ENGINEERING
On-demand: investigate a slow query and explain the likely cause
Ask in chat about a slow query and an agent pulls its Honeycomb traces, cross-references recent deploys and PRs.
How it runs
The automated pipeline, trigger to output.
- TriggerEngineer asks about a slow query in chatSlack
- ActionPull query latency history and traces from HoneycombHoneycomb
- ActionGather recent GitHub commits, PRs, and deploysGitHub
- LogicReason over traces and diffs to rank causes
- OutputReply with explanation and optionally file Linear issueLinear
What it does
Gives engineers a conversational way to investigate a regression on demand. You name the query or endpoint; the agent gathers the trace evidence, lines it up against deploy history, reasons over what changed, and explains its top suspect in plain language with links.
When to use it
Use it during incident triage or a debugging session when you want an investigator that reasons across traces and code history, rather than a fixed report — especially when the regression doesn't map cleanly to one deploy.
How it works
- 1An engineer triggers the flow from chat naming the slow query and time range.
- 2The agent queries Honeycomb for that query's latency history and exemplar slow traces.
- 3It pulls recent GitHub commits, PRs, and deploys covering the regression window.
- 4It reasons over the trace spans and diffs to weigh candidate causes, asking follow-ups if needed.
- 5It replies in chat with a ranked explanation, the suspect PR, and the supporting trace.
- 6On request it files a Linear issue capturing the findings.
Set it up
What you configure once, before turning it on.
- 1Connect HoneycombDistributed traces and queries.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect LinearIssues, projects, cycles, triage.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Block PRs that add incompatible Hugging Face model licenses
When a pull request adds or bumps a Hugging Face model dependency, it fetches the model card license, checks it against your org's allowed-license policy.
Quarterly Logging Hygiene Audit Agent
An agent-driven quarterly sweep that surveys all Axiom datasets, builds a logging-hygiene scorecard per service.
Post-Merge Log Volume Recheck After Downsampling PR
After a log-level PR merges, waits a day then re-queries Axiom to confirm the targeted stream's volume actually dropped.
Axiom Ingest Cost Spike to Linear Triage Ticket
When Axiom ingest volume spikes beyond its baseline, identifies which service caused it and files a Linear ticket with the offending log stream, sample lines, and a downsampling…
File a Linear license-review ticket for risky model adds
When a PR introduces a Hugging Face model with a non-permissive or unknown license, it opens a Linear issue assigned to the legal-review team with the model, license.
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.