Connect your stack
27 native integrations. 3,200+ tools via managed connectors. Most are one-click OAuth, some use API keys - Viktor handles auth and starts working. No webhooks, no Zapier zaps.
Loading
Viktor is an AI employee that connects to Grafana with a scoped API key and helps you monitor application errors and incidents, running 10 Grafana actions for you like List Folders, Get Dashboard, and Save Dashboard. Ask in plain English in Slack or Microsoft Teams; Viktor does the work in Grafana and reports back. Setup takes about two minutes.
Free to start · No credit card · SOC 2 Type 1 · Works in Slack & Microsoft Teams
Messages you'd actually send. Paste one into Slack or Microsoft Teams, swap in your specifics, and Viktor takes it from there.
“Summarize the new errors in Grafana from the last 24 hours and flag any regressions.”
— you, in Slack or Teams
“Check Grafana for the root cause of last night's incident and report back.”
— you, in Slack or Teams
“Watch Grafana for a new critical alert and page me immediately.”
— you, in Slack or Teams
“Post a summary of this week's Grafana incident count to #eng every Friday.”
— you, in Slack or Teams
Ask in plain English in Slack or Microsoft Teams. Viktor picks the right Grafana actions, runs the work, and reports back. No workflows to build.
Search for dashboards by title, tag, or folder. Returns dashboard UIDs, titles, URLs, tags, and folder info. Use the UID with Get Dashboard to retrieve the full dashboard model. Use List Folders to discover folder UIDs for filtering.
Create or update a Grafana dashboard. This is an upsert operation — if the dashboard UID exists, it updates; otherwise it creates. Use Get Dashboard to retrieve an existing dashboard model before modifying it. Use List Folders to find the target folder UID. Pass overwrite: true to force-save over version conflicts.
Execute a query against any configured data source. Use List Data Sources first to discover available data sources and their UIDs. The query language depends on the data source type.
List all dashboard folders. Folders organize dashboards into logical groups. Use folder UIDs with Search Dashboards to filter by folder, or with Save Dashboard to place a dashboard in a specific folder.
List all configured data sources (Prometheus, Loki, InfluxDB, MySQL, etc.), their types, and UIDs. Use the data source UID with Query Data Source to execute queries. The type field indicates what query language to use (e.g., prometheus → PromQL, loki → LogQL, mysql → SQL).
List all alert rules with their current state (firing, normal, pending, inactive). Returns rule definitions including conditions, labels, and annotations. Use this to answer questions like 'what alerts are firing?' or 'what alerts exist for service X?'.
Get the full dashboard model by UID, including all panels, their queries, variables, and configuration. Use Search Dashboards first to find the dashboard UID. The returned model can be modified and saved back with Save Dashboard.
Get the current authenticated Grafana user's identity, including user ID, name, email, organization, and role. Use this to understand the user's permissions and organizational context. The user ID and org context may be needed when creating dashboards or filtering resources.
Permanently delete a Grafana dashboard by UID. This cannot be undone. Use Search Dashboards to find the dashboard UID.
Create an annotation on a dashboard or globally. Annotations mark events like deployments, incidents, or configuration changes on dashboard timelines. Use Search Dashboards to find the dashboard UID. Omit dashboardUid for a global annotation visible on all dashboards. Use time and timeEnd for range annotations (e.g., deployment window).
27 native integrations. 3,200+ tools via managed connectors. Most are one-click OAuth, some use API keys - Viktor handles auth and starts working. No webhooks, no Zapier zaps.
Message Viktor in Slack like you'd message a teammate. "Summarize the new errors in Grafana from the last 24 hours and flag any regressions." "Check Grafana for the root cause of last night's incident and report back." Plain English, any tool.
Viktor opens Grafana, runs the work, and posts back what changed. Sensitive actions wait for your approval. Everything is logged. You stop doing the work and start reviewing it.
A Grafana AI agent is an AI that connects to your Grafana account and completes work in it - it doesn't just answer questions about Grafana, it takes the actions. Viktor is that agent: an AI employee that works in Grafana on your behalf and delivers the finished result in Slack or Microsoft Teams.
Unlike workflow builders such as Zapier or Make, there is nothing to configure - no triggers to map, no workflows to maintain. You describe the outcome in plain English, and Viktor picks the right Grafana actions, chains them with the other 3,200+ tools it connects to, and asks for approval before anything sensitive runs.
Open and composable observability platform
Scoped API keys - Viktor stores your key securely, uses only the scopes you grant, and you can revoke it at any time.
Review-first approvals: sensitive Grafana actions wait for your sign-off before they run.
Isolated compute per team, encrypted in transit and at rest - and your data is never used to train models.
SOC 2 Type 1 compliant, with Type 2 and ISO 27001 in progress.
Yes. Grafana is one of the 3,200+ tools Viktor connects to, via a managed connector. Once connected, anyone on your team can put Viktor to work in Grafana from Slack or Microsoft Teams - no workflow builder, no code.
Ask for outcomes that span tools — Viktor pulls from Grafana, cross-references the rest of your stack, and delivers one finished result.
Viktor connects to 3,200+ tools and works across them in a single run.
