memopop-orchestrator/specs
- Path
- specs/index.md
Specs
- Containerizing Internal Comments and Recommendations for Consideration - Specification for separating LLM process commentary and meta-narration from final memo output into structured internal notes.
- Dataroom Analyzer Agent System Plan - A comprehensive plan for implementing a multi-agent dataroom analysis system that intelligently recognizes, categorizes, and extracts information from diverse document types in investment datarooms.
- Deck Analyzer Agent - A specialized agent for extracting structured data and visual screenshots from pitch decks (PDF and PowerPoint) to bootstrap investment memo generation.
- GUI Action Catalog — Draft v1 - Audit of the orchestrator’s CLI surface, bucketed by GUI tier. Defines which CLIs become buttons in v1, which wait for v2/v3, and which are excluded entirely. Includes a draft gui_actions.json and a query catalog.
- Interactive Terminal Application — Easy Interface for Casual Users - A guided CLI application that walks users through memo generation, export, and iteration without requiring knowledge of individual commands, flags, or file paths.
- Introducing Investigate Capital Syndicate with Detailed Artifacts - A research agent that investigates every investor, fund, family office, and financial institution on a company’s cap table and in the current round — producing detailed profiles, pattern analysis, and signal extraction for investment decision-making.
- Introducing a Competitive Landscape Research and Evaluation System - Two coordinated agents—a Competitive Landscape Researcher and a Competitive Landscape Evaluator—that produce accurate, validated competitor analysis by combining multi-query web research with structured relevance screening.
- Introducing a Content Density Mode System - A system-level content mode toggle (redundant vs concise) that alters the behavior of the writer, table generator, and quality agents to match different firm preferences for information density and repetition.
- Introducing a Diagram Generator Agent - Add a diagram_generator.py agent that identifies opportunities to create visual diagrams explaining complex business concepts, starting with TAM/SAM/SOM market sizing and expanding to common finance and consulting visuals.
- Introducing a GUI Native Desktop with Tauri - Specification for a Tauri control panel app that wraps the existing memo orchestration CLIs and agents. Mac-first build, written to keep cross-platform porting cheap.
- Introducing a KPI Extractor Agent - A zero-hallucination agent that extracts verifiable KPIs from pitch decks, dataroom documents, and spreadsheets, then cross-references with Perplexity internet search to validate accuracy.
- Introducing a Legal Doc Comparator - An agent that compares deal-specific legal documents (SAFEs, convertible notes, term sheets, incorporation docs) against firm-maintained standard templates, surfacing deviations and flagging common legal risks using a shared reference document.
- Introducing a One-Pager Cover Sheet and Export - A post-pipeline agent and CLI tool that distills the full investment memo into a single-page visual summary, usable as both a standalone deliverable and a cover sheet prepended to the full memo export.
- PDF Parser Agent Specification - A small specification for an agent and script to parse PDFs and convert them to markdown with properly formatted citations.
- Introducing a Table Generator Agent - A post-writer enrichment agent that identifies tabular data opportunities in memo sections and generates markdown tables with overflow anchor linking, configurable column schemas, and firm-specific customization.
- Introducing an Augment Research Writer Agent - Two-phase enrichment: Sonar Pro adds citations to research files, then a writer weaves them into existing prose without rewriting it.
- Introducing an Enrich Visualizations Agent - An enrichment agent that discovers and embeds publicly accessible charts, graphs, diagrams, and infographics from web sources to visually reinforce key claims in investment memos — the automated equivalent of grabbing charts from Google Image search.
- MemoPop Connector API - Ten tools, one step registry, and the docs and tests that ship with each. What we build so a partner’s Claude can write a MemoPop memo.
- Multi-Agent Orchestration for Investment Memo Generation - An exploration into using AI supervisors and specialized agents to generate high-quality content and documents.
- Per-Deal Focal Points - The small ordered list of analyst-supplied bullets that writer agents must treat as load-bearing emphasis, not optional context.
- Portfolio Listing Agent and Current Portfolio Section - Design notes for the portfolio_listing_agent that builds a Current Portfolio subsection and structured JSON for LP-commit emerging manager fund memos.
- Post-Generation Quality Agents - Mini-spec for four agents that run after the main writing pipeline to reduce redundancy, improve formatting, and enhance output quality.
- Reuse and Augment Research Across Runs - Running a deal again should cost only what changed: reuse every settled search and synthesis, and research only what is new.
- Table Generator Agent Specification - Specification for an agent that identifies numerical data in memo sections and source materials, then generates and inserts markdown tables.
- Targeted Legal Scan of Datarooms - Inventory every legal document. Read only the ones that state terms. A checklist is cheap; a model call is not.
- Thesis Frames and the Re-Angle Run - A memo’s angle is currently implicit — it emerges from the deal config, the outline, and whatever research landed, and it can only be changed by editing sections one at a time until they disagree with each other. This makes the frame a first-class object the pipeline holds, and adds a run mode that regenerates only the sections the frame touches, with the frame in every writer call so the sections agree. Grill-me at memo scope rather than section scope.
- Time-Series Analyst — Post-Transcription - The agent that computes. It reads the transcriber’s stated-only CSVs and derives — rolling up, cutting fiscal periods, naming its sources.
- Vision for Production-Grade MemoPop Monorepo - Strategic architecture for github.com/lossless-group/memopop-ai — a multi-app monorepo with Astro marketing site, Svelte web app, and Python agent orchestrator.