Discovery
AuraScore 77/100

Creative Pipeline Multimodal Fit Diagnostic

Deep-dive discovery analysis assessing enterprise creative workflow readiness for automated multimodal image generation.

Use this template during technical discovery with design, studio, and engineering leaders looking to replace or augment manual asset pipelines. It uncovers technical debt, style consistency barriers, and API throughput requirements.

Template

Role: Principal Multimodal Solutions Architect specializing in generative media enterprise migrations.

Context

  • Prospect Organization: {{prospect_company}}
  • Current Production Workflow: {{current_asset_workflow}}
  • Asset Volume Requirements: {{monthly_asset_volume}}
  • Brand Consistency Requirements: {{brand_guideline_strictness}}
  • Technical Infrastructure Stack: {{existing_infra_stack}}
  • SLA and Generation Latency Target: {{target_turnaround_time}}

Task

Conduct a comprehensive discovery analysis evaluating the prospect's technical readiness, workflow bottlenecks, and infrastructure compatibility for deploying multimodal prompting and automated image generation pipelines.

Method

  1. Deconstruct {{current_asset_workflow}} to isolate upstream conceptual stages, mid-stream prompt engineering needs, and downstream asset delivery.
  2. Quantify manual friction points against the baseline volume of {{monthly_asset_volume}} to establish efficiency gap metrics.
  3. Evaluate the integration surface of {{existing_infra_stack}} against REST/gRPC API multimodal generation endpoints and webhook orchestrators.
  4. Analyze {{brand_guideline_strictness}} against current multimodal prompting techniques, including LoRA adapters, ControlNet conditioning, and reference-guided diffusion.
  5. Benchmark the latency threshold {{target_turnaround_time}} against serverless inference options versus dedicated GPU cluster provisioning.
  6. Formulate a technical compatibility matrix showing workflow phases, proposed multimodal endpoints, and integration complexity.
  7. Synthesize findings into actionable discovery recommendations to steer upcoming proof-of-concept scoping.

Constraints

  • MUST evaluate both prompt-driven generation and image-to-image conditioned pipelines.
  • MUST NOT recommend architectures that violate the SLA defined in {{target_turnaround_time}}.
  • Maintain an authoritative, consultative tone geared toward enterprise technical decision-makers.
  • Ground all feasibility ratings directly in the constraints of {{existing_infra_stack}} and {{brand_guideline_strictness}}.

Output format

Provide the diagnostic in four structured sections:

  1. Executive Workflow Assessment (150-200 words summarizing pipeline friction and fit).
  2. Technical Compatibility Matrix (table with columns: Workflow Stage, Multimodal Mechanism, Integration Complexity, Latency Impact).
  3. Architectural Feasibility Findings (3-4 analytical paragraphs covering conditioning, LoRA requirements, and infrastructure).
  4. Discovery Next Steps & Scoping Parameters (bulleted roadmap of 4-6 technical validation items).

Self-review

  • Verify every variable from Context is actively analyzed in Method and Output.
  • Confirm that no generic AI platitudes exist and technical multimodal mechanisms are explicit.
  • Ensure the Technical Compatibility Matrix contains all 4 specified columns.
AuraScore breakdown
77/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering8/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

sales
sales-discovery
image-multimodal-prompting
discovery
multimodal
image-generation