Feedback AI

Analyzes writing drafts via LLM inference to generate constructive critique on prose quality, narrative structure, pacing, and clarity. The system processes submitted text through a feedback prompt template that instructs the language model to emulate developmental editor commentary, returning structured critique organized by feedback category (character development, plot coherence, dialogue authenticity, etc.). Feedback is generated synchronously with minimal latency to enable immediate iteration.

Generates contextual writing prompts and narrative suggestions based on the current draft content, using the submitted text as semantic context to suggest plot complications, character arcs, dialogue directions, or scene expansions. The system analyzes the draft's existing narrative elements (characters, setting, conflict) and uses LLM generation to propose story developments that extend or deepen the work. Prompts are designed to overcome writer's block by providing concrete narrative directions rather than abstract inspiration.

Maintains session-level history of submitted drafts and corresponding feedback, enabling writers to compare multiple versions of the same passage and track how feedback has been applied across iterations. The system stores draft snapshots with associated feedback and allows side-by-side comparison of revisions. This creates an audit trail of the writing process and helps writers identify which feedback suggestions produced the strongest improvements.

Implements a freemium business model where core feedback generation is available on the free tier with limited monthly submissions, while premium tiers unlock higher submission quotas, advanced feedback categories, and priority LLM inference. The system uses account-level quotas and feature flags to gate access, allowing writers to test the core feedback workflow before committing to paid subscription. Free tier is intentionally useful for drafting-phase work to reduce friction for new users.

Evaluates submitted text for prose-level issues (clarity, conciseness, word choice, sentence variety, passive voice, redundancy) using LLM-guided analysis rather than rule-based grammar checking. The system prompts the language model to identify specific prose weaknesses and suggest improvements, generating feedback that addresses stylistic and readability issues beyond mechanical grammar. Assessment is context-aware, considering the surrounding narrative rather than evaluating sentences in isolation.

Analyzes draft structure to identify pacing issues, narrative flow problems, and plot coherence gaps using LLM-based analysis of scene sequencing and tension arcs. The system evaluates how scenes connect, whether pacing accelerates appropriately toward climax, and whether plot threads are adequately resolved. Feedback addresses macro-level narrative architecture rather than sentence-level prose, helping writers identify structural revisions needed before final polish.

Evaluates character arcs, consistency, and development across the submitted draft by analyzing character actions, dialogue, motivations, and emotional progression using LLM-based narrative analysis. The system identifies inconsistencies in character behavior, flags underdeveloped arcs, and suggests opportunities for deeper character exploration. Feedback addresses whether character motivations are clear, whether emotional beats feel earned, and whether character voices are distinct.

Evaluates dialogue quality, character voice distinctiveness, and conversational authenticity using LLM-based analysis of speech patterns, word choice, and emotional subtext. The system identifies dialogue that feels stilted or exposition-heavy, flags characters with indistinguishable voices, and suggests opportunities for more natural or revealing dialogue. Assessment considers whether dialogue serves narrative function (advancing plot, revealing character) beyond mere conversation.