# System prompt Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/system-prompt
> Markdown URL: https://aitinkerers.org/technologies/system-prompt.md
> Technology record last updated: 2026-02-24T00:23:44Z
> Generated: 2026-09-21T23:35:53Z

The System prompt is the foundational instruction set: it defines the Large Language Model's (LLM) persistent role, behavior, and constraints.

System prompts are the AI's 'job description,' operating behind the scenes to dictate model conduct. They establish the core persona, like an 'expert in Node.js and Express' or a 'customer interview coach.' This static instruction set ensures consistency across all user interactions, unlike dynamic user prompts. Effective system prompts integrate key elements: Role Definition, Behavioral Guidelines, and Ethical Constraints. For example, a prompt might mandate a 'professional and friendly tone' while setting a hard rule: 'Never share sensitive data.' This structure is critical for production-grade agents (ChatGPT, Claude, etc.), directly impacting reliability, safety, and adherence to a specific task domain.

- Official technology site: https://docs.anthropic.com/claude/docs/system-prompts
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building a Persistent Memory & Stateful Second Brain AI Agent](https://dhaka.aitinkerers.org/talks/rsvp_kSMaLnvvGGg)

Demonstrating context engineering in practice through Slatekore - an open-source starter kit that gives Gemini CLI persistent memory using Obsidian as the storage layer. 1. State Management Without Infrastructure How to use the file system as persistent state - your Obsidian vault becomes both the agent's memory and its knowledge base. No databases, no vector stores, no MLOps. 2. Context Engineering for Agent Behavior Crafting system prompts (GEMINI.md) and workflow files that define agent capabilities, constraints, and multi-step reasoning patterns. The prompt is the agent's configuration. 3. Tool Use Through Natural Interfaces Connecting the agent to real actions: creating files, managing tasks, building knowledge graphs - all through natural language commands backed by structured templates. Watch a stateful agent capture research, recall context from previous sessions, update its knowledge graph, and execute project workflows - without any model training or fine-tuning.

- Event context: AI Tinkerers Dhaka 2nd Meetup: Dhaka Builds with AI! — 2026-02-07 — Dhaka
- Public talk page: https://dhaka.aitinkerers.org/talks/rsvp_kSMaLnvvGGg

### [Finally, an AI support agent that asks you when it doesn’t know](https://munich.aitinkerers.org/talks/rsvp_Ja8nd4WT_wI)

AI support agents right now are an annoying wall to get through when you need support for a product. What they're missing is risk management, understanding when to rely on their team instead of hallucinating and repeating previous answers. To solve this, we're building an AI support team that handles all the communication, and focuses on truth & high quality support rather than making it more difficult for users to get relevant help.

- Event context: AI Tinkerers Munich - November 21 — 2024-11-21 — Munich
- Public talk page: https://munich.aitinkerers.org/talks/rsvp_Ja8nd4WT_wI

## Related Technologies

- [AI agent](https://aitinkerers.org/technologies/ai-agent) ([Markdown](https://aitinkerers.org/technologies/ai-agent.md)) — 8 public demos
- [ARM](https://aitinkerers.org/technologies/arm) ([Markdown](https://aitinkerers.org/technologies/arm.md)) — 1 public demo
- [AVX2](https://aitinkerers.org/technologies/avx2) ([Markdown](https://aitinkerers.org/technologies/avx2.md)) — 1 public demo
- [Fine-tuning](https://aitinkerers.org/technologies/fine-tuning) ([Markdown](https://aitinkerers.org/technologies/fine-tuning.md)) — 20 public demos
- [Flow prompting](https://aitinkerers.org/technologies/flow-prompting) ([Markdown](https://aitinkerers.org/technologies/flow-prompting.md)) — 1 public demo
- [GCC](https://aitinkerers.org/technologies/gcc) ([Markdown](https://aitinkerers.org/technologies/gcc.md)) — 1 public demo
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Gemini CLI](https://aitinkerers.org/technologies/gemini-cli) ([Markdown](https://aitinkerers.org/technologies/gemini-cli.md)) — 16 public demos
- [LLVM](https://aitinkerers.org/technologies/llvm) ([Markdown](https://aitinkerers.org/technologies/llvm.md)) — 2 public demos
- [LLVM IR](https://aitinkerers.org/technologies/llvm-ir) ([Markdown](https://aitinkerers.org/technologies/llvm-ir.md)) — 1 public demo
- [Markdown](https://aitinkerers.org/technologies/markdown) ([Markdown](https://aitinkerers.org/technologies/markdown.md)) — 24 public demos
- [Obsidian](https://aitinkerers.org/technologies/obsidian) ([Markdown](https://aitinkerers.org/technologies/obsidian.md)) — 6 public demos
- [Prompt Engineering](https://aitinkerers.org/technologies/prompt-engineering) ([Markdown](https://aitinkerers.org/technologies/prompt-engineering.md)) — 28 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [RISC-V](https://aitinkerers.org/technologies/risc-v) ([Markdown](https://aitinkerers.org/technologies/risc-v.md)) — 1 public demo
- [SSE](https://aitinkerers.org/technologies/sse) ([Markdown](https://aitinkerers.org/technologies/sse.md)) — 4 public demos
- [System prompts](https://aitinkerers.org/technologies/system-prompts) ([Markdown](https://aitinkerers.org/technologies/system-prompts.md)) — 2 public demos
- [User prompt](https://aitinkerers.org/technologies/user-prompt) ([Markdown](https://aitinkerers.org/technologies/user-prompt.md)) — 1 public demo