SUMMARIZATION
Post-deploy span regression check with GitHub annotation
When a deploy webhook arrives, waits for a bake window, compares span latencies before and after the release, and if a regression is detected.
How it runs
The automated pipeline, trigger to output.
- TriggerDeploy webhook with release SHA arrivesHTTP webhook
- ActionQuery Honeycomb before/after span latenciesHoneycomb
- LogicBranch: stop if no service regressed past threshold
- ActionDraft regression narrative tied to the commitOpenAI
- ActionComment narrative on the GitHub commitGitHub
- OutputAlert perf channel with verdictSlack
What it does
This workflow ties latency regressions to the deploy that caused them. On a deploy webhook, it waits out a bake window, then compares Honeycomb span latencies in the pre-deploy and post-deploy windows for the affected services. If a meaningful regression appears, it writes a narrative linking the slowdown to that release and comments it directly on the GitHub commit, plus pings Slack.
When to use it
Use it when you want every deploy automatically vetted for latency impact, with the finding attached to the exact commit so the author sees it without digging. It closes the loop between "we shipped" and "things got slow."
How it works
- 1A deploy webhook fires with the release SHA and timestamp.
- 2The workflow waits the configured bake window for traffic to stabilize.
- 3It queries Honeycomb for span latencies in the before and after windows.
- 4It branches: if no service regressed past threshold, the run records a clean result and stops.
- 5An LLM drafts a regression narrative naming the slowed operations and the suspect commit.
- 6The narrative is posted as a comment on the GitHub commit and to the perf Slack channel.
Set it up
What you configure once, before turning it on.
- 1Connect HoneycombDistributed traces and queries.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect GitHubRepos, issues, pull requests, actions.
- 4Connect SlackChannels, DMs, threads, mentions.
- 5Connect HTTP webhookTrigger any URL on agent actions.
- 6Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 7Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 8Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Summarization workflows
Daily Front Escalation Digest with Salesforce Rollup
Each morning, sweeps the prior day's escalated Front conversations, summarizes each, enriches with Salesforce account value, and emails account execs a single prioritized digest.
File a Linear ticket for regressed errors after deploy
Detects Sentry issues that regressed in the latest deploy's release window, summarizes what broke and when it was previously fixed.
Daily release-health rollup to Confluence
Each morning, compares the last 24 hours of Sentry activity against the deploys that shipped in that window and publishes a dated release-health page to Confluence summarizing…
On-submit Loom standup roll-up archived to Confluence
When a standup video is submitted via webhook, transcribes it, generates a per-person written summary, and appends it to a running team standup page in Confluence.
Front Escalation Handoff Doc in Notion
When a Front escalation closes, drafts a structured handoff document in Notion capturing the resolution, customer commitments, and open follow-ups, then alerts the AE in Slack.
VIP Front Escalation Instant Exec Page-Out
Detects escalations from VIP accounts in Front, generates a one-paragraph executive recap, and pages the named account exec via Slack and Salesforce task within minutes.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.