CHATBOTS

Status Concierge with Question Logging to Snowflake

Answers "is X degraded" in Slack from live Datadog monitors and logs every question, resolved service, and verdict to Snowflake so you can see which services people worry about…

CategoryChatbots
EngineSim + Paperclip
Difficultyadvanced
Triggerchat
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerSlack command asks about service healthSlack
  • ActionResolve name + query Datadog monitorsDatadogDatadog
  • LogicCompute verdict from monitor states
  • OutputReply verdict + monitor link in SlackSlack
  • ActionLog question, service, verdict to SnowflakeSnowflakeSnowflake

What it does

Serves the standard chat health check — ask in Slack, get a Datadog-backed verdict — and additionally records each interaction (raw question, resolved service, verdict, timestamp, asker) into a Snowflake table. Over time this reveals which services drive the most uncertainty and where your dashboards or comms fall short.

When to use it

When you run the concierge at scale and want data on it: which services get asked about most, how often the answer is "degraded," and which teams ask. Feeds reliability reviews and helps prioritize observability investment.

How it works

  1. 1A Slack command or mention asks about a service's health.
  2. 2The flow resolves the name and queries Datadog monitor states.
  3. 3A logic step computes the verdict (ok / degraded / unknown).
  4. 4The bot replies in-thread with the verdict and monitor link.
  5. 5In parallel, an action writes a row to Snowflake capturing the question text, resolved service, verdict, asker, and timestamp for later analysis.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SlackChannels, DMs, threads, mentions.
  2. 2
    Connect DatadogMetrics, traces, log search.
  3. 3
    Connect SnowflakeWarehouses, queries, shares.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.