SKILL.md · 24000
This is the test that tells you "it works" for real. If no matching real event exists yet (common if the eval was just enabled), trigger the feature yourself, wait ~1 minute, and retry.
Recommended flow: synthetic → sanity-check the block template renders → flip real-requests on → confirm an actual post lands in the channel → save + enable the workflow.
Step 7 — End-to-end verify in production
Once the workflow is enabled, trigger the feature yourself. Within a minute or two:
- The
$ai_generationevent should appear in AI observability - The eval should auto-run and emit an
$ai_evaluationevent - The workflow should fire and the Slack post should land in the configured channel
- Click "View Trigger Session" — should land on the recording of you using the feature, not the replay homepage
If "View Trigger Session" lands on the replay homepage, $session_id is missing on the $ai_evaluation event (which is separate from the $ai_generation event — threading is independent for the two). Backend fix needed — see prerequisites.
Worked example A (Pattern A): group session summary use cases
Pattern: a group_summary_use_case_feed eval streaming to a #<team>-usage-feed channel. Trace prefix: session-summary:group:. Opener: "A user ran a group summary on". Slack channel showed e.g.:
📊 group_summary_use_case_feed triggered by some user "A user ran a group summary on a company's onboarding sessions from the last 7 days. They were trying to understand why account activation rates are low. The summary surfaced that most users abandon at the company onboarding wizard after creating accounts." [View Trace] [View Trigger Session] [View Person]
The PRs that made this work (linked here as worked examples of the session_id threading pattern, not as steps in the skill itself):
- PostHog/posthog#54952 — threads
trigger_session_idthrough to$ai_generationevents on the session summary backend - (Followup PR — threads
$session_idonto$ai_evaluationevents specifically)
Worked example B (Pattern B): PostHog AI in error tracking mode
Pattern: an agent_mode = 'error_tracking' scoped feed streaming to a #<team>-usage-feed channel, answering "what are users actually trying to DO when they chat with PostHog AI in error tracking mode?" Mode sizing varies by an order of magnitude or more across agent modes — spot-check volume per §Step 1 before wiring, because a high-volume mode can flood a channel. Opener: "A user asked PostHog AI about".
Enabling PR: PostHog/posthog#55160 — threads agent_mode and supermode onto every $ai_generation emitted by the chat agent loop. Wiring lives in ee/hogai/core/agent_modes/executables.py (AgentExecutable._get_model) and passes the dict through the existing posthog_properties field on MaxChatMixin in ee/hogai/llm.py. Before this PR, scoping a PostHog AI eval to a specific mode wasn't possible — you'd end up evaluating every PostHog AI generation, which produced noisy feeds with low single-digit PASS rates.
Key observation from setup: the agent_mode tag reflects the mode at turn-time, but chat state retains mode selection even when users drift off-topic mid-conversation. Spot-check: a random agent_mode=error_tracking sample included a conversation that ended up being about session replay pricing. The eval prompt's classification must be permissive about topic drift — PASS only when the turn is recognizably in-scope for the mode, FAIL when the conversation has drifted to something else entirely.
Validating signal quality after launch
Once the feed has been running for a day or two, sanity-check the eval output at scale.
If posthog:llma-evaluation-report-create is exposed: schedule an AI report on the eval so the pass/fail picture keeps arriving without you asking for it.
posthog:llma-evaluation-report-create
{
"evaluation": "<uuid>",
"frequency": "scheduled",
"rrule": "FREQ=WEEKLY;BYDAY=MO",
"delivery_targets": [{ "type": "email", "value": "[email protected]" }]
}
posthog:llma-evaluation-report-generate runs a configured report right away, and posthog:llma-evaluation-report-run-list returns the content of past runs.
UI fallback: open the eval in AI observability → Evaluations, then the "Reports" tab.
If the FAIL bucket is large, the classification step is too strict — relax it. If the PASS bucket has lots of generic reasonings, iterate on the prompt to enforce concreteness. The report gives a quick read on this without you having to scroll through individual events.
Spot-check raw events when needed (note: the stored result value is 'True', not 'PASS' — see step 6):
SELECT
properties.$ai_evaluation_reasoning AS reasoning,
properties.$ai_trace_id AS trace_id,
timestamp
FROM events
WHERE event = '$ai_evaluation'
AND properties.$ai_evaluation_name = '<your eval name>'
AND properties.$ai_evaluation_result = 'True'
AND timestamp > now() - INTERVAL 1 DAY
ORDER BY timestamp DESC
LIMIT 25
Tips
- The reasoning field IS the Slack message — design the prompt for that, not for "chain of thought before classification." Models can produce structured Slack-ready text in one pass.
- LLM judges are non-deterministic across reruns. Expect 1-5% noise even with a fixed prompt and model. If you need reproducibility, pin a deterministic provider/seed in
model_configuration. - Keep the eval scoped tightly via the
conditionsproperty filters on$ai_trace_idprefix. Otherwise it fans out to every$ai_generationevent in the project and burns LLM cost. - For high-volume features (>10k traces/week), consider sampling — set the eval to run on a percentage of matching events rather than all of them. Slack flooding is a real failure mode.
- The "View Trigger Session" button is the highest-value link in the alert. Without it, the feed is just text — you can't watch what the user was actually doing. Verify it works in step 7 before considering the feed shipped.
- Once the feed is live, keep reading the passing runs' reasoning (a scheduled report, or the SQL above with
$ai_evaluation_result = 'True') to surface the dominant use case clusters. That's how you turn the feed into actual product insights instead of just a notification stream.