AI / Digital twins
Built for professionals whose time is scarce and whose questions carry weight: clinicians, advisers, educators, anyone fielding the same hard conversations on repeat.
Simon's Twin, listening on Didymo.
Try a Didymo conversation: ask his digital twin about PTR's training.
What Didymo is
Didymo answers from the organisation's own approved material, on a phone or in a browser, for the professional whose questions repeat but whose time does not.
WAYS IN
Chat, a voice call, a live avatar on screen and a booked meeting are ways into the same conversation. Each runs on the phone or browser a visitor already has.
Type a question on a phone or in a browser. Didymo answers in text, drawing only on material the organisation has approved.
Explore chat →
Speak instead of typing. A voice call with Didymo, on the phone or in a browser, in the twin's own voice.
Explore voice →
A live face on a phone or laptop screen, for the conversations that need one.
Explore the avatar →
Book real time with the person Didymo represents: a Google Meet appointment, made straight from the conversation.
Explore booking →
Chat, voice and the on-screen avatar all finish with a reply. Booking finishes with a Google Meet in the diary of the person Didymo represents.
No form to fill in and no email thread. The visitor chooses from what is actually free, and the appointment is made where they are already talking.
The meeting is with the person, and Didymo has already carried the context to it, so the conversation starts where the visitor left it rather than at the beginning.
Approved knowledge
Didymo's answers are drawn from the organisation's own approved material, not general knowledge picked up from the open internet. The professional decides what goes in, and what stays out.
Human oversight
The owner reviews what Didymo has said, corrects an answer when it needs correcting, and keeps the approved-source list as the boundary of what the twin may say.
Human handoff
Didymo is built to extend a professional's reach, not replace their judgement. When a question needs a person, the conversation moves to them, with the context already in place.
A visitor picks the way that suits the moment. What sits behind the answer, the approved material and the boundaries around it, does not change with the choice.
A visitor's first message, a harder one later, and the moment an owner checks a new answer before it goes live.
Keeping it current
An owner adds and removes source material as it changes, and Didymo answers from whatever is approved today, not a fixed set from the day it launched.
Before the skin, the mesh
Before a twin has a likeness, it has structure: approved knowledge, boundaries, and the character built around them.
The visitor sees a face on a screen. Behind it is the structure and the knowledge that make the conversation possible.
"AI plays a crucial role here as well, especially now, helping to script and gamify scenarios that provide a more realistic experience. It enables us to craft narratives that adapt in real-time, making the experience progressively more challenging and thus more effective."
Simon Lowe
CEO, People Tech Revolution, on AI inside PTR's scenarios. The Cusp of a Revolution, Global Best Practice Group, October 2024
What a digital twin is, a fully custom build, and where Didymo fits in.
The twin on this page is mounted by a script tag, a custom element and the window events this site's own navigation dispatches, and the developer page shows that markup. Access to the PTR API and SDK is arranged under an enterprise agreement.
NIST guidance on AI risk management and generative AI risks.

The framework behind the approved-knowledge and human-oversight language above.

The generative-AI risk profile behind the "hands off to a person" guidance above.
AI / Digital twins
Built for professionals whose time is scarce and whose questions carry weight: clinicians, advisers, educators, anyone fielding the same hard conversations on repeat.
Try a Didymo conversation: ask his digital twin about PTR's training.
What Didymo is
Didymo answers from the organisation's own approved material, on a phone or in a browser, for the professional whose questions repeat but whose time does not.
WAYS IN
Chat, a voice call, a live avatar on screen and a booked meeting are ways into the same conversation. Each runs on the phone or browser a visitor already has.
Type a question on a phone or in a browser. Didymo answers in text, drawing only on material the organisation has approved.
Explore chat →
Speak instead of typing. A voice call with Didymo, on the phone or in a browser, in the twin's own voice.
Explore voice →
A live face on a phone or laptop screen, for the conversations that need one.
Explore the avatar →
Book real time with the person Didymo represents: a Google Meet appointment, made straight from the conversation.
Explore booking →
Chat, voice and the on-screen avatar all finish with a reply. Booking finishes with a Google Meet in the diary of the person Didymo represents.
No form to fill in and no email thread. The visitor chooses from what is actually free, and the appointment is made where they are already talking.
The meeting is with the person, and Didymo has already carried the context to it, so the conversation starts where the visitor left it rather than at the beginning.
Approved knowledge
Didymo's answers are drawn from the organisation's own approved material, not general knowledge picked up from the open internet. The professional decides what goes in, and what stays out.
Human oversight
The owner reviews what Didymo has said, corrects an answer when it needs correcting, and keeps the approved-source list as the boundary of what the twin may say.
Human handoff
Didymo is built to extend a professional's reach, not replace their judgement. When a question needs a person, the conversation moves to them, with the context already in place.
A visitor picks the way that suits the moment. What sits behind the answer, the approved material and the boundaries around it, does not change with the choice.
A visitor's first message, a harder one later, and the moment an owner checks a new answer before it goes live.
Keeping it current
An owner adds and removes source material as it changes, and Didymo answers from whatever is approved today, not a fixed set from the day it launched.
Before the skin, the mesh
Before a twin has a likeness, it has structure: approved knowledge, boundaries, and the character built around them.
The visitor sees a face on a screen. Behind it is the structure and the knowledge that make the conversation possible.
"AI plays a crucial role here as well, especially now, helping to script and gamify scenarios that provide a more realistic experience. It enables us to craft narratives that adapt in real-time, making the experience progressively more challenging and thus more effective."
Simon Lowe
CEO, People Tech Revolution, on AI inside PTR's scenarios. The Cusp of a Revolution, Global Best Practice Group, October 2024
What a digital twin is, a fully custom build, and where Didymo fits in.
The twin on this page is mounted by a script tag, a custom element and the window events this site's own navigation dispatches, and the developer page shows that markup. Access to the PTR API and SDK is arranged under an enterprise agreement.
NIST guidance on AI risk management and generative AI risks.

The framework behind the approved-knowledge and human-oversight language above.

The generative-AI risk profile behind the "hands off to a person" guidance above.