research/playbook

Business Playbook — high-fidelity, execution-ready startup playbooks.

Category: research
Source: workflows/research/playbook.py

Input Schema

Field	Type	Default	Description
`cluster`	`object`	—
`clusters`	`any[]`	—
`confidence_score`	`number`	`0.5`
`core_value_proposition`	`string`	`""`
`description`	`string`	`""`
`differentiators`	`any[]`	—
`estimated_build_complexity`	`string`	`"medium"`
`idea`	`object`	—
`idea_id`	`string`	`""`
`key_features`	`any[]`	—
`monetization_model`	`string`	`""`
`name`	`string`	`""`
`pricing_suggestion`	`string`	`""`
`problem_cluster_id`	`string`	`""`
`regenerate`	`object`	—	When set, this run is a regeneration. Workflows may read `direction` / `keep` / `extra_instructions` to modulate prompts; the engine persists `parent_run_id` and `parent_variant_index` as run lineage columns.
`spec`	`object`	—
`specs`	`any[]`	—
`tagline`	`string`	`""`
`target_persona`	`string`	`""`
`time_to_mvp_days`	`integer`	`30`
`variants`	`integer`	`1`	Number of independent variant executions (1–10). When > 1, the engine runs the workflow N times with different sampling, producing N outputs.

Output Schema

No schema defined.

Task Pipeline

prepare_playbook_input → generate_playbook_sections → format_playbook_output

Task	Description
`prepare_playbook_input`	Normalize input — accept piped problem-intelligence output or manual fields.
`generate_playbook_sections`	Generate all playbook sections in parallel via thread pool.
`format_playbook_output`	Strip internal keys and return the playbook.

Run-spec example

Save the YAML below as my-run.yaml, edit the values, and run with the CLI or POST it to the API. Required fields are uncommented; optional knobs are documented above the input: block — copy any line under input: and uncomment to set.

workflow: research/playbook

# Optional fields — copy any line(s) under `input:` and uncomment to set:
#   cluster: null
#
#   clusters: []
#
#   confidence_score: 0.5
#
#   core_value_proposition: ""
#
#   description: ""
#
#   differentiators: []
#
#   estimated_build_complexity: medium
#
#   idea: null
#
#   idea_id: ""
#
#   key_features: []
#
#   monetization_model: ""
#
#   name: ""
#
#   pricing_suggestion: ""
#
#   problem_cluster_id: ""
#
#   spec: null
#
#   specs: []
#
#   tagline: ""
#
#   target_persona: ""
#
#   time_to_mvp_days: 30
#

input: {}

Run it locally:

fab-workflow --from-file my-run.yaml

Or submit over the wire — the same file is the request body:

curl -X POST 'https://gofabric.dev/v1/workflows/runs?name=research/playbook' \
  -H 'Authorization: Bearer fab_xxx' \
  -H 'content-type: application/yaml' \
  --data-binary @my-run.yaml

Every workflow also accepts the universal WorkflowInput fields — variants (1–10 fan-out) and regenerate (creative-direction hints with run lineage). See Run-specs (YAML / TOML / JSON) for the full top-level shape (metadata, priority, bundle, parent, etc.).

Warnings

Last user task format_playbook_output has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.