What Is Favoriot?
When people first hear “Favoriot,” the first thing they usually ask me is:
“So… is it an IoT platform?”
Yes.
But that answer is too shallow. It has now evolved into an AIoT platform.
Favoriot is not just a place to collect sensor data or draw dashboards. Favoriot is built to help people make decisions from real-world data and act on them.
That difference matters more than most people realise.
To explain this properly, I usually walk through how Favoriot works from the very beginning, not from the dashboard, but from intent.
Step 1: Start With the Real Question (Not the Sensor)
Most IoT projects begin like this:
“We have sensors. Let’s collect data.”
I used to think that was fine. Then I saw too many projects fail quietly.
In Favoriot, we begin with a simple but uncomfortable question:
Why are we collecting this data at all?
This is called Intent & Context Definition in the Favoriot Insight Framework.
Before installing a single sensor, we clarify:
- What decision are we trying to improve?
- What does “normal” look like?
- What risk truly matters?
- What should happen when things go wrong?
Without this step, data turns into noise, and dashboards multiply for no reason.
Intent gives meaning to everything that comes next.
This idea is clearly explained in the Favoriot Insight Framework document.
Step 2: Capture Reality, Not Assumptions
Once the intent is clear, Favoriot moves to building a data foundation.
This is the part most people expect from an IoT platform, and yes, Favoriot does this well:
- Sensors and devices send telemetry data
- Data flows through standard IoT protocols
- Everything is stored securely as time-series data
Favoriot manages:
- Device onboarding
- Data ingestion
- Secure storage
- Data consistency over time
I often tell people this:
“If you don’t trust the data, you won’t trust the insight.”
That’s why this layer exists. No shortcuts.
Step 3: See What Is Happening
Now we reach the familiar territory: dashboards.
Favoriot provides descriptive insights using Favoriot Analytics:
- Charts and visualisations
- Min, max, average values
- Trends over time
- Seasonal and pattern breakdowns
This answers questions like:
- What is the current status?
- How did things change over time?
- Are values within expected ranges?
This layer gives visibility.
Nothing more, nothing less.
And that honesty is essential.
At this stage, Favoriot is not guessing, predicting, or recommending anything yet.
Step 4: Understand Why It Happened
This is where many platforms stop. Favoriot doesn’t.
Next comes diagnostic insights, where Favoriot starts connecting the dots.
Here, multiple data streams are analysed together:
- Sensor A compared with Sensor B
- Current behaviour compared with historical patterns
- Relationships and unusual deviations identified
This layer answers:
- Why did this change occur?
- Why do these parameters move together?
- Is this behaviour unusual for this context?
I like to think of this step as moving from “What just happened?” to
“Oh… now I get it.”
This is where understanding begins.
Step 5: Anticipate What Comes Next
Once you understand the past and the present, the next natural question is:
“What’s likely to happen if nothing changes?”
This is predictive insights, powered by Favoriot Intelligence.
Favoriot learns from historical IoT data to:
- Forecast future values
- Estimate trends
- Highlight growing risks
Typical questions answered here:
- Will this parameter cross a limit soon?
- Is the system drifting toward failure?
- What should we expect next week or next month?
This layer creates foresight.
Not certainty. Not magic. Just informed anticipation.
Step 6: Decide and Act Before It Hurts
This is the final step, and the one I care about the most.
Prescriptive insights answer one question only:
What should we do now?
Here’s how Favoriot handles it:
- Predictions are checked against defined rules
- Alerts or notifications are triggered
- The right people are informed at the right time
For example:
“This parameter is expected to exceed the limit within 48 hours. Notify the maintenance team.”
This is where Favoriot stops being a passive system and becomes a decision companion.
The framework ends with action, not reports.
That’s intentional.
Putting It All Together
The full Favoriot flow looks like this:
- Intent and context give focus
- Data foundation builds trust
- Descriptive insights give visibility
- Diagnostic insights give clarity
- Predictive insights give foresight
- Prescriptive insights lead to action
Most IoT platforms begin with data and stop at dashboards.
Favoriot starts with intent and ends with action.
That single shift changes how IoT feels.
Calmer. Clearer. More useful.
If you want the formal structure behind this explanation, the Favoriot Insight Framework (FIF) document lays it out clearly from Layer 0 to Layer 5.
And every time I revisit it, I still pause and think:
“This is how IoT should have worked from the start.”
Leave a Reply