Our AI assistant , a.k.a. codi, also deserves its own changelog thread. Especially after the publication of flespi roadmap 2024 , where we highlighted a focus on the application of AI tech in our telematics services. Here, we accumulate changes in codi's architecture and post updates to its capabilities as soon as they are integrated. The list with actual codi capabilities: It can support you answering any flespi-related question loaded with the knowledge published in our comprehensive Knowledge Base and 7 year old Blog . It can generate code for your flespi-related API calls in any language, consult on flespi REST API , its structure and parameters to use. It can generate you PVM code to transform message parameters and parse binary and textual payloads upon your request. You may supply example in your code of choice and it will try to provide you with corresponding PVM code . It can generate flespi expressions for you upon request. It can consult you on the integrated protocols , devices and explain the meaning and protocol-specific source for any message parameter within some protocol. It can show you how to control device remotely, which API calls to use and how to correctly construct command API call for your specific device. It can help you to troubleshoot and diagnose what is wrong and propose changes in the configuration of devices, channels, streams, calculators, plugins and webhooks that you created. It can navigate you through parameters reported by the particular device (telemetry). It can assist you with your account usage and limitations or suggest how to save money on your flespi bill. It can consult you on the device configuration, remote management, peripheral usage for hardware produced by Teltonika, Ruptela, Xirgo, Galileosky, Suntech, Calamp, Howen, few most popular device models by Queclink, Jimi Iot(Concox), Topflytech and some other brands. That knowledge is based on the information from official device manuals . It can schedule itself a special followup task for itself and proactively assist you in your question until resolution. It can combine flespi knowledge with other platform-specific knowledge (e.g. Wialon, GPS-Trace) for edge consulting.

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 assistant

shal

Step by step codi's architecture evolved into gen3.1. Not that much due to the fundamental changes but we implemented hundreds of minor improvements based on the practical usage. And raised codi's intelligence to a next level.

The most notable change is the model - codi is now mostly powered by the latest and most-intelligent model from Anthropic - claude-3-5-sonnet-20241022. After we improved knowledge retrieval system it's capabilities in resolving the majority of issues are now in par with human engineers. Just give it a try! You can find codi in top-right corner of your flespi.io account under CHAT button.

And another AI tool by flespi (open source) for your support engineers and FAE deserves a special record here as well.

For those who prefer quick, simple and efficient device manufacturer exploring tool for your support staff - please use it directly by this link: https://flespi.io/deviceassist/. You can add the token to the link for auto-login if needed.

This tool can be integrated into your CRM, ERP, Support portal via iframe. Also device assistant can be integrated into your support chat or LLM as a function tool or source of information via API.

shal

We've enhanced codi's capabilities with protocol implementation analysis features. Now our AI assistant can:

Analyze protocol implementation details
Explain parameter names, values and conditions
Compare protocol specifications with actual implementation in flespi

This allows for deeper technical discussions and more accurate troubleshooting. You can access these new capabilities by clicking the CHAT button in the top-right corner of your flespi.io account and communicating with codi.

shal

Codi received a per-chat memory and can activate it to access information you shared with flespi in your past conversations. This keeps its communication with the user very private and specific. You may now ask it what it knows about you ;-)

And we have implemented a self-training system that automatically creates anonymized long-term knowledge for the AI from all complex and resolved use cases in flespi HelpBox since 2018 and applies it when appropriate. This feature immediately pushed codi's intelligence level to new heights, making it now almost unreachable by a human in all flespi-related discussions.

shal

We enhanced codi with the ability to read PDF documents attached to the HelpBox chat and improved its ability to assist with complex device protocol questions.

For example when resolving parsing errors generated by the device it is now capable to extract related raw traffic and analyze if the traffic conforms to the official protocol documentation.

shal

We've enhanced codi (AI assistant) with Proactive Assistance System.

codi can now provide timely follow-up assistance for implementation verification and complex tasks. This system is designed to be helpful but unobtrusive - codi will check in at appropriate intervals when it might benefit your workflow, while respecting conversation boundaries and your preferences.

So don't be surprised if you receive a message from codi without asking - it's just checking if everything is going well with your implementation or if you need any additional help! :)

shal

codi (AI assistant) can now provide comprehensive support for Wialon-related questions by accessing official Wialon documentation.

This integration enables seamless support across both platforms while maintaining clear boundaries - complex Wialon-specific issues will still be directed to the Wialon support team (support@wialon.com), but codi can now handle a much wider range of Wialon documentation questions directly in the flespi chat.

Whether you're connecting devices through flespi to Wialon, configuring Wialon to receive flespi data, or simply have questions about how the platforms work together, codi can now provide more comprehensive assistance for your cross-platform needs.

shal

And codi can now access Tracy - the AI assistant for GPS-Trace platform, enabling support for cross-questions about Ruhavik, Forguard, and other GPS-Trace applications. This integration follows our recent Wialon knowledge expansion, further enhancing codi's capabilities as a comprehensive telematics consultant.

shal

codi (AI assistant) now adapts to your working style

We've implemented a behavioral learning system that allows codi to understand your technical preferences and usage patterns over time. This means codi will gradually adapt its responses to match your expertise level, preferred communication style, and the specific flespi features you use most.

For example, if you consistently work with Teltonika devices and prefer code-focused solutions, codi will prioritize relevant examples and skip basic explanations. Or if you're learning flespi and need step-by-step guidance, codi will maintain a more explanatory approach. This adaptation happens automatically based on your interactions - no configuration needed.

This system focuses purely on improving technical assistance quality. It observes patterns like your device ecosystem, preferred troubleshooting approaches, and platform features you use, then tailors responses accordingly. Think of it as codi learning to speak your language - whether that's direct API examples for experts or detailed walkthroughs for those getting started.

shal

codi (AI Assistant) intelligence now scales with flespi plan

Starting today, codi adapts its capabilities to match your subscription level:

Free plan users receive basic AI assistance
Start plan customers get standard intelligence with deeper analyzes
Pro, Enterprise, and Ultimate subscribers enjoy the most advanced frontier models available nowadays with expanded knowledge and superior problem-solving abilities

This tiered approach ensures each user receives support aligned with their operational needs and platform usage.

shal

A lot of improvements and features have been integrated into codi since the last changelog entry in June. New models, new capabilities, extra knowledge, and various tool improvements. The most notable improvements are related to analytics and device message analysis:

Expressions evaluation via the integrated expression testing tool to precisely analyze how device messages are evaluated by calculator counters and selectors;
Geofences detection proficiency via the integrated hit test method;

We are also constantly improving the knowledge base of protocol documentation, device manuals, and building a common device configuration experience database. Basically, codi is the only AI in the world that has already participated in thousands of telematics projects worldwide and built incredible knowledge from that. No human can ever match it anymore when we talk about telematics. It knows practical things about devices - their problems, applications, configuration hacks - that even their manufacturers know nothing about.

And yes, to uncover the best capabilities, you have to be on a Pro plan, and the most intelligent consultation on advanced complexity questions is available to Enterprise and Ultimate plan users only. Free and Start plan users have a very high level of support, but it cannot be compared to higher plans, especially when we talk about complex things in telematics.

shal

We loaded into Codi EU Tachograph regulations and various requirements. The knowledge is based on official CELEX documents.

shal

Codi goes beyond chat — meet new flespi services for AI agents

The same flespi intelligence that powers your HelpBox conversations is now available programmatically — for your AI agents, IDEs, and automation pipelines.

Documentation expert — ask questions about flespi platform features and configuration. The expert searches our KB, blog, and API specs and returns a focused answer. Perfect for embedding flespi knowledge into your support agents or development workflows.

Account expert — delegate complex analysis to a flespi platform expert with read access to your account. It can perform multi-step investigation across your devices, channels, logs, and configurations — the same kind of deep diagnostics codi does in chat, now available as a single API call.

Both are accessible as REST API tools and through MCP servers for Claude Code, Cursor, and other AI-powered IDEs.

You can now build custom, fully functional flespi-based applications in hours. Details and setup: flespi AI integration.