T1 starter · engineering / any team — two data sources gathered in parallel, one model call, one file on disk. Your first taste of « the boring parts run themselves ».
The job
Every morning you reconstruct yesterday from memory. Your git history already knows. This workflow reads the commits since yesterday, stamps the date from a builtin (not from the model’s imagination), and writes the three standup bullets in your tone.The shape
The file
t1-standup-digest.nika.yaml
How it works
Two tasks start together
today and history declare no depends_on — the engine runs them
in parallel. Parallelism is the default, not an option you switch on.The digest waits for both
depends_on: [today, history] makes digest the merge point. Its
prompt interpolates both outputs with ${{ tasks.X.output }}.Constructs you just used
| Construct | Where | Reference |
|---|---|---|
| implicit parallelism | today + history | DAG shape |
exec: | history | The 4 verbs |
nika:date · nika:write | today · save | Builtins |
outputs: | envelope tail | YAML syntax |
Make it yours
- Point
--sinceat your sprint cadence (--since=fridayfor Monday standups). - Swap
mock/echoforanthropic/claude-haiku-4-5— a one-liner job wants a fast model. - Add a
nika:notifytask to post the note straight into your team channel — see Release notes for the pattern.
Next · Meeting actions
Same tier, one new idea: structured output — the model returns typed
JSON, not prose.