We'll post here all the changes regarding flespi AI subsystems.

Recently we installed beta-version of next AI platform for the codi and now its implementation is totally different comparing to the initial . A little bit later we will publish a dedicated blog article with more insight about new codi architecture. A set of new codi capabilities: Loaded with REST API knowledge with the possibility to generate programming code on any language accessing flespi API. Generate flespi expressions upon your request. Provided knowledge of integrated protocols , devices and trained to understand per-protocol message parameters, their meaning and protocol-specific origin of each param, (e.g. Teltonika's AVL ID 199 and 357 mapped to segment.vehicle.mileage parameter in flespi)

We enhanced codi(AI assistant) capabilities with: Troubleshooting and diagnose what is wrong in your account with basic items. It now propose specific changes or explain meaning of the configuration of your devices, channels, streams, calculators, plugins and even webhooks. It can navigate you through parameters reported by the particular device (telemetry). And it can help you to understand which settings and commands are available and how to construct API call to remotely control some parameters of specific devices.

We trained codi to generate PVM code on your request. With PVM code you can transform device message, parse it fields into different parameters (BLE beacons, data from serial port, etc) and in general do with message whatever you want before it is registered in flespi and streamed to your servers. Maybe not all tasks, but quite capable. You can supply to it either description of the task or just a code block on your favorite programming language and it will try to provide you corresponding pvm code. PVM code is not yet automatically validated and may be incorrect, but you may provide codi feedback what is wrong and it will try to fix it. Most of popular tasks it should be able to solve already.

This week we installed 3rd version of our AI assistant platform. Principal change is that we got rid of specific QnA experts and now using two-stage processing to determine correct context of the discussion. And based on the context we are preloading different knowledge, instructions for LLM and even choosing different LLM/model for answer preparation based on the user capabilities. One model for a bla-bla-bla discussion, another model to solve deep technical problems, third model for sales consulting and so on ;-) As a bonus for our users now codi has a knowledge about all protocols and devices integrated into flespi. It can search and propose you OBD, CAN, personal trackers, pet trackers, assets trackers and so on. And even recommend some settings to adjust in your devices: We are still in the very early phase for this but within few months we will have enough knowledge to cover top-5 or even top-10 device manufacturers.

We recharged codi with a knowledge about user account limitations and counters, including billing information. Now it is able to consult and advice some actions on how to save money in your flespi account ;-) Enjoy! P.S. Be aware that codi's math skills are not excellent and sometimes it multiply numbers incorrectly. For small numbers, like those that you may have in you invoice it happens in rare cases. However if take into account big numbers like UNIX timestamp - without calculation tools it hallucinates on its own quite a lot.

Remember in our roadmap 2024 I wrote about the attempt to enrich codi's knowledge with device-specific? Now it is able to consult you about Teltonika devices. Fully loaded with all official documentation it now knows a lot about each Teltonika device model: commands, parameters, configuration, firmware, FAQs, basically everything that you can find on the Teltonika Wiki . When using this feature make sure you provided into chat context either information about your flespi device ID or at least specify device model and manufacturer, e.g. Teltonika FMB920. If you will give your device ID codi will load the knowledge for its particular model. And yes, this feature is very experimental and we will adopt it based on real life scenarios and user expectations. Do not push codi too hard.

We enriched codi with the knowledge from official device manuals by: Ruptela , Xirgo and Galileosky . Now every request from you with indication of device ID or device type name loads into AI context also quite a lot of information from manufacturer's manual. Also we enabled quick AI assistance using manufacturer's manual directly in the device . This functionality is limited only to the information from manual and do not have access to device state, but can be used as a quick and efficient way to navigate through device manual.

We loaded codi with the knowledge extracted from Howen Technologies manuals for most popular devices . Now it can effectively consult you how to configure, operate, troubleshoot and install Howen video devices.

We are now providing the AI assistant service for most popular Jimi IoT , Suntech and Topflytech devices. Also for one manufacturer - Calamp , which recently filed bankruptcy we integrated into the device AI assistant the knowledge on writing PEG scripts (special calamp scripts for controlling device logic) and other general Calamp-specific information from its manuals.

AI assistance is available for Atrack devices. AI assistent ready to help with the reports for all the models. AK11, AK500 and AS500 also equipped with device Manuals knowledge. Reporting protocol assistance is also avialble for Streamax devices and the group of 3 scooter and bike sharing related protocols: Omni , Freego and Segway-Ninebot

[Changelog] flespi AI and MCP

shal

flespi AI agents are now available for all flespi users.

They are autonomous workers living in your flespi account capable for any kind of telematics-related work in flespi and other connected telematics systems, such as Wialon Hosting. To interact with flespi AI agents you can use Telegram, Slack and even E-Mail.

Agents can consult, analyze, monitor and act securely.

shal

Codi (AI assistant) now distinguishes consulting from delegated tasks.

Codi answers everything a human support engineer would answer without limits.

Work that support would hand back to you to do yourself — repeated checks, monitoring, bulk investigations, reports, complete deliverables — is a delegated task, and every plan includes a number of them per day and per month.

When the allowance is used up, Codi points you to a flespi AI agent, the tool built for this kind of work, or to the next plan.

shal

Teltonika FOTA WEB connector for flespi AI agents is now available.

Give your flespi AI agent a FOTA WEB API token and it becomes a Teltonika expert: it audits the fleet, its firmware and configuration versions, prepares configuration changes based on the official Teltonika documentation and delivers them with FOTA WEB tasks, queues firmware updates, and watches the tasks until they complete.

Give it flespi and/or Wialon Hosting account access and the agent will be able to see device configuration from both sides - FOTA WEB (same as Teltonika Support) and from corresponding connected platform (same as your Platform Support).

As with other AI connectors - all modification operations that agent can issue are protected by explicit approval of human in loop by default.

shal

Wialon Platform connector for flespi AI agents is now available.

Wialon Platform gives telematics service providers full business control and a powerful foundation for true product ownership. With the new connector flespi AI agent can be used to extract fleet data, assist in devices configuration, debug issues, design the workspace UI and automation directly on the Wialon Platform.

Coupled with Wialon Hosting connector flespi agent can seamlessly operate both Wialon systems together building the combined solution for fleets.

shal

Every flespi AI agent now has an intelligence level that sets how capable it is and what each of its reasoning steps costs ranging from 25 up to 250 AI credits per step.

Along with the levels, the free monthly AI credits grow with the plan:

1,000 on Free and Start
2,000 on Pro
5,000 on Enterprise
10,000 on Ultimate

shal

AI classification of driving events is now available.

The new classify-driving-events AI tool reviews the video and images of vehicle cameras, lists the ADAS and DSM events it observes and gives a verdict on each alarm the device reported: confirmed, rejected or undetermined.

It is available over REST API and in the support MCP server for 1 to 10 AI credits per file. The ai-driving-events plugin runs the same review automatically for the footage your devices upload and resets the false alarms in their messages.

shal

Wialon Local connector for flespi AI agents is now available (Wialon Local release 2604 or newer).

All three Wialon products are now supported and accessible by flespi AI agents: Hosting, Local and Platform.

shal

flespi AI agents now build and run automations and integrations in your account.

A handler script an agent binds to a timer or an MQTT topic can now apply the actions decided in advance on its own. A job on a schedule, a reaction to an event, a provisioning chain where each step waits for the outcome of the previous one, a bridge between flespi and the systems the agent is connected to.

Every write a script queues passes the agent's approval rules just like one from a reasoning step, consumes no AI credits when it succeeds, and wakes the agent for a reasoning step only when something fails.

shal

flespi AI agents can now work for your customers, under your brand.

Assign a persona to an agent and it becomes your assistant: your name, your audience, your rules of engagement, and with branded disclosure no mention of flespi at all.

Give each customer an agent connected to their flespi (or Wialon Hosting, Local, Platform, Teltonika FOTA WEB) account, embed the chat into your application with a single link, and your customers get an AI assistant that answers in their terms and acts on their account with their approval, while the agents and their spending stay under your control.

shal

flespi AI agents approval rules improved

You can now set approval rules for specific operations of each connector, on top of the connector default.

For example, with the flespi connector the agent may change devices, calculators and plugins on its own while every /platform operation still requires explicit human approval. With the Teltonika FOTA connector the agent may upload firmware files, but the firmware task itself still goes through a human. The Wialon Hosting, Local and Platform connectors take rules the same way, by units, geofences, users, modules and other parts of the account, and the email connector by recipient address mask.

Approval rules work on top of the credential each connector holds. The token or key configured in the connector defines what the agent can reach at all, while the rules only decide which of those operations run automatically, ask you first, or are rejected.

shal

flespi AI agents now build apps and dashboards for you.

Ask for a live map for your dispatchers, a report page or a one-click tool for your team, and the agent builds the app: a web page under a link of its own, no servers or developers on your side.

With the flespi connector the agent also supplies the backend for this app.

shal

We integrated into flespi AI agent access to connectivity providers: emnify and onomondo.

This gives agent capabilities to quickly build and maintain connectivity health dashboards with combined providers views,
alert you on problems with SIM, synchronize them together with changes in devices, analyze traffic consumption, activate/deactivate SIMs according to your actual telematics configuration and much more.