# Prompt Engineering Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/prompt-engineering
> Markdown URL: https://aitinkerers.org/technologies/prompt-engineering.md
> Technology record last updated: 2026-02-23T10:21:54Z
> Generated: 2026-09-22T07:51:39Z

Prompt Engineering is the discipline of structuring inputs (prompts) to Large Language Models (LLMs) to reliably and efficiently elicit a desired, high-quality output.

This is the core skill for maximizing performance from models like GPT-4 and Claude 3: it's the art and science of guiding an AI. The process involves systematic iteration and applying specific techniques to control the model's behavior and reduce 'hallucination.' Key advanced methods include Chain-of-Thought (CoT) prompting, which forces the LLM to process complex problems step-by-step, and Few-Shot prompting (providing 2-3 examples) to establish a clear output format or style. Mastery of these methods directly translates to tangible gains: improved accuracy, reduced API costs from fewer retries, and production-ready outputs for applications like customer service bots or code generation.

- Official technology site: https://www.promptingguide.ai/
- Public AI Tinkerers demos and talks: 28
- Result page: 1 of 2

## Recent Public Talks and Demos

### [What Breaks When LLMs Turn Fictional Prose into Screenplays](https://st-louis.aitinkerers.org/talks/rsvp_9CI_yEjbp-4)

I built a human-in-the-loop workflow that converts a narrative fiction scene into screenplay/teleplay format while trying to preserve subtext, pacing, character power dynamics, and scene function. For the demo, I’ll show a short prose scene, the weaker output from a basic prompt, and then the improved screenplay-style output after I changed the prompt structure and context constraints to better control exposition, visual action, dialogue compression, and tone.

- Event context: AI Tinkerers St. Louis: April 2026 Meetup — 2026-04-14 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_9CI_yEjbp-4

### [Building an AI WhatsApp guide for the Valencia Fallas festival](https://valencia.aitinkerers.org/talks/rsvp_73Oz6MkCmvU)

I built an AI-powered WhatsApp assistant that acts as a digital guide for the Valencia Fallas festival. Visitors can ask about the main Fallas monuments and receive explanations about their meaning, satire, and artistic concept. For the most important Fallas, the assistant also delivers pre-recorded audio explanations in Spanish and Valencian, allowing visitors to experience them as if they were using an audio guide. The project demonstrates how conversational AI can turn a messaging app into an accessible cultural guide for large public events without requiring users to install a dedicated app.

- Event context: AI Tinkerers Valencia March Meetup — 2026-03-17 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_73Oz6MkCmvU

### [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

### [Building an Interpretable AI Market Regime Engine](https://valencia.aitinkerers.org/talks/rsvp_ZWrBWUN_Uig)

This talk presents Zensei, an AI-powered market regime engine designed to translate complex macro and market data into structured, interpretable intelligence. Rather than predicting prices or issuing trading signals, Zensei models market risk as a hierarchy of regimes, constraints, and transitions, and uses AI to explain what changed, why it matters, and what would alter the regime next. The system combines a deterministic rules-based engine with carefully designed prompts that generate consistent, non-alarmist, human-readable explanations in real time. The demo will show how structured data, regime logic, and prompt engineering work together to produce explainable, high-signal outputs suitable for decision support.

- Event context: AI Tinkerers Valencia January Meetup — 2026-01-29 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_ZWrBWUN_Uig

### [Build Voice Assistant for under 20$](https://seattle.aitinkerers.org/talks/rsvp_5oovtgd9AT0)

We have seen Voice assistants from Cortana, Alexa to whatever that shows up in next few days with the current genAi revolution. In this talk, we show how build personal (hopefully secure) Voice Assistant), that can teach us new language, maybe help with some interview, or may be just to have a good conversation. This app deployed on Azure was built during after work hours, a bit of next js, prompt engineering, might help cancel a lot of subscriptions

- Event context: AI Tinkerers Seattle - March Meetup — 2025-03-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_5oovtgd9AT0

### [How to build a Gamemaster](https://seattle.aitinkerers.org/talks/rsvp_qAOZpkD0eMY)

Building a voice-based agent for *entertainment* is a huge challenge. Game development is a unique craft that most engineers struggle with: iterating to "find the fun" feels unintuitive. I present our D&D-like experience delivered by an AI Gamemaster, and share how combining game systems, human-authored content, and the craft of gamemastery, has resulted in a compelling experience that players spend hours enjoying.

- Event context: AI Tinkerers Seattle - March Meetup — 2025-03-28 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_qAOZpkD0eMY

### [Jailbreak RUN - How to gamify LLM security education](https://poland.aitinkerers.org/talks/rsvp_e2dRi-00VFU)

Jailbreak RUN is both a community event and a Discord LLM-powered bot with a simple concept: challenge an entire server of users to work together to break the bot and extract a password or force it to perform a specific action. The bot is designed to hybridize prompt engineering with application logic tailored to a specific event, and through attempts to break the bot, it also enables storytelling tied to uncovering information about the game directly from the bot. So far, the following editions have been conducted: - A classic Jailbreak with guardrails. - A Jailbreak with encrypted input and output messages, making some jailbreak methods more difficult or outright impossible to use. - Jailbreaking a vector database by attempting to override the RAG (Retrieval-Augmented Generation) system to extract hidden sensitive data from the database while simultaneously bypassing guardrails. This concept is highly scalable to other variants, such as the planned PvP mode, where players will design bots for one another and compete in a tournament to see who can jailbreak the other teams' bots first.

- Event context: AI Tinkerers Poland - Second Meetup in Warsaw (January) — 2025-01-30 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_e2dRi-00VFU

### [Evaluating a Medical Assistant](https://poland.aitinkerers.org/talks/rsvp_NPP2O6J7Te4)

How do you evaluate an AI system that assists doctors with medical documentation? In this talk, we'll share practical insights from building an evaluation framework for Noa Notes @ Docplanner - a system that transcribes and summarizes doctor-patient conversations. We will discuss our two-tier evaluation approach combining detailed factual assessment with style analysis, see how we leverage LLMs in the evaluation pipeline, and share specific examples of how prompt engineering improved our metrics. We'll also discuss challenges unique to the medical domain and how we addressed them.

- Event context: AI Tinkerers Poland - Second Meetup in Warsaw (January) — 2025-01-30 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_NPP2O6J7Te4

### [Alignment Platform for LLM-as-a-Judge](https://london.aitinkerers.org/talks/rsvp_BKcNgmzepMA)

A simple UI that's currently in beta that helps developers align an LLM-as-a-Judge to their use case.

- Event context: AI Tinkerers London - January Meetup — 2025-01-22 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_BKcNgmzepMA

### [Stable Diffusion ControlNets for controlled GenAI Data Viz](https://dc.aitinkerers.org/talks/rsvp_xEa4tHjvi6I)

Will Angel will demonstrate using Generative AI for data visualization, including the use of Control Nets and Stable Diffusion to accurately encode information in generated data visualizations to get the creativity of AI image generation for accurate data visualization. The demos will include multiple image generation models such as Flux and Stable Diffusion, some examples of prompt engineering, different methods for controlling image models and using ControlNet to structure the output of image generation into usable and correct charts. Link: https://github.com/DataDrivenAngel/gen_ai_viz_demo

- Event context: AI Tinkerers - DC Metro Meetup (January 15th 2025) — 2025-01-15 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_xEa4tHjvi6I

### [Finding Patent Prior Art with AI](https://chicago.aitinkerers.org/talks/rsvp_vHz4JF0Wu5U)

Patents form the cornerstone of innovation protection, with the USPTO processing over 600,000 applications annually representing billions in economic value. To get a patent, an invention must be genuinely novel—but proving novelty is a complex, time-consuming process that costs companies tens of thousands of dollars per application. Patent examiners and professionals spend countless hours searching for "prior art" that might show an invention already exists. In this talk, I will demonstrate an AI-powered system that not only identifies relevant prior art but provides detailed mapping between patent claims and existing disclosures, enabling patent examiners to quickly evaluate patentability and transform the examination process.

- Event context: AI Tinkerers Chicago January Meetup — 2025-01-14 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_vHz4JF0Wu5U

### [DreamGPT: turning a weakness of large language models into a strength](https://seattle.aitinkerers.org/talks/rsvp_f323DmW_6KY)

DreamGPT turns LLM hallucinations into a feature for divergent thinking, generating innovative ideas through unexpected connections. In this demo, I’ll show how DreamGPT amplifies hallucinations using fine-tuned prompt engineering and a custom backend pipeline, walking through the key code and algorithms. We’ll explore real-time examples of productive chaos, reframing a common AI flaw into a powerful tool for creative ideation.

- Event context: AI Tinkerers Seattle - December 2024 Meetup — 2024-12-12 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_f323DmW_6KY

### [Unlocking the 95% of unstructured data in construction](https://munich.aitinkerers.org/talks/rsvp_OAevBQmVyOI)

I’ll showcase how vertical applied AI can deliver end-to-end work results for processing, thousand of documents in construction companies, improving accuracy from 42% to 82%.

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

### [Toybox](https://toronto.aitinkerers.org/talks/rsvp_A41w5FMUrnQ)

An Jackbox TV-style party game that uses AI image generation as the primary mechanic. The game starts with players writing prompts to generate images using a given set of starting words. In subsequent rounds, each player receives an image from another player and has to try to create as similar an image as possible. The catch? They can't use the same words. Every round, more words are taken away until you're left trying to generate an image of a cat without using the words cat, kitten, feline, kitty, or any other cat-adjacent word.

- Event context: AI Tinkerers Toronto - Spooky Botober Meetup at Mozilla HQ — 2024-10-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_A41w5FMUrnQ

### [Shoulder Angel + Weave - an observable voice AI for personal accountability](https://sf.aitinkerers.org/talks/rsvp_4WpkMICnGx8)

Shoulder Angel is a voice AI that watches your screen and calls you if your activity gets out of line with your goals. A voice interface works here because it's harder to ignore than messages and push notifications. Voice is a natural way to engage and, ideally, gets out of your way. It uses W&B's Weave to trace LLM inputs and outputs and to speed development by evaluating prompts at every step.

- Event context: AI Tinkerers - Halloween Edition - October 2024 Meetup — 2024-10-23 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_4WpkMICnGx8

### [Real World Application: Helping Champions of Our Most Vulnerable w/ LLMs](https://chicago.aitinkerers.org/talks/rsvp_Ms5d_H7w1q4)

The Briefed.io team has been tinkering with AI to help social security disability applicants get the highest quality representation. Attorneys who represent these clients are underwater and need better tools to sift through large PDF documents to extract the most relevant diagnoses, procedures, and treatments that show their client is disabled. We've been tinkering with LLMs and various prompts to create structured output, 'score' results, and improve prompting and processes.

- Event context: AI Tinkerers Chicago October Meetup (First Anniversary!) — 2024-10-22 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_Ms5d_H7w1q4

### [500 prompt variations for semantic routing](https://toronto.aitinkerers.org/talks/rsvp_3KpAg305Ekw)

In this demo we'll cover using LLMs for intent classification and a bunch of ablations we ran. We'll also see if humans are better than LLMs at prompting.

- Event context: AI Tinkerers - Toronto - September 2024 Meetup — 2024-09-20 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_3KpAg305Ekw

### [AI-Driven Innovation: Revolutionizing Science and Technology Storytelling](https://la.aitinkerers.org/talks/rsvp_3FYDbXXjNpI)

Explore how the “Airwolf ~ The Chronicles Series” harnesses the power of AI to not revolutionize scientific and technical research, but also enhance project execution, and visual storytelling. This talk delves into the integration of AI across multiple facets of the project, including scriptwriting, scientific research, sponsorship strategy, technological innovation, and visual design. Learn about the deployment of ten specialized GPT agents that contributed to the entire production lifecycle, from generating visual representations of lost civilizations historical texts using text-to-video technology to developing an AI-driven eVTOL for groundbreaking exploration, and even integrating AI in the storytelling. By leveraging: LLMs, NLP, advanced GPT model training, AI workflows, TOT, advanced prompting, and supervised learning, this session offers valuable insights into the practical applications of AI in transforming traditional workflows and enhancing creative, technical and operational outcomes such as: Efficiency, quality, cost savings, innovation and engagement. Below is the pilot segment for your review (please do not share). Video: https://www.dropbox.com/scl/fi/8vj28kmpr8cnfp45v3dlf/V4-EDIT-AIRWOLF-30-JUIN.mov?rlkey=mmpq9u4ev8fe3d5b5hhwamv2k&st=ojz7edmr&dl=0 Password: AW2024

- Event context: Aug 28th - LA AI Tinkerers Meetup & Demos — 2024-08-29 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_3FYDbXXjNpI

### [LNKDNLM - A Linkedin job search engine](https://berlin.aitinkerers.org/talks/rsvp_lh44RVOHlbM)

It is a sister project of "Analyzing and Searching Job Listenings using LLMs". This project is focusing on how fast can we develop an open source end-to-end LLM product and deploy it and send it to the user base! In this talk I will discuss how can we use LLM to make it read job description and then filter out jobs instead of traditional keyword search! This saves us alot of time as job search is itself a job! My talk will include approaches I tried, including exploiting long context, different prompt engineering techniques, and how I deployed it on servers.

- Event context: AI Tinkerers Berlin - August 22 — 2024-08-22 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_lh44RVOHlbM

### [Automating building, deployment and maintenance of AI with AI agents](https://london.aitinkerers.org/talks/rsvp_pfh4cKzrGok)

Nowadays, everyone wants to integrate AI into their products or workflows, but building and maintaining AI models remains challenging, especially for non-experts. Weco uses AI agents to help developers implement AI features without dealing with low-level details like prompt engineering, model selection, output structuring, or writing machine learning code. Users submit task descriptions in natural language, and our system provides an API endpoint for the requested AI feature.

- Event context: AI Tinkerers London - July Meetup — 2024-07-09 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_pfh4cKzrGok

### [Pick-Em's Bot](https://seattle.aitinkerers.org/talks/rsvp_H6MqDp0e2zM)

This is an LLM agent built that scrapes sports articles and team stats to predict winners for ESPN's Pick-Em's game. For the 2023 NFL season, this agent won my local group's pick-em's competition and came in the top 15% across all of ESPN's users (~one million users played). The top player across all of ESPN for 2023 correctly chose 195 games (~71%). This agent correctly chose 163 (~60%).

- Event context: AI Tinkerers Seattle - June 2024 — 2024-06-07 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_H6MqDp0e2zM

### [YouSim](https://seattle.aitinkerers.org/talks/rsvp_hYVHhU5uSoU)

You've hard of worldsim and websim, now there's YouSim. Leveraging the inherent theory-of-mind capabilities to create an experience where an agent tries to model you the user.

- Event context: AI Tinkerers Seattle - June 2024 — 2024-06-07 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_hYVHhU5uSoU

### [Choose Your Own Adventure](https://amsterdam.aitinkerers.org/talks/rsvp_gyiitroBNfc)

As a fun side-project at ML6 we created a Choose Your Own Adventure game similar to the identically named book series. The player assumes the role of the protagonist and makes choices that determine the main character's actions and the plot's outcome. The key here is that the game is fully generated using Generative AI. This means that the story is generated with through an LLM, the visuals with Stable Diffusion, and the sounds with Music Gen.

- Event context: AI Tinkerers Amsterdam - Inaugural Meetup - May — 2024-05-23 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_gyiitroBNfc

### [AI agents for investment research](https://la.aitinkerers.org/talks/rsvp_WaoS2XyFySY)

Using various ai personas to do the aspects of financial analysis based on their personas (fundamental analysis, technical analysis, growth and innovation analysis etc)

- Event context: May 21st - LA AI Tinkerers Meetup & Demos — 2024-05-22 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_WaoS2XyFySY

## Related Technologies

- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [LLMs](https://aitinkerers.org/technologies/llms) ([Markdown](https://aitinkerers.org/technologies/llms.md)) — 83 public demos
- [Stable Diffusion](https://aitinkerers.org/technologies/stable-diffusion) ([Markdown](https://aitinkerers.org/technologies/stable-diffusion.md)) — 32 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos
- [function calling](https://aitinkerers.org/technologies/function-calling) ([Markdown](https://aitinkerers.org/technologies/function-calling.md)) — 11 public demos
- [Generative AI](https://aitinkerers.org/technologies/generative-ai) ([Markdown](https://aitinkerers.org/technologies/generative-ai.md)) — 45 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [theory-of-mind](https://aitinkerers.org/technologies/theory-of-mind) ([Markdown](https://aitinkerers.org/technologies/theory-of-mind.md)) — 2 public demos
- [AI agent](https://aitinkerers.org/technologies/ai-agent) ([Markdown](https://aitinkerers.org/technologies/ai-agent.md)) — 8 public demos
- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos
- [AI image generation](https://aitinkerers.org/technologies/ai-image-generation) ([Markdown](https://aitinkerers.org/technologies/ai-image-generation.md)) — 1 public demo

## More Results

- Next: https://aitinkerers.org/technologies/prompt-engineering.md?page=2