Fernão: The Personal AI Redefining Task Management

Improvement of the Calendar Function

In the ongoing effort to improve Fernão, a personal AI assistant, significant changes were made to the calendar function. Initially, Fernão used the ICS format to retrieve calendar events, but this method proved inefficient. The ICS format does not allow native filtering of events, which forced Fernão to download the user's entire schedule just to extract a few relevant meetings. It was like bringing home an entire library just to look up a single sentence in a book.

To solve this problem, other options were explored: Google offers calendar access through an API that allows native event filtering. Thanks to this API, Fernão now retrieves only the events it actually needs. This improvement has greatly cut the schedule generation time, from nearly five minutes to about twenty seconds. With this new pipeline in place, the surrounding logic was also refactored to make the whole function cleaner and faster.

An example of how Fernão now retrieves calendar events through the API:

def get_events_for_date(target_date=None, use_api=True):
    # Retrieves events for a specific date from Google Calendar.
    # First tries the API (if use_api=True), falls back to ICS if the API fails.
    target_date: datetime.date object for the target day. If None, uses today.
    use_api: If True, first tries the Google Calendar API. If False, uses only ICS.
    # List of dictionaries of events.

New Features

In addition to the technical improvements, new features have been added to Fernão. Now, in the calendar view, the user can mark tasks as complete, and they are automatically synced with the Microsoft To-Do app. This integration simplifies task management and could foreshadow a trend in which users build their own personal operating systems by integrating various tools.

That suggests that over time, many people will end up building their own "personal operating systems," assembling workflows from their favorite tools, integrating what they need and swapping out components whenever better options appear. If features become easy to replicate, loyalty to specific platforms will weaken.

This also raises an interesting question: will companies eventually try to lock down their systems by restricting APIs and external integrations? It is possible. But shutting themselves off is unlikely in the long run. If users cannot connect tools to their own workflows, they will simply go elsewhere (… and will this behavior be limited to advanced users?).

With this new capability in the Schedule Maker, another feature was implemented for Fernão.

Introduction: the Task Decomposer

Fernão's new role is to decompose tasks. The Task Decomposer follows a simple workflow:

• Start with a large generic task in Microsoft To Do;
• Add context on how the task should be broken down;
• Fernão decomposes the task and builds a plan;
• The resulting tasks are saved in To-Do with due dates and later appear in the daily assistant.

How the Task Decomposer appears in the sidebar:

Task Decomposer Module

Take a concrete example. One of the biggest tasks on the To Do list is "Project Documentation at DareData." This is not a small operational task; it is a structural project.

The goal is to consolidate and formalize the company's internal knowledge in Notion, making sure the key questions about the company are clearly answered in the Knowledge Hub. This means going through each department, identifying gaps, creating or refining pages, structuring the information properly and assigning clear ownership for each section.

In practice, this requires audits, writing and governance decisions. It is not something that gets "just done" in one go: the goal is to finish it within three weeks, realistically devoting between 30 minutes and an hour a day.

This is exactly the kind of task that benefits from decomposition. Some contextual information is fed into the Task Decomposer to turn this giga-task into an action plan:

• The Knowledge Hub is currently being built in Notion. Here’s the current structure of Notion and departments:

  Network Members Manual

  [DareData Network Members Manual]

  Sales & Partnerships

  Marketing (Brand and Gen-OS)

  [Technical Specialists] [Account Managers]

• Review each department and create the pages that make sense (search the web for more context on what DareData is if you need ideas on pages to create for each department or use your knowledge of what absolutely needs to be documented in a 130-person B2B company).

• Ensure that each page has an Owner.

• Review the suggestions recorded by the team in the suggestions, at a rate of one or two each day.

• Add some departments that are missing: Administration, Key Members, Finance, Product.

After clicking "decompose," Fernão will start forging:

Fernão Forging the Task

The generated tasks and plan can now be reviewed and submitted to Microsoft To-Do. It is also necessary to assign the Microsoft To-Do list they will go to:

Destination List in Microsoft To-Do

Adjustments and Improvements

Testing reveals two adjustments to make.

• First, Fernão is supposed to be a medieval chronicler, not a fantasy warrior, so the forge design will be changed. His clothing should have a medieval look.

• Second, on a more practical note, a "Submit All" button is needed. Submitting tasks one by one is tedious, especially when breaking down larger projects.

How this looks in the Microsoft app:

Submit New Tasks in To-Do

The emoji will probably be removed. This kind of "emojification" is very typical of LLM-generated front-end code.

Here is the current prompt used for task decomposition. It will continue to be refined through further testing and observation of how it performs in real use cases.

name: task_breakdown
description: Break down a task into actionable sub-tasks of 20 minutes
max_tokens: 4096

You are a productivity expert helping to break down complex tasks into manageable...