InSummary

Extracts structured event data from connected calendar sources (Google Calendar, Outlook, etc.) by parsing event metadata including titles, descriptions, attendees, timestamps, and custom fields. The system normalizes heterogeneous calendar formats into a unified internal representation, handling timezone conversions, recurring event expansion, and attendee resolution to build a queryable event corpus for downstream analysis.

Synthesizes extracted calendar events into narrative performance review text using LLM-based summarization and insight extraction. The system identifies key themes (projects worked on, meetings attended, cross-functional collaboration), quantifies activity (meeting hours, attendee diversity), and generates structured review sections (accomplishments, collaboration, growth areas) by prompting an LLM with the normalized event corpus and optional user-provided context or goals.

Exports finalized reviews and reports to multiple formats (PDF, Word, plain text, HTML) and integrates with common sharing mechanisms (email, Google Drive, Slack, ATS systems). The system handles formatting preservation across formats, manages access controls, and may provide sharing links with expiration or view-only permissions.

Automates the scheduling and generation of recurring performance reviews and status reports on a defined cadence (weekly, monthly, quarterly, annually). The system manages scheduling logic, triggers generation at specified times, and may send reminders or notifications to users and managers when reports are due or ready for review.

Generates weekly or monthly status reports by aggregating calendar events into time-bucketed summaries (e.g., 'This week I attended X meetings, worked on Y projects, collaborated with Z teams'). The system uses template-based or LLM-driven formatting to structure the report with sections for accomplishments, in-progress work, blockers, and upcoming priorities, pulling narrative content from event titles, descriptions, and attendee lists.

Analyzes the completeness and quality of calendar data to identify gaps, vague event titles, missing attendee information, or sparse event coverage that would degrade downstream summarization. The system may provide feedback to users (e.g., 'Your calendar is 40% sparse this month; add more event details to improve summary quality') and flag events with low-signal titles that cannot be meaningfully summarized.

Integrates calendar data from multiple sources (Google Calendar, Microsoft Outlook, Apple Calendar) into a unified event corpus, handling authentication, permission scoping, and conflict resolution when the same event appears across multiple calendars. The system deduplicates events, merges attendee lists, and maintains source attribution for audit purposes.

Allows users to define custom templates for performance reviews and status reports, specifying sections, formatting, tone, and content emphasis (e.g., 'focus on leadership moments', 'include metrics on meeting hours'). The system uses template variables and conditional logic to populate sections based on extracted calendar data, enabling organizations to standardize review formats while maintaining flexibility.

Aggregates calendar events into user-defined time periods (weekly, monthly, quarterly) for summarization and reporting. The system handles period boundaries, handles events spanning multiple periods, and provides configurable aggregation logic (e.g., sum meeting hours, count unique projects, list attendees per period). Supports both fixed periods (calendar weeks/months) and custom date ranges.

Extracts attendee information from calendar events and computes collaboration metrics such as unique collaborators, cross-functional team interactions, meeting frequency with specific individuals, and collaboration diversity (e.g., 'collaborated with 15 unique people across 5 teams'). The system may identify key stakeholders, frequent collaborators, and collaboration patterns to highlight in reviews.

Applies natural language processing to calendar event titles and descriptions to extract key topics, projects, and accomplishments without requiring manual tagging or structured metadata. The system uses NLP techniques (entity recognition, topic modeling, keyword extraction) to identify project names, deliverables, and work themes from unstructured text, enabling summarization even when events are not explicitly categorized.

Provides a user-facing interface for reviewing, editing, and refining auto-generated performance reviews and status reports before finalization. The system allows users to add missing accomplishments, remove inaccurate statements, adjust tone, and provide additional context that was not captured from calendar data. Changes are tracked and may be used to improve future summaries.