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 Logfire with a scoped API key and helps you run and evaluate LLM and AI infrastructure workloads, running 2 Logfire actions for you like Run SQL Query, and Record Log Entry. Ask in plain English in Slack or Microsoft Teams; Viktor does the work in Logfire 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.
“Run this batch of documents through Logfire and summarize the results.”
— you, in Slack or Teams
“Compare Logfire's output on this prompt with what we use today.”
— you, in Slack or Teams
“Set up a daily job that queries Logfire on new entries and reports back.”
— you, in Slack or Teams
“Watch Logfire for a cost or latency spike and alert me with the likely cause.”
— you, in Slack or Teams
Ask in plain English in Slack or Microsoft Teams. Viktor picks the right Logfire actions, runs the work, and reports back. No workflows to build.
Executes an arbitrary SQL query against Logfire's records (unified logs + traces, one row per span) or metrics tables and returns the results. Use this for any analysis, search, or aggregation over your telemetry — recent activity, error hunting, latency analysis, counts, etc. To discover what columns are available before writing a query, run SELECT columnname, datatype FROM informationschema.columns WHERE tablename = 'records' (or 'metrics') with this same tool — there is no separate schema-discovery tool. Useful columns on records include starttimestamp, spanname, message, level, servicename, duration, isexception, exceptiontype, and exceptionmessage. Example — find exceptions: SELECT spanname, exceptiontype, exceptionmessage FROM records WHERE isexception = true ORDER BY starttimestamp DESC. Example — count by level: SELECT level, count() AS n FROM records GROUP BY level ORDER BY n DESC. After using Record Log Entry to write data, use this tool to confirm what was recorded. See the SQL reference and query API docs.
Records a single log entry or event in Logfire as a zero-duration span, via OTLP ingestion. Use this whenever the user wants to log, record, or note an event, deployment, incident, or error — this is Logfire's equivalent of calling logfire.info()/logfire.error() from the SDK. This creates a single point-in-time entry, not a full distributed trace with parent/child spans. Setting exceptionType/exceptionMessage marks the entry as an exception (isexception = true when later queried). After recording, use Run SQL Query to confirm what was written (e.g. SELECT FROM records WHERE message LIKE '%...%' ORDER BY starttimestamp DESC LIMIT 1).
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. "Run this batch of documents through Logfire and summarize the results." "Compare Logfire's output on this prompt with what we use today." Plain English, any tool.
Viktor opens Logfire, 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 Logfire AI agent is an AI that connects to your Logfire account and completes work in it - it doesn't just answer questions about Logfire, it takes the actions. Viktor is that agent: an AI employee that works in Logfire 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 Logfire actions, chains them with the other 3,200+ tools it connects to, and asks for approval before anything sensitive runs.
AI Observability Platform for LLMs, Apps & RAG
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 Logfire 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. Logfire 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 Logfire from Slack or Microsoft Teams - no workflow builder, no code.
Ask for outcomes that span tools — Viktor pulls from Logfire, 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.
