- a/docs/stylesheets/extra.css +++ b/docs/stylesheets/extra.css @@ -319,6 +319,28 @@ color: #cccccc; } +/* Table header background */ +[data-md-color-scheme="default"] .md-typeset table:not([class]) th { + background-color: #f2f2f2; +} + +[data-md-color-scheme="slate"] .md-typeset table:not([class]) th { + background-color: #1e1e1e; +} + +/* Light mode: visible links */ +[data-md-color-scheme="default"] { + --md-typeset-a-color: #FF6600; +} + +[data-md-color-scheme="default"] .md-typeset a { + color: #FF6600; +} + +[data-md-color-scheme="default"] .md-typeset a:hover { + color: #cc5200; +} + /* Dark mode: white headings, grey body text, visible links */ [data-md-color-scheme="slate"] { --md-typeset-color: #b0b0b0; diff --git a/mkdocs.yml b/mkdocs.yml index de6611a..6fa062d 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -42,6 +42,14 @@ nav: - What is OpsPilot?: what-is-opspilot.md - UI Overview: Data-insights/Features/overview.md - AI: + - Coworker: + - Overview: Data-insights/Features/OpsPilot/Coworker/overview.md + - Getting started: Data-insights/Features/OpsPilot/Coworker/getting-started.md + - Tasks: Data-insights/Features/OpsPilot/Coworker/tasks.md + - Usage: Data-insights/Features/OpsPilot/Coworker/usage.md + - Knowledge: Data-insights/Features/OpsPilot/Coworker/knowledge.md + - Settings: Data-insights/Features/OpsPilot/Coworker/settings.md + - FAQ: Data-insights/Features/OpsPilot/Coworker/faq.md - OpsPilot Assistant: - Overview: Data-insights/Features/OpsPilot/AIoverview.md - User guide: Data-insights/Features/OpsPilot/OpsPilot-user-guide.md