01 The Gap

Publishers drown in data. They decide in spreadsheets.

Every week, millions of sell-out, stock and trend data points flow into publishing houses. None of it was designed for the people who actually use it: editors, collection heads, marketing leads. They still reach for Excel, Outlook and intuition.

02 Conversational Intelligence

Ask. Get an answer. Decide.

Every question an editor asks, typed as a feature. Pricing, reprint triggers, segment scans, portfolio alerts: each one is a question your teams ask every week, returned as an answer in seconds with sources and confidence levels.

Market Signals

  • Segment Acceleration
    Segments growing above their 6-week trend.
  • Emerging Themes
    Editorial themes rising before the charts.
  • Price Mix Shift
    Price-point glide inside a segment.
  • Segment Saturation
    Structural decelerations, scored 0–100.
  • Concentration Shift
    Publisher concentration tracked via HHI index.
  • Winning Format
    The dominant format in a given genre.

Title Intelligence

  • Breakout Detection
    Titles with velocity above 80/100.
  • Lifecycle Evolution
    Title lifespan per genre.
  • Title Benchmark
    Comparables at the same lifecycle stage.
  • Growth Concentration
    Titles carrying a segment's growth.
  • Frontlist vs backlist
    Frontlist vs backlist contribution.

Publisher Intelligence

  • Publisher Gain
    Publishers gaining share in a segment.
  • Franchise & Author Effect
    Pull of an established author or franchise.

Market Overview

  • Segment Overview
    A segment's full profile.
  • Market Trend
    Fiction evolution over 12 weeks.
03 Forecasting Engine

Three surfaces. One forecasting engine.

Behind every DS Agent answer runs a single prediction engine, tuned for publishing and contextualized per market. It surfaces in three places where editorial decisions actually happen.

04 Comparables Engine

Every new book starts with a question.What does it look like?

Before a cover exists, before a print run is decided, editors already reach for comparables: titles close enough in shape and intent to anchor a forecast. DS Agent turns that reflex into a content-based filtering engine, running on the full metadata graph your data already carries.

01 / Objective

Identify the most similar titles across the market portfolio (same publisher, same group, external) before a single copy ships.

02 / Approach

Content-based filtering on master data and content description. Every field you carry (Thema · BIC · BISAC, publisher ID, collection, pagination, keywords, extract, price) becomes a similarity axis.

03 / Result

A scored ranking of comparables with minimum distance to the new title: the anchor for every downstream forecast.

05 One Interface

Forecasting. Recommendation. Analytical lenses. One interface, one vocabulary.

Three modes of work (predicting a print run, anchoring a new title to its comparables, scanning a segment or a backlist), all accessed the same way: a question typed in plain language, an answer returned in seconds. The editor never leaves the conversation.

  • How many copies should we print?

    How many copies should we print?

    A 52-week print run projection per ISBN, with confidence band and sell-through envelope. Actuals compared to model live.

  • What does this new title look like?

    What does this new title look like?

    A ranked shortlist of comparable books from the market portfolio, scored on genre, theme, audience, price and format, feeding the frontlist model.

  • What's moving in my market right now?

    What's moving in my market right now?

    Segments accelerating or saturating, emerging themes, concentration shifts: 15 lenses, every one accessible by plain-language query.

06 Under The Hood

Simple for the editor. Rigorousunderneath.

  • Your data, ingested

    Weekly feeds, normalized into a single schema, BISAC/Thema-aligned across markets. DS Agent consumes never republishes.

  • Forecast & signal engine

    LangChain-orchestrated models: velocity detection, reprint estimation, segment scoring. Tuned per-market, not a generic LLM.

  • Conversational layer

    Natural-language routing to 15 analytical features, multi-language (FR · EN · DE · ES · IT), ISBN-aware. Every answer traces its sources.

For the first time, we're asking the data the same questions we ask each other at the morning stand-up. And getting answers before the coffee gets cold.

Editorial Director · Early access partner · Fiction catalog · 800+ titles

07 Today, In Production

Shipped. Not a slide.

A fully functional prototype runs today on simulated data. Five markets, five languages, fifteen features. Every element on this page is backed by working software.

  • from question to actionable answer Median round-trip, plain-language query → ranked result 30
  • forecast horizon, per ISBN Rolling weekly projections, all catalog titles 52
  • analytical lenses in the catalog 11 shipped · 15 scoped · one unified vocabulary 15
  • working languages FR · EN · DE · IT · ES · markets covered at launch 5
08 Trajectory

Five phases. One decision surface.

Foundation

Full prototype on simulated data. Experience validated.

1

Unified Search & Title Intelligence

ISBN routing, rich title detail, synthetic chat responses.

2

Frontlist Engine Integration

Pre-launch print run recommendations: confidence, drivers, comparables.

3

Backlist Forecasting & Portfolio Management

1W/1M/1Q/1S/1Y forecast engine + catalog-wide reprint alerting.

4

Recommendation Engine

Content-based filtering on master data feeding the frontlist forecast.

5

09 Delivery Model

The portal is how editors meet DS Agent now. By 2027, we come to them.

The next generation of editorial workflows won't live in dashboards. They'll live inside the AI copilots publishers already use every day. DS Agent ships in two modes from day one: a hosted portal for the 80% who need an experience, and an MCP + REST surface for the 20% with their own AI stack.

Portal

Hosted experience. Your brand, our engine.

Full DS Agent experience: every feature, every screen, zero integration on the publisher side.

White-labeled: partner brand, partner URL, partner auth.

Ship in weeks: the default path for 80% of publishers.

Native

DS Agent as a capability, not a destination. Inside the copilot the editor already uses.

MCP server + REST API: zero UI to build. The copilot calls DS Agent like any other tool.

Lives inside their workflow: Claude, ChatGPT Enterprise, Copilot, Glean, custom stacks.

Same engine, same vocabulary: forecasts, comparables, lenses. Delivered where editors already think.

Three layers. Clear boundaries.

  • 1.

    Publisher's AI Copilot

    What their editors already use

    Claude · ChatGPT · Copilot · Glean · custom

  • 2.

    DS Agent MCP Server

    Our engine exposed as a capability

    forecasts · comparables · lenses · portfolio

  • 3.

    Market data providers

    Your data, governed by your contract

    Circana · NielsenIQ · MediaControl · Emmelibrì

See the full suite in 30 minutes.

Personalised demo

Request a demo