Selected work: entrepreneurial R&D project Since August 2024

The work moves forward. The state of the project should move with it.

Private Twin brings expected work close to observed execution, to rebuild a current state that is sourced and correctable: what changed, which decisions were made, who carries the next step, what is blocked, and which deadlines are about to slip. It does this without constant chasing or extra reporting.

Built Advanced full-stack prototype
Built Operational Sim Lab (traces and simulations)
In progress Product and market validation under way
Private Twin screenshot: the timeline of a reconstructed working day, time attributed to projects, detected meetings, and unattributed periods still visible Inspect
Prototype · reconstructed timeline

From the day’s traces, Private Twin rebuilds a timeline of the work and attributes it to the relevant projects. Periods that remain uncertain stay visible as such.

Prototype screenshot
01
The lived
problem
Immediate value

Picture several people and several agents working in parallel on the same files. A decision is made in a meeting, an agent takes an action, a deadline moves inside a tool, a trade-off arrives by email. Yet no shared representation of the work is updated. Everyone acts on a partial version of the situation.

The problem is no longer only finding information. It is knowing what is true right now, what has been done, what is still expected, who carries the next step, and what an agent may commit to without a fresh human check.

01 Where does this project stand?
02 What has changed recently?
03 What did we decide?
04 Which actions are still open?
05 Which risks or blockers need watching?
06 How much time did this project actually take?
Prototype · interactions across a day

Private Twin rebuilds the thread of the day and connects the events that belong to the same sequences of work.

Prototype screenshot

Private Twin screenshot: the thread of a day, events split by source, and reconstructed links between those belonging to the same sequences of work Inspect
02
Vision
Medium- and long-term vision, not an available feature

From the pyramid to the value-creation network

AI does not only change how tasks get done. It can also change how an organisation coordinates itself.

Today, a large share of intermediate work goes into searching for information, rebuilding the state of projects, preparing readouts and multiplying synchronisation meetings. When people and agents share a common context that is explainable and current, part of that coordination can be carried by the system.

REPORTING CONSIGNES

Pyramid organisation

Information travels up through reporting; decisions and instructions travel back down through the layers.

Shared context

Explainable and governed: access rights, traced decisions, checkpoints.

Network of people and agents

Connected around projects, skills, dependencies and value-creation flows. Useful context circulates without crossing every layer.

Conceptual representation, not a product screenshot ○ person  ·  ▢ agent  ·  ◇ project

The project starts by rebuilding the thread of one person’s work and the state of their projects. In the medium term, those validated and governed contexts could let colleagues, managers and agents share what they need without multiplying status requests, reporting and coordination meetings.

The system can absorb part of the information searching, the state rebuilding and the reporting. A manager’s role then shifts from collecting and relaying information towards arbitration, supporting teams, and owning decisions.

Guardrail

Automate the mechanics of coordination without surveilling people or replacing human accountability.

03
From problem
to prototype

Six steps, from research to the field

The project did not start with development. It started with a problem I experienced as a manager.

01

Explore the problem

Reading the research on agentic AI and cognitive science, particularly human attention and the effects of fragmented work.

Research
02

Frame the idea

Private Twin answers first a problem I run into myself as a manager: steering several projects involving many people, while information, decisions and actions stay scattered. In that situation, reliable and current visibility becomes critical to coordinate teams and anticipate risk.

Lived problem
03

Test the initial interest

Calls and video conversations with about ten people, to test the problem against their own day-to-day and check whether the subject held.

Field
04

Build

More than a year building a complete prototype and an AI-assisted development method. I also built a harness, the technical frame that runs, checks and evaluates the agents. It is designed to keep language-model calls to the strict minimum and avoid dependence on a single provider.

Build
over a year
05

Monitor and evaluate

Creating Sim Lab to keep a complete trace of every run, follow how responsibility is delegated between the human and the agents, replay scenarios and catch regressions. An agent’s flow is drawn like a production line: every trace becomes a checkpoint.

Build
06

Deepen market validation In progress

The phase currently under way, across four families of knowledge workers: twenty interviews in total, comparing how intense the problem is, how acceptable capture feels and what follow-up actually happens. A survey will only be used if a specific question later needs sizing.

Field
04
What the
prototype holds

Reliable context, for people and for agents

Assistants, agents and the people working with them need a reliable execution state. Private Twin maintains that state so they can act without losing context, evidence or control.

The prototype rests today on six complementary building blocks:

01 Local capture of authorised traces A local application that collects only the work traces it has been allowed to collect.
02 Attachment to the right projects An engine that links activity, meetings, communications and files to the right projects.
03 Context base It connects people, clients, projects, decisions and actions.
04 Timesheet, daily readout and next actions Three operational outputs proposed from observed work: accounting for the effort, understanding what changed, and keeping commitments visible.
05 Human validation Confirming or correcting the results stays in the user’s hands.
06 Sim Lab Monitoring and evaluation of the system. See Sim Lab
Private Twin screenshot: a proposed narrative memory, flagged as a decision and reviewed, attached to a client and a stakeholder, with its sources and the correct or archive actions Inspect
Prototype · sourced narrative memory

A memory proposed from work traces, linked to the right people and carrying its sources. Validation stays with the user.

Screenshot of a conversation: the Private Twin connector is queried from ChatGPT and describes structured access to the work history Inspect
Connector · queried from ChatGPT

The Private Twin connector makes the structured history of the work queryable from ChatGPT.

05
Technical
evidence
Sim Lab: monitoring and evaluation

Checking that an agent behaves as intended

An agent that convinces over a handful of tries is not necessarily reliable over time. Sim Lab freezes a working day, replays it and compares versions.

Sim Lab can take a World snapshot: a complete, frozen photograph of a working day and of the system state at that moment. That World can then be duplicated to test several versions under exactly the same conditions, without touching the original day.

As on a production line, every step is a checkpoint. When a result degrades, Sim Lab helps pinpoint where and why the behaviour changed.

Conceptual diagram: production line and checkpoints

Snapshot

A day and the system state, frozen.

Duplication

The original World stays untouched.

Replay

Same scenarios, same conditions.

Comparison

Code, configuration, prompts or models.

Divergence

The first point where behaviour degrades.

Sim Lab screenshot: an exclusion step filters the traces. Those kept move on to extraction; the others are excluded with a stated reason, such as outbound, automated or commercial domain. Inspect
Sim Lab · a controlled trace flow

In Sim Lab, every trace crosses checkpoints: what was kept, what was excluded and why all stay observable.

Prototype screenshot, extract of a flow

06
People and
data

Keeping people and data under control

Three design principles, stated without promising anything beyond what is actually implemented.

01

Local-first by default

Work data and its context stay local by default. When an external model is used, what is sent is limited to what is necessary.

02

Deterministic first

Classic, deterministic processing is preferred wherever generative AI adds nothing. Language-model calls are reserved for the steps that need them, with the option to switch provider.

03

Proposals, not verdicts

What the system produces stays a proposal: the user can verify it, correct it or reject it. The point is to make work visible and understandable, never to score or monitor people.

07
Current
status

An advanced prototype, still being tested against the field

Built
A complete prototype that collects, links and interprets different work traces.
An architecture designed to preserve context, sources and human validation.
A harness that limits dependence on language models and their providers.
An operating Sim Lab for monitoring, replay and version comparison.
Validation under way
Evaluating the results across more days and more real situations.
Improving the features before switching them on for users.
Identifying the client profiles who feel the problem most sharply.
Validating usage, adoption and the value actually created.

Private Twin is presented as an advanced prototype under validation, not as a product whose market is already established.

A complete approach, not just a technical build

01 Start from a lived problem and take it to other users.
02 Turn research into hypotheses, then into design decisions.
03 Build a complete agentic product and its architecture.
04 Structure a method for AI-assisted development.
05 Design the harness needed for monitoring and evaluation.
06 Build in confidentiality, traceability and human accountability from the start.
07 Build a value proposition, then take it to market.