# Mini Internal Hackathon

We’re kicking off a **2-week internal hackathon** to improve Cortensor’s end-to-end (E2E) flow and uncover bugs by building lightweight, creative tools and bots.

This is part of an **ongoing internal initiative** — future rounds will continue to support rapid iteration, internal improvements, and developer experience upgrades.

\
**Public hackathons** will follow later, after multiple internal rounds.

***

### Objective

Build small proof-of-concept (PoC) apps or bots that:

* Interact with the **Cortensor API**
* Improve node operator or developer experience
* Focus on **usability**, **bug discovery**, and **creative tooling**

***

### Prize Pool (in $COR equivalent)

* 1st Place: $150
* 2nd Place: $100
* 3rd Place: $50
* 4th Place: $25
* 5th Place: $25

Top projects may also receive **monthly $COR grants** for ongoing maintenance and improvement — just like community tooling and infra contributors.

**Top 3 apps** will be considered for dedicated roles and potential monthly $COR support — similar to our community tooling and infra contributors.

**Ongoing Support**\
Exceptional projects may also receive monthly $COR grants for continued maintenance and improvement beyond the hackathon.

***

## Project Ideas

### Chat & Utility Bots

#### 🔹 Ask Me Anything Bot

Telegram or web bot that answers user questions using Cortensor’s API.\
\&#xNAN;*Optional:* Restrict to certain domains (e.g., programming), or add tone/context options.

#### 🔹 Tweet Generator

Web form or bot where users input a topic → generates tweet drafts via LLM API.\
\&#xNAN;*Optional:* Regenerate button or tone selector (bold, funny, serious).

#### 🔹 Daily Motivation Bot

Sends one AI-generated motivational quote per day.\
\&#xNAN;*Optional:* Tone selector like “cheerful,” “serious,” or “sarcastic.”

#### 🔹 Explain Like I’m 5

Simplifies complex topics into plain language.\
Prompt example: `“Explain [Topic] like I’m five.”`

#### 🔹 Smart Reply Generator

Reads the last few Telegram messages and suggests natural replies (like Gmail Smart Reply).

#### 🔹 Template Completion Tool

Takes structured input (e.g., tweet idea, email topic) and generates a polished version using prompt templates.

#### 🔹 Eliza-Style Therapist Bot

Retro-style, supportive chatbot built on fixed personas and templates.

### Agent-Based Ideas

#### **🔹 Support Agent Bot**

Build a basic support agent that helps answer node operator questions, provides setup steps, or links to relevant documentation using Cortensor API + RAG-like memory.

#### **🔹 Task Validator Agent**

An agent that reviews completed inference tasks (e.g., image, text) and flags potential quality issues — simulating part of the validator role with a helpful UI or Discord bot.

#### **🔹 Feedback Collector Agent**

Simple web/Telegram agent that periodically asks users for feedback on Cortensor experience (node running, test task, app flow) and stores the responses.

#### **🔹 Cortensor Assistant Agent**

A bot that knows the current DevNet, open issues, FAQs, and roadmap — usable in Discord or on the dashboard for internal team support.

***

### Community Collaboration

All internal hackathon projects will be shared and maintained via our public repo:\
🔗 [**github.com/cortensor/community-projects**](https://github.com/cortensor/community-projects)\
This will become the home for all **community-built tools, apps, infra, and experiments**.

***

### Got Ideas or Feedback?

Suggest new ideas or form small teams by joining the conversation on Discord:\
🔗 [**discord.gg/cortensor**](https://discord.gg/cortensor)

***

Let’s build fast, test creatively, and improve the network from within — one bot at a time.\
Public hackathons are coming soon, but it starts here.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cortensor.network/community-and-ecosystem/hackathon/mini-internal-hackathon.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.