# RFC on DotBot, an LLM based intent-driven AI assistant for Polkadot

**URL:** <https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837>\
**Category:** Ecosystem\
**Created:** [January 26, 2026, 11:11am UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837 "2026-01-26T11:11:25Z")\
**Posts on this page:** 11\
**Page:** 1

<div class="post-metadata">

**Author:** ![Vikk](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/vikk/32/5434_2.png) [@Vikk](https://forum.polkadot.network/u/Vikk)\
**Post date:** [January 26, 2026, 11:11am UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/1 "2026-01-26T11:11:25Z")

</div>

_Hello everyone, this is Vikk from the Hungarian Polkadot DAO, and I’m writing in connection with a new proposal on the idea of [DotBot](https://live.dotbot.zelmacorp.io/), which is currently in the RFC (Request for Comments) phase. We would like to gather as much feedback as possible from the global Polkadot and Kusama communities so we can better understand the community’s perspective on DotBot and adjust our plans accordingly. At a later stage - probably 2-3 weeks from now - we will submit the proposal to OpenGov to request funds to further develop the current POC. Thank you very much the community’s contribution! Please find DotBot’s proposal below.👇_

In 2026, AI is everywhere, it’s our personal assistant, our co-pilot, and our researcher. But in crypto, we’re still stuck in the “manual transmission” reality, clicking through five screens just to move tokens across chains.

We think it’s time for Polkadot to have a conversation. We’re building DotBot, a chatbot that lets you execute transactions using simple English. No more overcomplicated flows, just tell the bot what you want to do, and it handles the technical heavy lifting while keeping you secure and asking for your permission when needed.

 ![dotbot mockup min](https://europe1.discourse-cdn.com/flex005/uploads/polkadot2/original/2X/f/fb790655b168104dd31ec3d08a1856324c65e13f.png)

## What is the goal?

Our goal is to bridge the gap between user intent and on-chain execution. We’re building the “brain” that knows which request to call and how to handle transactions easily, so you don’t have to worry about complex situations.

We know there’s still much work ahead. We’re focusing on refining the system right now and would appreciate any feedback.

## What it does

The project focuses on translating user intent into safe, runtime-aware transactions across Polkadot Asset Hub and selected parachains. While basic asset transfer functionality is already implemented, further work is required to ensure correctness guarantees, robust transaction validation, and predictable behavior across wallets and runtimes.

We’re excited to share our progress on stabilizing and preparing DotBot’s execution layer for release. This includes enhancements like transaction simulation, end-to-end scenario validation, and modular infrastructure that can be reused by wallets and applications.

 ![dotbot previews min](https://europe1.discourse-cdn.com/flex005/uploads/polkadot2/original/2X/7/7e0d726a2e1cf5455debd60e20867328d92be697.png)

## How can you test it?

Development of DotBot is already underway, and a functional prototype exists.

The current implementation focuses on intent-driven transaction execution rather than traditional form-based workflows. In particular, DotBot currently supports:

- Conversational input for asset transfers _**(only on AssetHub at the moment)**_ using natural language
- Context-aware interpretation of user intent across multiple messages
- Clarification prompts when user intent is ambiguous (e.g. resolving “_Who is Alice?_”)
- Explicit user confirmation before any transaction is constructed or submitted
- Visualized execution flows that expose each step of the transaction lifecycle
- Generation of runtime-compatible Polkadot extrinsics based on interpreted intent
- Wallet-based signing using standard Polkadot browser extensions

Ready to see it in action? Let’s give it a try!

- **Where can you test it?** → Link to DotBot POC: [link to DotBot POC](https://live.dotbot.zelmacorp.io)
- **Curious about the code? See our code:** [GitHub - Hungarian-Polkadot-DAO/DotBot](https://github.com/Hungarian-Polkadot-DAO/DotBot)
- **Tell us what you think** : We really want to hear what you think. Please fill out our [short feedback form here](https://tally.so/r/jalkG1). Your input will directly shape our Treasury proposal.

## How it helps the ecosystem

Polkadot is powerful but sometimes hard to use. DotBot makes it accessible to everyone, not just the power users. It’s a new way to interact with the network, new users don’t need to learn about blockchain and what’s the exact process of sending crypto to a friend. They just ask and DotBot help to do this.

---

<div class="post-metadata">

**Author:** ![alice\_und\_bob](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/alice_und_bob/32/10098_2.png) [@alice\_und\_bob](https://forum.polkadot.network/u/alice_und_bob)\
**Post date:** [January 27, 2026, 8:08am UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/2 "2026-01-27T08:08:20Z")

</div>

Hey Vikk!

Are you using MCP for the bot?

---

<div class="post-metadata">

**Author:** ![optr](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/optr/32/7367_2.png) [@optr](https://forum.polkadot.network/u/optr)\
**Post date:** [January 28, 2026, 6:47pm UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/3 "2026-01-28T18:47:22Z")

</div>

Hey @alice_und_bob  
I think we could say that, yes. We are developing _Agents_, which are basically classes in the lib. For example `AssetTransferAgent`. It has certain capabilities. The LLM knows about the capabilities of that agent. It will fulfill your request, by using the capabilities of that agent. Thinking in longer terms, there will be multiple agents, if a user prompt is complicated, it will compose the flow from multiple agent calls, it will use the capability of the first agent, it will then use the capability of the second agent, probably, it will then go back to the first agent, for example:

1. transfer
2. swap
3. transfer again

For this, you need 2 agents.

---

<div class="post-metadata">

**Author:** ![Vikk](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/vikk/32/5434_2.png) [@Vikk](https://forum.polkadot.network/u/Vikk)\
**Post date:** [February 2, 2026, 10:37am UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/4 "2026-02-02T10:37:14Z")

</div>

GM @alice_und_bob, thanks for your questions. I hope you find @optr‘s answer helpful. Do you have any other questions / recommendations regarding DotBot’s POC? We’d really like to hear your words on the topic! 🙂

---

<div class="post-metadata">

**Author:** ![ultracoconut](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/ultracoconut/32/5932_2.png) [@ultracoconut](https://forum.polkadot.network/u/ultracoconut)\
**Post date:** [February 3, 2026, 2:54pm UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/5 "2026-02-03T14:54:59Z")

</div>

```auto
Let's be honest, is this something absolutely necessary to spend money on? In my opinion, it isn't. Sorry.

```

---

<div class="post-metadata">

**Author:** ![Vikk](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/vikk/32/5434_2.png) [@Vikk](https://forum.polkadot.network/u/Vikk)\
**Post date:** [February 3, 2026, 10:01pm UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/6 "2026-02-03T22:01:47Z")

</div>

Hi @ultracoconut!

Please don’t be sorry! You absolutely have the right to express your opinion. If you feel that an AI chatbot for Polkadot, capable of performing different kinds of on-chain actions on behalf of still-lost users, is unnecessary, that’s completely okay.

That said, we believe an AI chatbot for Polkadot is very much needed, and it’s unfortunate that there is still no viable product in this direction within the Polkadot ecosystem. Meanwhile, other blockchain ecosystems are far ahead in this area, investing significant amounts of R&D efforts and huge amounts of money into LLM-based, user-centric chatbots and other AI tools.

Please find the examples below:

1. Solana just announced their Colosseum Hackathon, focusing on AI agents:

> **[Colosseum Agent Hackathon](https://colosseum.com/agent-hackathon/?ref=blog.colosseum.com)**
>
> Solana's first hackathon where AI agents compete. Build, submit, and vote on Solana projects created by AI.

1. Galichat & SendAI, both are AI chatbots to help users performing on-chain actions, like token sends and swaps, etc… on Solana.

> **[GaliChat – AI Agents that Grow Your Business](https://www.galichat.com/pricing)**
>
> Power your business growth with AI Agents that deliver flawless customer experiences and lead generation. Make your customers happy while saving money.

> **[SendAI](https://www.sendai.fun/)**
>
> The tooling Layer for AI Agents

1. Polygon just announced that they integrates x402, to enable autonomous, programmable payments for AI agents and APIs on Polygon.

> **[Agentic Payments Infrastructure | x402 on Polygon](https://polygon.technology/payments/agentic-payments)**
>
> Enable autonomous, programmable payments for AI agents and APIs. Polygon + x402 delivers instant finality, ultra-low fees, and global rails.

1. Base chain just announced that they are open for a more agentic ecosystem with OpenClaw: [https://open-claw-ecosystem.vercel.app](https://open-claw-ecosystem.vercel.app)

2. Lastly, if you didn’t know that, even the Web3Foundation announced in one of their earlier [Medium Post](https://medium.com/web3foundation/new-w3f-grant-guidelines-b2c921a84850) the following guideline:

---

<div class="post-metadata">

**Author:** ![ultracoconut](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/ultracoconut/32/5932_2.png) [@ultracoconut](https://forum.polkadot.network/u/ultracoconut)\
**Post date:** [February 4, 2026, 11:36am UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/7 "2026-02-04T11:36:46Z")

</div>

You don’t need a Dotbot; any agent today would be capable of performing a transaction on Polkadot. An agent was able to autonomously purchase a SIM card, add a voice protocol to it, and call their human on the phone in the morning.

Agents today can perform transactions on Polkadot while having coffee using a Unitree robot.🤖

---

<div class="post-metadata">

**Author:** ![optr](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/optr/32/7367_2.png) [@optr](https://forum.polkadot.network/u/optr)\
**Post date:** [February 4, 2026, 12:50pm UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/8 "2026-02-04T12:50:01Z")

</div>

They wouldn’t be able to safely execute transactions, this is a much more critical task than you think, with several nuances.

Beside, you don’t want to give full control to it, you want it to help you prepare transactions, which you can then overview. This is not something, ChatGPT can do for you as of today.

---

<div class="post-metadata">

**Author:** ![ultracoconut](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/ultracoconut/32/5932_2.png) [@ultracoconut](https://forum.polkadot.network/u/ultracoconut)\
**Post date:** [February 4, 2026, 1:12pm UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/9 "2026-02-04T13:12:19Z")

</div>

What you’re describing is a problem with the agents. So the Polkadot treasury would spend money to improve them? They’ll be improved in a few months without us spending any money.

---

<div class="post-metadata">

**Author:** ![optr](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/optr/32/7367_2.png) [@optr](https://forum.polkadot.network/u/optr)\
**Post date:** [February 4, 2026, 5:54pm UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/10 "2026-02-04T17:54:04Z")

</div>

Let me answer to your question from a technological standpoint:

I think we’re mixing up two different things here.

We’re not building or “improving” AI agents. And we’re definitely not assuming agents are dumb or incapable — we know they’re getting better fast.

The problem isn’t whether an agent can _create_ a Polkadot transaction. Many already can. The problem is whether you want to **trust a generic agent to safely execute on-chain actions in a complex, multi-runtime ecosystem**.

That’s where things get tricky.

DotBot isn’t about giving an agent the keys and letting it do whatever it wants. It’s the opposite. The agent only helps interpret intent. DotBot then constrains it, checks it against the actual chain state, simulates what will happen, and shows the user exactly what they’re about to sign.

This is not something that “just fixes itself in a few months” as agents improve, because agents don’t magically gain Polkadot-specific safety guarantees, runtime awareness, or edge-case coverage on their own.

That’s also why we’re building things like the ScenarioEngine. You can’t just assume all paths work. On-chain mistakes are expensive and irreversible, so you need to actively test weird and bad scenarios — not hope the agent gets it right.

So no, the Treasury wouldn’t be paying to make agents smarter.  
It would be paying to make agent-driven UX **safe enough to actually use on Polkadot**.

---

<div class="post-metadata">

**Author:** ![optr](https://dub1.discourse-cdn.com/flex005/user_avatar/forum.polkadot.network/optr/32/7367_2.png) [@optr](https://forum.polkadot.network/u/optr)\
**Post date:** [February 9, 2026, 5:34am UTC](https://forum.polkadot.network/t/rfc-on-dotbot-an-llm-based-intent-driven-ai-assistant-for-polkadot/16837/11 "2026-02-09T05:34:05Z")

</div>

Westend AssetHub RPCs don’t work, so we will start implementing `Paseo`, as a substitute.

```auto
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔍 Westend Relay Chain
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[06:32:18] ✅ OK 3175 ms wss://westend.api.onfinality.io/public-ws
[06:32:21] ✅ OK 2367 ms wss://westend-rpc.polkadot.io
[06:32:23] ✅ OK 2331 ms wss://westend.public.curie.radiumblock.co/ws

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔍 Westend Asset Hub
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[06:32:23] ❌ FAIL 267 ms wss://westend-asset-hub-rpc.polkadot.io
[06:32:24] ❌ FAIL 81 ms wss://westmint.api.onfinality.io/public-ws
[06:32:24] ❌ FAIL 243 ms wss://sys.ibp.network/westmint

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 CUMULATIVE STATISTICS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Endpoint Total OK TO Fail OK% Avg ms
wss://westend.api.onfinality.io/public-ws 4059 4019 40 0 99% 3324
wss://westend-rpc.polkadot.io 4059 4054 1 4 99% 2412
wss://westend.public.curie.radiumblock.co/ws 4059 4056 2 1 99% 2472
wss://westend-asset-hub-rpc.polkadot.io 4059 0 4 4055 0% —
wss://westmint.api.onfinality.io/public-ws 4059 0 7 4052 0% —
wss://sys.ibp.network/westmint 4059 0 22 4037 0% —

```
