Internal AI Strategy Workspace
A bounded AI workflow for moving from messy campaign briefs to structured strategy.
Campaign Sandbox turns messy campaign briefs into structured creative routes, synthetic audience simulations, risk reviews, execution plans, and exportable strategy reports.
Case Snapshot
The problem, the system response, the available proof, the strategic value, and the intentional boundary.
Problem
Early campaign strategy work often starts with client notes, product claims, creative mandatories, audience assumptions, launch constraints, and unclear positioning.
The challenge was to turn those inputs into structured campaign thinking without pretending to replace strategy, market research, or creative judgment.
The core design constraint was reliability: the system had to be useful without becoming an uncontrolled autonomous agent.
Not an autonomous agent. A bounded strategy workflow.
Objective
Architecture decision
Bounded LLM stages handle interpretation, synthesis, and critique. Deterministic code handles routing, schemas, validation, scoring, access control, proof checks, exports, and safety boundaries.
Campaign strategy requires judgment and synthesis.
Reliability requires deterministic boundaries.
Route selection should remain human-controlled.
Synthetic reactions must not be treated as research.
Exports should be deterministic and auditable.
Workflow / Decision cockpit
The Decision Cockpit summarizes the recommended route, runner-up strength, biggest tradeoff, primary risk, close-score warnings, and selection or export status.
Route development
Every route includes a name, strategic role, killer line, enemy, proof mechanism, visual world, channel fit, failure mode, and strategic estimate.
Synthetic audience reactions are planning hypotheses, not market research.
Creative review
Creative Director Review examines originality, ownability, cultural sharpness, visual potential, conversion clarity, and genericity risk. It also proposes sharper route names, killer lines, and route-level notes.
Key features
Users can paste a campaign brief or upload supported files. Extracted text is shown in an editable preview before the workflow runs. TXT and PPTX are supported reliably; PDF extraction is labeled honestly because results can vary by file and environment.
The system identifies audience desire, audience resistance, the brand proof challenge, the creative trap, the creative opportunity, and a campaign tension statement.
Synthetic personas react to each route as planning hypotheses only. They are never presented as research, survey data, focus-group findings, or performance predictions.
Rules provide route tradeoffs, feasibility estimates, risk categories, close-score warnings, and recommendation logic without claiming predictive accuracy.
The workflow stops before final execution so the user, not the model, chooses which strategic territory should move forward.
Saved runs support internal reuse and comparison while remaining in browser storage rather than a server database.
Execution
After manual route selection, the workflow generates a campaign spine, launch plan, channel system, production system, copy system, measurement system, claims and legal review, and next actions.
Export system
Markdown reports, HTML reports, and PPTX route decks are generated directly from validated workflow output. No LLM is used during export generation.
Reliability and safety design
Proof integrity guardrails block unsupported testimonials, fake user-generated content, and unsubstantiated performance claims unless the source brief provides support.
The repository is public, but a deployed operating surface should remain behind an internal password gate because using the app can trigger server-side LLM calls.
Technical stack
Outcome
Campaign Sandbox is suitable as an internal strategy accelerator and a portfolio case study in reliable AI workflow design.
What I learned
Useful AI systems need deterministic routing, schema validation, explicit safety boundaries, human approval points, quality gates, traceable stages, clear caveats, and controlled access.
The strongest version is not an autonomous marketing agent. It is a structured workspace that accelerates strategy while keeping the human responsible for judgment.
Limitations / Final status
