research/idea-deep-dive

Idea Deep Dive — take a startup idea and produce a complete business blueprint.

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

Input Schema

Field	Type	Default	Description
`category`	`string`	`""`
`core_value_proposition`	`string`	`""`
`description`	`string`	`""`
`differentiators`	`any[]`	—
`estimated_build_complexity`	`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.
`tagline`	`string`	`""`
`target_persona`	`string`	`""`
`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_idea → validate_market → generate_product_variants → plan_content_strategy → merge_variants_and_content → research_pricing → design_landing_page → plan_go_to_market → project_revenue → merge_final_branches → format_deep_dive

Task	Description
`prepare_idea`	Normalize the input — accept either a full idea dict or manual fields.
`validate_market`	Estimate TAM/SAM/SOM, map competitors, and assess market timing.
`generate_product_variants`	Generate all viable product forms — not just SaaS.
`plan_content_strategy`	Generate a content strategy for organic growth — blog, video, lead magnets.
`merge_variants_and_content`	Merge parallel results from product-variants and content-strategy branches.
`research_pricing`	Research pricing strategy — competitor prices, willingness to pay, tier design.
`design_landing_page`	Generate a complete landing page blueprint with copy.
`plan_go_to_market`	Generate a go-to-market playbook — first 100 users, launch strategy, partnerships.
`project_revenue`	Generate revenue projections — conservative, moderate, aggressive scenarios.
`merge_final_branches`	Merge parallel results from landing-page, GTM, and revenue branches.
`format_deep_dive`	Structure the final deep dive output.

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/idea-deep-dive

# Optional fields — copy any line(s) under `input:` and uncomment to set:
#   category: ""
#
#   core_value_proposition: ""
#
#   description: ""
#
#   differentiators: []
#
#   estimated_build_complexity: ""
#
#   key_features: []
#
#   monetization_model: ""
#
#   name: ""
#
#   pricing_suggestion: ""
#
#   problem_cluster_id: ""
#
#   tagline: ""
#
#   target_persona: ""
#

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/idea-deep-dive' \
  -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_deep_dive has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.
Task merge_variants_and_content has no Pydantic types — contract is opaque to consumers.
Task merge_final_branches has no Pydantic types — contract is opaque to consumers.