RAG Studio Notes
Chat loaded

A|A|A AI

Multi-expert AI system with memory

Drop files here to attach
Agent
0%
Context window

Train Data

Training engine

Qwen 3.6 / Unsloth = domain adaptation, SFT, and GRPO. Full = nanoGPT (PyTorch). Tiny = microGPT (pure Python).

Qwen 3.6 / Unsloth

Data Sources

Connect S3, PostgreSQL, DWH (BigQuery, Redshift, Snowflake), or use local files. Credentials are stored securely.

Training runs

Data is trained in chunks to avoid overfitting and memory issues. Each run has a queue of chunks.

Training dashboards

Metrics and parameters per run. Status, chunks progress, and loss.

Chunk queue

Chunks are processed one by one (or in small batches). Current chunk and progress are shown below.

Run Full training

Starts nanoGPT train.py. Select your run to train on your data; otherwise uses Shakespeare demo.

Training parameters

If nanoGPT is missing: clone next to the app (git clone https://github.com/karpathy/nanoGPT ../nanoGPT) or set NANOGPT_PATH to the nanoGPT folder.

Samples (generate from trained nanoGPT)

Generate text from a checkpoint. Run Full training first or select an existing checkpoint.

Autotrain

Autonomous LLM training: the agent experiments with architecture, hyperparameters, and optimizers. Each iteration trains for a fixed time budget, evaluates val_bpb, keeps or discards changes.

Orchestration

Manage work by status. Add tasks, move them through stages, run with the same AI pipeline as chat.

Workflows

Triggers
Manual
Webhook
Schedule
Actions
Agent task
Query (AAAAI)
MCP tool
🖥Mac/PC action
Control flow
Approval
Condition
Split
Merge
Loop
Integrations
In this workflow

MCP Marketplace

Enable MCP (Model Context Protocol) plugins for ChatGPT, Claude, Gemini, and this product. Toggle to install or disable.

Platform:
Loading MCP catalog…