> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nika.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Standup digest

> T1 starter · engineering — the standup note writes itself from what you actually committed.

> **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

```mermaid theme={"system"}
flowchart LR
  today["today · nika:date"]:::invoke
  history["history · git"]:::exec
  digest["digest"]:::infer
  save["save · nika:write"]:::invoke
  today --> digest
  history --> digest
  digest --> save
  classDef infer fill:#5b8cff22,stroke:#5b8cff,color:#5b8cff
  classDef exec fill:#ff7a3c22,stroke:#ff7a3c,color:#ff7a3c
  classDef invoke fill:#22d3ee22,stroke:#22d3ee,color:#22d3ee
```

## The file

```yaml t1-standup-digest.nika.yaml theme={"system"}
nika: v1
workflow: standup-digest
description: "Read yesterday's commits, write today's standup note"

model: mock/echo            # deterministic · swap for ollama/llama3.1 (local · zero key)

tasks:
  # No deps between these two → the engine runs them in parallel.
  - id: today
    invoke:
      tool: "nika:date"
      args: { op: now }

  - id: history
    exec:
      command: "git log --since=yesterday --oneline --no-merges"

  - id: digest
    depends_on: [today, history]
    infer:
      prompt: |
        Date · ${{ tasks.today.output }}
        Commits since yesterday ·
        ${{ tasks.history.output }}

        Write my standup note · 3 bullets · done / doing / blocked.
        Plain words · no fluff.

  - id: save
    depends_on: [digest]
    invoke:
      tool: "nika:write"
      args:
        path: "./standup-note.md"
        content: "${{ tasks.digest.output }}"

outputs:
  note: ${{ tasks.digest.output }}
```

## How it works

<Steps>
  <Step title="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.
  </Step>

  <Step title="The digest waits for both">
    `depends_on: [today, history]` makes `digest` the merge point. Its
    prompt interpolates both outputs with `${{ tasks.X.output }}`.
  </Step>

  <Step title="The note lands on disk">
    `nika:write` takes an explicit `content:` — a write without content
    writes nothing. The workflow also returns the note via `outputs:`.
  </Step>
</Steps>

## Constructs you just used

| Construct                  | Where               | Reference                             |
| -------------------------- | ------------------- | ------------------------------------- |
| implicit parallelism       | `today` + `history` | [DAG shape](/concepts/workflows)      |
| `exec:`                    | `history`           | [The 4 verbs](/concepts/verbs)        |
| `nika:date` · `nika:write` | `today` · `save`    | [Builtins](/reference/builtins)       |
| `outputs:`                 | envelope tail       | [YAML syntax](/reference/yaml-syntax) |

## Make it yours

* Point `--since` at your sprint cadence (`--since=friday` for Monday standups).
* Swap `mock/echo` for `anthropic/claude-haiku-4-5` — a one-liner job wants a fast model.
* Add a `nika:notify` task to post the note straight into your team channel — see [Release notes](/examples/release-notes) for the pattern.

<Card title="Next · Meeting actions" icon="list-check" href="/examples/meeting-actions">
  Same tier, one new idea: structured output — the model returns typed
  JSON, not prose.
</Card>