AI AGENTS
Conversational Drop-Rule Advisor for Telemetry Spend
A chat agent an engineer asks about a noisy metric or dataset; it inspects live Datadog and Honeycomb cardinality and returns a ready-to-paste drop or aggregate rule…
How it runs
The automated pipeline, trigger to output.
- TriggerEngineer sends a chat message naming a metric or dataset
- ActionPull current cardinality and volume from Datadog and HoneycombDatadog
- ActionInspect dataset volume and query patterns in HoneycombHoneycomb
- LogicEvaluate safe-to-drop dimensions and draft rule
- OutputReply in chat with rule, rationale, and savings
What it does
This is an on-demand advisor you talk to in chat. Ask it something like which tags on a metric are costing the most, or whether a Honeycomb dataset can be safely sampled, and it queries the live cardinality and volume, reasons about which dimensions are safe to drop or aggregate, and hands back a concrete rule you can paste into your collector config along with an estimate of what it saves.
When to use it
Use it during cost-cleanup sessions or incident reviews when an engineer wants a fast, specific answer about one metric or dataset instead of waiting for a scheduled report. It complements the automated scans by serving ad-hoc questions.
How it works
- 1An engineer sends a chat message naming a metric, tag, or dataset.
- 2The agent parses the target and pulls current cardinality and volume from Datadog and Honeycomb.
- 3A logic step evaluates which dimensions are high-cardinality and low-query-value and therefore safe to drop or aggregate.
- 4It drafts the exact drop or aggregate rule and computes projected monthly savings.
- 5It replies in chat with the rule, the rationale, and the savings estimate.
Set it up
What you configure once, before turning it on.
- 1Connect DatadogMetrics, traces, log search.
- 2Connect HoneycombDistributed traces and queries.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More AI Agents workflows
Custom Metrics Cardinality Spike Pager
A webhook from a Datadog monitor fires when custom-metric cardinality jumps; an agent pinpoints the offending metric and tag, estimates the added cost.
Sentry-to-Confluence Runbook Updater
When a Sentry issue is resolved, the agent finds the matching Confluence runbook page and proposes an inline update with the verified fix.
Stale Doc-PR Chaser for Runbook Gaps
On a daily schedule the agent finds runbook doc PRs that were opened from resolved incidents but never reviewed, summarizes what each one fixes.
Resolved Incident to Public Troubleshooting Doc
For customer-facing errors resolved in Sentry, the agent drafts a sanitized troubleshooting entry and opens a PR to your ReadMe documentation.
On-Call Runbook Gap Closer: Resolved Sentry Issues to Doc PRs
An agent reads each newly resolved Sentry issue, compares the actual fix against your existing runbook, and opens a GitHub PR adding the missing remediation steps.
Weekly On-Call Doc-Gap Digest
Each week the agent reviews every Sentry issue resolved in the last 7 days, ranks the ones whose runbook coverage is missing or thin.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.