01Digital twin
A digital twin, its wiki-LLM memory, and WhatsApp as the command center
Every person (and the company itself) gets a digital twin. Its memory isn't a raw chat log: it's a living wiki, rewritten by the model — Andrej Karpathy's "LLM as an operating system" idea, applied to your business. Linked to its owner's WhatsApp, the twin becomes their command center: you text it, it orchestrates the agents and comes back with the result.
Under the hood- WhatsApp paired with each team member's number: the twin receives requests there, delegates them to agents, asks for approvals and delivers files in the conversation.
- Memory structured as knowledge pages (people, accounts, projects, decisions), not a pile of logs.
- The model re-reads, corrects and merges its own notes: memory stays dense and current instead of bloating.
- Targeted retrieval: for each task, only the relevant pages enter the context.
In plain termsYour agents know your context on the first try — clients, history, your way of doing things — without you re-explaining everything. And everyone runs their team of agents from WhatsApp, no app to open.
02Execution memory
Each agent has its own working memory
Beyond the shared company memory, each agent keeps an execution memory: what it tried, what worked, the preferences it learned on its recurring tasks.
Under the hood- Episodic trace per run: goal, steps, tools called, result and human approval.
- Successful patterns become habits; failures become guardrails.
- Isolated per agent: sales doesn't inherit support's reflexes, and vice versa.
In plain termsAn agent that improves with use: the second follow-up, the tenth quote, the hundredth support reply are faster and sharper than the first.
03Nightly dreams
At night, the agents dream
When no one is working, the agents don't really sleep. They replay the days, explore leads and prepare the ground — an offline "replay", without eating into your working hours.
Under the hood- Replay of past tasks to extract reusable lessons.
- Forward exploration: drafts, monitoring, hypotheses prepared for the next day.
- Asynchronous work: heavy processing runs outside office hours.
In plain termsYou start the day with work already cleared: leads prepared, drafts ready, attention points surfaced.
04Consolidation
Nightly consolidation of the company brain
Just as a brain consolidates memories during sleep, Bruno consolidates your company brain every night: the day's scattered traces are sorted, linked and integrated into long-term memory.
Under the hood- Agents' execution memories are summarised and promoted to the company wiki.
- Deduplication and linking: scattered facts become connected knowledge.
- What matters is reinforced, noise fades: memory gains signal, not volume.
In plain termsYour company's knowledge stops leaving with people or getting lost in threads: it accumulates, connects and stays available.
05Orchestration
The agents talk to each other
A lone agent plateaus fast. The value appears when they collaborate: sales asks for research, the writer pulls the data, the twin arbitrates — under your approval at key points.
Under the hood- Internal exchange protocol: an agent can delegate a sub-task to another.
- Orchestration by the twin: it routes the request to the right roles and recomposes the result.
- Human checkpoints: you approve the steps that commit the company.
In plain termsYou hand over a goal, not a list of micro-tasks: the agent team coordinates to deliver it.
GPT-4o€0.012
Claude€0.008
Mistral€0.002