Revive takes a body of work and lets you speak with it. The work can be books, letters, notebooks, poems, or a full course catalog. The author's beliefs are in that text too, so each mind can take a side in an argument and hold it. Eight of these minds speak with each other now. It is a thought experiment that runs in production today.
A published work is not active
Most work becomes silent after publication. A book stays closed on a shelf. A notebook stays behind glass. A recorded lesson stays in a folder. The author's knowledge is in these pages. But the text gives the same words to each reader, in the same sequence. You must know the correct page before the work can help you.
Revive makes the work answer
Revive connects your question to the correct pages. You can ask Franklin's Autobiography a question. Leonardo's notebooks give answers. Dickinson's poems supply the correct verse for the moment. A living teacher's recorded lessons become lessons that do not stop. An AI model writes each answer from those pages, and a second model checks it against them.
“What an astonishing thing a book is. But one glance at it, and you're inside the mind of another person.”Carl Sagan · Cosmos, ep. 11
A new way to read
Archives keep the works safe, and search tools find them. Revive lets a reader ask them questions. It can also connect two bodies of work, so Cosmos can speak with the Notebooks, and Poor Richard with the collected poems. When two texts disagree, their answers disagree too.
The usual method: imitation
Most persona chatbots imitate a style. The voice sounds almost correct, but the model invents the beliefs as it speaks. Ask an ungrounded Franklin about social media, and you get a generic lecture. The lecture contains nothing that Franklin wrote. These personas also invent quotations, and they agree with almost everything. For education and research, a persona that invents quotations is worse than no persona.
The Revive method: grounding
Each answer from a Revive persona comes from the person's own words. The system searches their books, letters, transcripts, and poems, and it quotes them. Franklin's own letters give Franklin's voice. A biography about Franklin gives a biographer's voice. Each mind also carries a structured worldview. The worldview records what the person believed about wealth, truth, science, and love. When two minds meet, they can disagree, because their sources disagree.
The core ideaA grounded persona answers only from the author's own text, so you can check each answer against that text.
Every answer in the Revive app shows its Revive Score. A second model checks each claim against the pages. A passing answer shows from 95 to 100, and Revive hides an answer that fails. The Franklin answer on this page is a real answer from the app, with its real score. The “Franklin” costume quotation is invented, to show an ungrounded persona. See how an answer is checked.
Eight minds are active, one is ready
Each persona comes from one body of primary sources. The sources are the person's own words, indexed and searchable. Each portrait starts as the mind's own words, then the face comes through.
| Mind | Who | Sources |
| Gabriella 2.0 | Spiritual teacher & consciousness guide | 430 chunks, from her session & book-chapter transcripts |
| Benjamin Franklin | Polymath, statesman, self-made philosopher | 173 chunks, from the Autobiography & Poor Richard's Almanack |
| Leonardo da Vinci | Renaissance polymath, writing from Clos Lucé, 1515 | 1,634 chunks, from Richter's edition of the Notebooks |
| Carl Sagan | Astronomer & science communicator | 402 chunks, from Cosmos & 13 TV episode transcripts |
| Decode | Critical analyst of the digital attention economy | 46,912 chunks, from 83 courses, 1,030 papers & 815 case studies |
| Emily Dickinson | Poet · a curator, not a character | 629 poems, from 629 complete poems, indexed whole |
| Sir David Attenborough | Naturalist & broadcaster | 1,170 chunks, from 626,467 words across 20 documentary sources |
| Walter Russell | Painter, sculptor & mystic natural philosopher | 1,371 chunks, from nine books & the 12-unit Home Study Course |
| Mark Twain | Fully indexed, not yet live | 6,575 passages ready: the next mind to go live |
Meet each mind in full →
For the living
The work can also be your own. You can publish your body of work as something people can speak with.
Two of the eight minds show this today
Gabriella 2.0 comes from a living teacher. Her recorded sessions and book chapters became a persona that teaches her material. A tuned voice model reads her grounded answers aloud. She can hold a thousand conversations while the teacher sleeps. Decode is not a person. It is a curriculum of 83 courses and a research library with an analyst's voice.
This is for people who make things
This front end can carry an author's books, a teacher's course catalog, a researcher's papers, or ten years of blog posts. The persona answers with your words, cites your pages, and disagrees where you disagree. You stay the author, and the persona is an interface to the work you made. Readers can ask it questions instead of reading the full text in sequence.
Bring a corpus
We can take your folder of text to a running persona with you. Developer partners get the full build. Work with us →
Four plain steps
- Gather the words. Collect the body of work. It can contain books, letters, lectures, poems, courses, or transcripts. The material can be old or new. The persona gets its ideas only from this material.
- Index the words for search. The system divides the words into short passages and indexes each one. For each question, it can then find the most applicable passages quickly.
- Record what they believed. We read the sources closely. We record each mind's positions on wealth, truth, science, and love. The persona then holds positions, and it can disagree.
- Let them speak. You ask a question. The persona finds the passages that apply and answers with them. In a group conversation, it agrees or disagrees as its sources tell it.
- Source material. All the words the person wrote or said.
- Chunk & embed. The text is divided into passages and stored as searchable vectors.
- Vector search. Your question finds the passages that apply to it.
- Grounded reply. An answer in the persona's voice, with its sources.