> ## 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.

# Deep research brief

> T4 epic · research — plan → budgeted research agent → thinking-model synthesis. Auditable end to end.

> **T4 epic · research / consulting / VC** — plan-then-execute. A fast
> model writes the plan, an agent works the web **under explicit
> budgets**, a thinking model synthesizes. Three stages, three different
> cost profiles, every intermediate on disk.

## The job

« Get me up to speed on X by Thursday » is two days of tabs, or it's
this pipeline: four sharp queries planned, researched with verbatim
quotes and source tracking, synthesized into an executive brief that
separates what's true from what's contested.

## The shape

```mermaid theme={"system"}
flowchart LR
  plan["plan · typed"]:::infer
  investigate["investigate · 3 tools"]:::agent
  brief["brief · thinking"]:::infer
  save["save · nika:write"]:::invoke
  plan --> investigate
  investigate --> brief
  brief --> save
  classDef infer fill:#5b8cff22,stroke:#5b8cff,color:#5b8cff
  classDef invoke fill:#22d3ee22,stroke:#22d3ee,color:#22d3ee
  classDef agent fill:#b07bff22,stroke:#b07bff,color:#b07bff
```

## The file

```yaml t4-deep-research-brief.nika.yaml theme={"system"}
nika: v1
workflow: deep-research-brief
description: "plan → budgeted research agent → thinking synthesis → brief on disk"

model: anthropic/claude-sonnet-4-6

vars:
  topic:
    type: string
    required: true
    description: "What to research"

tasks:
  - id: plan
    infer:
      model: anthropic/claude-haiku-4-5    # planning is a fast-model job
      prompt: "Break '${{ vars.topic }}' into 4 sharp research queries · no overlap."
      schema:
        type: object
        required: [queries]
        properties:
          queries:
            type: array
            items: { type: string }

  - id: investigate
    depends_on: [plan]
    agent:
      system: |
        You are a rigorous researcher. Work the queries one by one ·
        fetch sources · keep verbatim quotes · note what each source
        actually supports. Call nika:done when the plan is exhausted.
      prompt: "Research plan · ${{ tasks.plan.output.queries }}"
      tools:
        - "nika:fetch"                 # the web
        - "nika:write"                 # scratch notes
        - "nika:done"                  # the loop-completion sentinel
      max_turns: 25
      max_tokens_total: 150000
      schema:
        type: object
        required: [findings, sources]
        properties:
          findings:
            type: array
            items: { type: string }
          sources:
            type: array
            items: { type: string }

  - id: brief
    depends_on: [investigate]
    infer:
      prompt: |
        Findings · ${{ tasks.investigate.output.findings }}
        Sources · ${{ tasks.investigate.output.sources }}
        Write the executive brief · what's true · what's contested ·
        what it means · what to do. Two pages max.
      thinking:
        enabled: true
        budget_tokens: 8000

  - id: save
    depends_on: [brief]
    invoke:
      tool: "nika:write"
      args:
        path: "./research/${{ vars.topic }}.md"
        content: "${{ tasks.brief.output }}"
        create_dirs: true

outputs:
  brief: ${{ tasks.brief.output }}
  sources:
    value: ${{ tasks.investigate.output.sources }}
    type: array
    description: "Every source the agent actually used"
```

## How it works

<Steps>
  <Step title="Right model, right stage">
    Planning is a haiku-class job (`model:` override on the task);
    synthesis gets a `thinking:` budget. The envelope default covers the
    middle. One file, three cost profiles.
  </Step>

  <Step title="The agent has a leash">
    `max_turns: 25` + `max_tokens_total: 150000` bound the loop;
    `nika:done` lets it exit cleanly when the plan is exhausted. The
    final message must match the schema — findings AND sources.
  </Step>

  <Step title="Callable by other workflows">
    The typed `outputs:` (`brief`, `sources`) make this a building
    block — a parent workflow can consume the contract without parsing
    prose.
  </Step>
</Steps>

## Constructs you just used

| Construct                   | Where         | Reference                             |
| --------------------------- | ------------- | ------------------------------------- |
| per-task `model:` override  | `plan`        | [Providers](/concepts/providers)      |
| agent budgets + `nika:done` | `investigate` | [The 4 verbs](/concepts/verbs)        |
| `thinking:`                 | `brief`       | [The 4 verbs](/concepts/verbs)        |
| typed `outputs:`            | envelope tail | [YAML syntax](/reference/yaml-syntax) |

## Make it yours

* Force source-grounding harder: have `brief` cite `${{ tasks.investigate.output.sources }}` inline per claim.
* Competitive variant: seed `plan` with [Competitor radar](/examples/competitor-radar)'s digest instead of a bare topic.
* Weekly cadence: pair with your scheduler and diff this week's brief against last week's with `nika:json_diff`.

<Card title="Next · Incident war room" icon="fire-extinguisher" href="/examples/incident-war-room">
  Parallel evidence gathering, a settle-and-recheck loop, and a
  postmortem that refuses to claim recovery it can't prove.
</Card>