
Reading highlight retention and knowledge graph console
Reduce the effort of turning scattered highlights into reviewed, connected and retained knowledge.
- For
- Researchers, students and knowledge workers who read across books, articles and video and need to retain and connect what they capture
- Solves
- Highlights and notes scatter across reading apps and media, so captured material is rarely revisited, connected or turned into durable understanding.
- Delivers
- A reviewed, searchable knowledge library with scheduled review prompts
- Built in
- about 5 weeks of creation time, MVP in 6 days
- Investment
- $12,500 for the MVP, $42,500 for the full product
- Run it
- Inside your business, or as part of your offer to clients
What it does
Reduce the effort of turning scattered highlights into reviewed, connected and retained knowledge.
- Import highlights from Kindle books, web articles and YouTube transcripts.
- Summarize long passages and online content into concise notes.
- Mark and annotate important sections for later reference.
- Search highlights by meaning and context, not only keywords.
- Schedule spaced-repetition review prompts.
- Send a daily review email of selected highlights.
- Show a knowledge feed that resurfaces saved material.
- Build a knowledge graph that connects related concepts and entities.
- Resurface content on a schedule matched to the user's learning curve.
- Link notes and cards manually to strengthen connections.
- Discover relationships between new and previously saved content.
- Adjust reading speed and font settings.
- Import and export common document formats.
- Show contextual definitions for complex terms.
- Compare the reviewed library against the recorded baseline and value assumptions.
- Capture corrections and named-owner approval before consequential use.
- Export a versioned reviewed knowledge library with source references and unresolved questions.
Everything these tools do, in one app
- Highlight Import Import highlights from various sources such as Kindle books, web articles, and YouTube transcripts.Found in Screvi
- Text Summarization Condense lengthy passages or diverse online content into concise summaries.Found in 2Read, Active Recall
- Highlighting and Annotation Mark important sections of text for future reference.Found in 2Read
- AI Semantic Search Quickly locate specific highlights using intelligent search that recognizes context and meaning.Found in Screvi
- Spaced Repetition Receive timely review prompts to reinforce memory retention.Found in Screvi
- Daily Review Get a daily email of selected highlights to keep learnings fresh.Found in Screvi
- Knowledge Feed A feed that encourages revisiting highlights to reinforce retention.Found in Screvi
- Knowledge Graph Automatically connect related concepts, entities, and content pieces without manual effort.Found in Active Recall
- Personalized Resurfacing Schedule Resurface content on a schedule tailored to the user’s learning curve.Found in Active Recall
- Manual Linking Manually link notes and content cards to strengthen connections within the knowledge graph.Found in Active Recall
- Relationship Discovery Discover relationships between new and previously saved content to enhance contextual understanding.Found in Active Recall
- Customizable Reading Modes Adjust reading speed and font settings to suit preferences.Found in 2Read
- Document Format Integration Import and export various document formats for easy use.Found in 2Read
- Contextual Definitions Provide definitions and explanations to aid comprehension of complex terms.Found in 2Read
What goes in, what comes out
- Imported highlights
- Transcripts
- Notes
- Reading preferences
AI drafts, people review. Searchable structured library and data stewardship console.
- A reviewed
- Searchable knowledge library with scheduled review prompts
How it works
The workflow
- InStart with
Imported highlights, transcripts, notes and reading preferences
- 1
Confirm the buyer's problem and scope
- 2
Collect imported highlights
- 3
Transcripts
- 4
Notes and reading preferences
- 5
Then follow this sequence: 1
- OutFinish with
A reviewed, searchable knowledge library with scheduled review prompts
AI does the heavy lifting, people stay in charge
Use AI to interpret permitted inputs, suggest structured mappings and generate candidate outputs for the three stated task modules. Use deterministic code for arithmetic, schema validation, hard constraints and reproducible tests. Review source-linked explanations and uncertainty before accepting results. One fixed import format set and licensed source access; final accuracy and citation checks remain editorial. A model suggestion is never a verified fact, professional decision or authorization to act.
What your team sees
Primary screens: Import and source setup, Library and knowledge graph, Review and retention. Use a source list for connected reading and media, a central library canvas with semantic search and filters, and a right-hand panel for definitions, links and review state. Let users compare a highlight against its source passage and linked concepts. Display imported, summarized, linked and reviewed states. Provide a daily review view with scheduled prompts and a knowledge feed. Make the task-specific outcome a reviewed, searchable knowledge library with scheduled review prompts visible beside its evidence, review state and value baseline.
Accounts and administration
Project ownership, source versions, user comments, approval states, usage allowances, revision limits, export history and a rights record for supplied material. Add organization access boundaries, named reviewers, usage caps, data retention controls, export logs and explicit approval for external actions.
Integrations and data access
Reader-owned highlights, authorized transcripts and permitted research sources. Cloud storage, document import/export and reading or note destinations. Start with file exchange and validate destination specifications before promising direct sync. Start with authorized file exchange. Validate current provider access, usage rights and schema behavior before promising a connector.
How we build it
We build with our own AI software development factory, so most implementations take days to a few weeks of creation time, not months. You see working software at every step, and exact timing depends on availability.
- 1
Scoping call
Day 1Thirty minutes on your process, your data and how you want to run it: for your own team, or for your clients. You get a fixed scope and price for the MVP.
- 2
MVP
6 daysOne buyer segment, one recurring use case; first modules: import highlights from Kindle books, web articles and YouTube transcripts; summarize long passages and online content into concise notes. Manual review in the loop. Built by our AI software factory.
- 3
Paid pilot
7 daysAccounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.
- 4
Full product
3 weeksSelf-serve onboarding, billing, monitoring and the wider integration set.
- 5
Run and improve
MonthlyWe host, monitor and improve it for a fixed monthly fee, or hand it over to your team. How the retainer works.
Why we start with an MVP
An MVP, or minimum viable product, is the smallest version that your users can actually work with. It is not a cheap version of the full solution. It is a test, built to answer the questions that decide whether the rest is worth building.
- Pick the riskiest assumption. Here: will researchers, students and knowledge workers who read across books, articles and video and need to retain and connect what they capture use it to solve "highlights and notes scatter across reading apps and media, so captured material is rarely revisited, connected or turned into durable understanding"?
- Build only what tests it. One team, one use case, a few core modules. People do the rest by hand for now.
- Run a paid pilot. Agree quality and outcome thresholds before the pilot using this measure: Highlights reviewed per week and retained-understanding checks on held-out material.
- Measure, then decide. Track highlights reviewed per week and retained-understanding checks on held-out material; accepted-output rate; material error rate; reviewer correction time; actual repeat purchase. Then expand, change course or stop, with evidence instead of opinions.
MVP scope for this solution. Pilot scope: One fixed import format set and licensed source access; final accuracy and citation checks remain editorial. Implement one approved input format, a bounded representative case set and the first two task modules: import highlights from Kindle books, web articles and YouTube transcripts; summarize long passages and online content into concise notes. Support the third module with operator review: mark and annotate important sections for later reference. Include source references, corrections, basic organization access, approval states, export and value measurement. Use managed operator assistance for unresolved exceptions. The cost estimate covers this narrow prototype, not unrestricted multi-tenant scale, complex production integrations, specialist certification or physical operations.
After the MVP. Once paid pilots prove usefulness, automate repeatable reviewed steps and add one verified source integration. Expand supported inputs and case volume only after new evaluation cases pass. Build reusable customer configurations and recurring value reports around the reviewed knowledge library with scheduled review prompts. Retain the explicit scope boundary: One fixed import format set and licensed source access; final accuracy and citation checks remain editorial.
What the build depends on. Highlight upload and preview, asynchronous processing jobs, editable version history, reviewer access and tested export formats. High-fidelity retention requires specialist learning QA. Obtain representative authorized cases, baseline measurements, qualified reviewers and a buyer-side decision owner. Specific limitation: One fixed import format set and licensed source access; final accuracy and citation checks remain editorial.
Investment
A planning range to start the conversation, not a quote. You pay per phase, so you can stop after the MVP.
- Phase 1
MVP
One buyer segment, one recurring use case; first modules: import highlights from Kindle books, web articles and YouTube transcripts; summarize long passages and online content into concise notes. Manual review in the loop.
- Phase 2
Paid pilot
Accounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.
- Phase 3
Full product
Self-serve onboarding, billing, monitoring and the wider integration set.
Indicative total, MVP to full product$42,500about 5 weeks of creation time · start with the MVP from $12,500
Running costs per month
A rough indication of monthly hosting and AI model costs once it is live, not tested. Real costs depend on usage, file sizes and the models chosen.
| Stage | Hosting and infrastructure | AI usage | Total per month |
|---|---|---|---|
| MVP and paid pilotabout 3 customers | $30–$60 | $50–$100 | $80–$160 |
| Full productabout 50 customers | $110–$210 | $350–$700 | $460–$910 |
Run it or resell it
For your own team
Researchers, students and knowledge workers who read across books, articles and video and need to retain and connect what they capture run it inside the business: imported highlights, transcripts, notes and reading preferences in, a reviewed, searchable knowledge library with scheduled review prompts out, reviewed by your people.
As part of your offer
Agencies, consultancies and software companies can offer it to their own clients under their brand. We build and maintain it; you sell and deliver it.
Your brand, or this one
Run it under your own brand, or start from this concept style.
- primary
#912745 - accent
#54c9bc - surface
#f1e4e8 - ink
#22201e
- Headings
- Libre Baskerville
- Text
- IBM Plex Sans
- Voice
- Rigorous, transparent, cited
Selling it to your own clients: the go-to-market playbook
Pricing to test
Test a USD 300-1,500 fixed pilot for one defined reading and media package. Offer a monthly production allowance after repeat demand. Quote complex multi-source or specialist research workflows separately. These are test prices, not market benchmarks. Package the initial sale as one bounded reviewed knowledge library with scheduled review prompts. Recurring fees must specify volume, review depth and integration support. For exchanges, test a disclosed coordination or successful-service fee rather than holding customer funds. Reprice only after measuring real delivery labor; platform-build cost is separate from a commercial pilot fee.
Message to test
Reduce the effort of turning scattered highlights into reviewed, connected and retained knowledge. Demonstrate a concrete reviewed knowledge library with scheduled review prompts using the buyer's approved example and show the baseline, corrections and actual delivery effort.
Where to find buyers
Researchers, students and knowledge workers who read across books, articles and video professional communities; specialist consultants serving this buyer; permissioned partner introductions; practical demonstrations at relevant trade or practitioner events.
Lead magnet
A reviewed sample knowledge library with scheduled review prompts from a small authorized input set, with a transparent calculation of highlights reviewed per week and retained-understanding checks on held-out material and no promised savings.
The first 30 days
- Week 1: interview five researchers, students and knowledge workers who read across books, articles and video and inspect a recent example of highlights and notes scattered across reading apps and media, so captured material is rarely revisited, connected or turned into durable understanding.
- Week 2: prepare a consented or synthetic demonstration of the three task modules.
- Week 3: seek one bounded paid pilot with agreed baseline and acceptance criteria.
- Week 4: measure highlights reviewed per week and retained-understanding checks on held-out material, reviewer effort and repeat-purchase interest. This is a demand-validation plan, not a thirty-day full-product delivery promise.
Paid pilot
Agree quality and outcome thresholds before the pilot using this measure: Highlights reviewed per week and retained-understanding checks on held-out material. Continue only if the buyer accepts the actual output, the intended job outcome improves without unacceptable errors, and measured delivery cost fits willingness to pay. Revise or stop if access is unavailable, qualified review cannot be provided, or apparent savings disappear after corrections and support. Use held-out cases when comparing model quality; use a properly reviewed comparison design before making causal claims. Record missing cases and negative results alongside successful outputs.
Success metrics
Highlights reviewed per week and retained-understanding checks on held-out material; accepted-output rate; material error rate; reviewer correction time; actual repeat purchase.
Retention and expansion
Repeat the workflow when the buyer again needs a reviewed knowledge library with scheduled review prompts. Retain permissioned settings and reviewed examples, report realized value honestly, and sell increased volume or adjacent approved workflows only after contribution margin and quality remain acceptable.
Why clients would pick it
A reusable library of approved import formats, linking rules and review examples, together with reliable delivery for a narrow research niche. Build a permissioned library of representative task cases, reviewer corrections and verified operating constraints for researchers, students and knowledge workers who read across books, articles and video. Repeatable delivery and useful integrations matter more than access to a base model.
Alternatives and positioning
Screvi, 2Read and Active Recall, plus manual note files and generic reading apps. Compare this product with the buyer's present method on highlights reviewed per week and retained-understanding checks on held-out material. Offer a bounded paid workflow instead of claiming broad autonomous expertise. Market uniqueness and competitor coverage are not verified.
Main delivery costs
Import and processing attempts, transcript and document handling, storage, reviewer hours, user revision rounds and licensed source material. Additional initial validation requires representative authorized sample preparation, buyer interviews, buyer-side evaluation and bounded validation of the reviewed knowledge library with scheduled review prompts. Track cost per accepted output, including correction work, unsuccessful cases and support.
Safeguards
Preserve source attribution, quotation accuracy and usage permissions. Users approve substantive changes and publication scope. One fixed import format set and licensed source access; final accuracy and citation checks remain editorial. Keep all consequential actions under authorized human control and do not fabricate missing inputs, permissions, professional judgments or market evidence.