# Firestore Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/firestore
> Markdown URL: https://aitinkerers.org/technologies/firestore.md
> Technology record last updated: 2026-02-23T20:57:58Z
> Generated: 2026-09-21T18:42:50Z

Firestore is a serverless, NoSQL document database: It delivers real-time data synchronization and elastic scaling for web, mobile, and Gen AI applications.

This is a fully managed, enterprise-grade document database built by Google Cloud. It utilizes a flexible NoSQL data model (documents in collections) and ensures strong consistency with ACID transactions. The core value proposition is real-time synchronization across all clients (iOS, Android, Web) and robust offline support, enabling reliable user experiences. Firestore scales automatically from zero to global traffic, offering up to 99.999% availability with multi-region replication. You can leverage native SDKs, a powerful query engine, and even use a MongoDB-compatible API for quick integration.

- Official technology site: https://cloud.google.com/firestore
- Public AI Tinkerers demos and talks: 4
- Result page: 1 of 1

## Recent Public Talks and Demos

### [The AI-First Development Workflow](https://st-louis.aitinkerers.org/talks/rsvp_VHAgcAJsbGY)

This presentation details a paradigm shift in software engineering where AI is the primary builder and the human is the Principal Orchestrator. The Core: It replaces traditional human team roles with specialized, adversarial AI agents. The Rigor: It implements the Planning Gauntlet (Architect/Critique/Revise) and the Hardening Cycle (Review/Fix/Test) to ensure that solo output meets industrial production standards. The Impact: It enables a single engineer to operate as a full-force squad, delivering mission-critical software with zero-drift and zero-bug tolerance. This presentation describes the workflow I've developed building production software using AI at my day job (IntelePeer) as well as in my side projects (IgnitionAI)

- Event context: AI Tinkerers – St. Louis Meetup: February 4, 2026 — 2026-02-04 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_VHAgcAJsbGY

### [Using NLP/ML and cloud functions to automate peer groups.](https://nyc.aitinkerers.org/talks/rsvp_MZuKe3l91uQ)

Code walk through of a VueJS front end launching late 2024 or early 2025 using machine learning/NLP over GCP cloud functions, Firestore / Cloud Run backend to automatically create peer groups. Would show Python code over Google Cloud Functions (gen2) using models (not actual subscribers!) we've been using in development in code calling SpaCy libraries and Regex functions to extract keywords, and then use those, currently in a Dice/Sorenson algorithm on web-based device (phone or laptop) to create peer groups.

- Event context: AI Tinkerers - New York City - November 2024 Meetup | Win Meta Ray-Bans — 2024-11-12 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_MZuKe3l91uQ

### [Dynamic Structured Record Augmentation of LLMs](https://nyc.aitinkerers.org/talks/rsvp_o5c_H5O-V5U)

An approach that enables LLMs to dynamically create, manipulate, and retrieve structured records in a NoSQL database. This approach serves as an alternative to vector-based RAG, creating a data store that's both human and model-readable. Demoed in a mobile app for tracking daily records (e.g., cat medication, exercise, expenses) to illustrate practical applications. The core mechanism I’m focusing on is prompting for structured Tool/Function completions to do CRUD operations on structured records - to capture, remember, retrieve, and query against information the user wants to reference later. The schema / structure of the records themselves is also frictionlessly created / edited by the model. Both the table structures and the records themselves are stored in a NoSQL database. The “magic” is in actively managing the system prompt on the chat chain to provide full context and dynamically generate the functions available as tools for each completion. This “dynamic but structured” approach uses JSON Schema to define, communicate, and validate functions. A technical challenge was dynamically generating and validating table / context-specific functions. I did this by embracing JSON Schema in the table definition as well as the functions presented to the LLM. I’ll focus my demo on the prompt, the Firestore database, and the function building. This is a Flutter app that runs on iOS and Android. I’m very excited to share this approach with the other Tinkerers - shown as a fully working implementation that can be tried out, as well as access to all the code.

- Event context: AI Tinkerers July Meetup — 2024-07-24 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_o5c_H5O-V5U

### [Sift Social AI: An AI Social Media Analyst](https://chicago.aitinkerers.org/talks/rsvp_WrKas5P5Vow)

Sift Social is an AI social media analyst that can help you identify the best content to post, the best influencers to work with and the best UGC to boost. Social Media Data Collector Sift Social is an AI agent powered with the most robust social media data collection workflow on the market Hashtag Collector Comment Analysis Influencer Identification + Outreach AI Data Analyst Using an advanced LLM technology, Sift Social is able to turn TikTok trends into strategic insights Talk Directly To Your Data In Plain English Automate Data Analytic Workflows Assess Influencer Impact

- Event context: AI Tinkerers Chicago May Meetup — 2024-05-07 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_WrKas5P5Vow

## Related Technologies

- [Cloud Run](https://aitinkerers.org/technologies/cloud-run) ([Markdown](https://aitinkerers.org/technologies/cloud-run.md)) — 12 public demos
- [Android](https://aitinkerers.org/technologies/android) ([Markdown](https://aitinkerers.org/technologies/android.md)) — 11 public demos
- [BigQuery](https://aitinkerers.org/technologies/bigquery) ([Markdown](https://aitinkerers.org/technologies/bigquery.md)) — 1 public demo
- [Cloud SQL](https://aitinkerers.org/technologies/cloud-sql) ([Markdown](https://aitinkerers.org/technologies/cloud-sql.md)) — 3 public demos
- [Cloud Storage](https://aitinkerers.org/technologies/cloud-storage) ([Markdown](https://aitinkerers.org/technologies/cloud-storage.md)) — 1 public demo
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Flutter](https://aitinkerers.org/technologies/flutter) ([Markdown](https://aitinkerers.org/technologies/flutter.md)) — 24 public demos
- [Google Cloud Functions (Gen 2)](https://aitinkerers.org/technologies/google-cloud-functions-gen-2) ([Markdown](https://aitinkerers.org/technologies/google-cloud-functions-gen-2.md)) — 1 public demo
- [Imagen](https://aitinkerers.org/technologies/imagen) ([Markdown](https://aitinkerers.org/technologies/imagen.md)) — 10 public demos
- [JSON Schema](https://aitinkerers.org/technologies/json-schema) ([Markdown](https://aitinkerers.org/technologies/json-schema.md)) — 9 public demos
- [NoSQL](https://aitinkerers.org/technologies/nosql) ([Markdown](https://aitinkerers.org/technologies/nosql.md)) — 1 public demo
- [Pandas AI](https://aitinkerers.org/technologies/pandas-ai) ([Markdown](https://aitinkerers.org/technologies/pandas-ai.md)) — 1 public demo
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 106 public demos
- [Pub/Sub](https://aitinkerers.org/technologies/pub-sub) ([Markdown](https://aitinkerers.org/technologies/pub-sub.md)) — 2 public demos
- [spaCy](https://aitinkerers.org/technologies/spacy) ([Markdown](https://aitinkerers.org/technologies/spacy.md)) — 10 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos
- [Vertex AI](https://aitinkerers.org/technologies/vertex-ai) ([Markdown](https://aitinkerers.org/technologies/vertex-ai.md)) — 31 public demos
- [Vue](https://aitinkerers.org/technologies/vue) ([Markdown](https://aitinkerers.org/technologies/vue.md)) — 8 public demos