Dash

Self-learning data agent that grounds answers in 6 layers of context.

Dash is a self-learning data agent that gets better with every query.

Most Text-to-SQL agents are stateless. They make mistakes, you fix them, then they make the same mistake again because every session starts fresh. Dash fixes this by grounding its answers in 6 layers of context and learning from every run.

Checkout the repo for more details.

How It Works

Dash retrieves relevant context at query time via hybrid search, generates grounded SQL, executes it, and delivers insights.

The Six Layers of Context

Layer	Purpose	Source
Table Usage	Schema, columns, relationships	knowledge/tables/*.json
Human Annotations	Metrics, definitions, business rules	knowledge/business/*.json
Query Patterns	SQL that is known to work	knowledge/queries/*.sql
Institutional Knowledge	Docs, wikis, external references	MCP (optional)
Learnings	Error patterns and discovered fixes	Agno LearningMachine
Runtime Context	Live schema changes	introspect_schema tool

Self-Learning

Dash improves without retraining or fine-tuning through two complementary systems:

System	Stores	How it evolves
Knowledge	Validated queries, table schemas, business rules	Curated by your team and refined by Dash
Learnings	Error patterns, column quirks, team conventions	Managed automatically by the Learning Machine

When a query fails because position is TEXT and not INTEGER, Dash saves that. Next time, it knows. When your team is focused on IPO prep, Dash learns that “revenue” means ARR, not bookings, and that the board wants cohort retention broken out by enterprise vs SMB.

Insights, Not Just Rows

Dash reasons about what makes an answer useful, not just technically correct.

Question: Who won the most races in 2019?

Typical SQL Agent	Dash
Hamilton: 11	Lewis Hamilton dominated 2019 with 11 wins out of 21 races, more than double Bottas’s 4 wins. This performance secured his sixth world championship.

Run Locally

git clone https://github.com/agno-agi/dash.git && cd dash

cp example.env .env
# Edit .env and add your OPENAI_API_KEY

docker compose up -d --build

# Load sample data (F1 races 1950-2020) and knowledge base
docker exec -it dash-api python -m dash.scripts.load_data
docker exec -it dash-api python -m dash.scripts.load_knowledge

Confirm Dash is running at http://localhost:8000/docs.

Connect to the control plane

1. Open os.agno.com and sign in
2. Click Add OS → Local
3. Enter http://localhost:8000

Deploy to Railway

railway login
./scripts/railway_up.sh

The script provisions PostgreSQL, configures environment variables, and deploys your application.

Then load your data and knowledge in production:

railway run python -m dash.scripts.load_data
railway run python -m dash.scripts.load_knowledge

Connect via the control plane:

1. Open os.agno.com
2. Click Add OS → Live
3. Enter your Railway domain

Example Prompts

Try these on the sample F1 dataset:

• Who won the most F1 World Championships?
• How many races has Lewis Hamilton won?
• Compare Ferrari vs Mercedes points 2015-2020

Adding Your Own Data

Dash works best when it understands how your organization talks about data. The knowledge base lives in three directories:

knowledge/tables/ for table metadata: schema descriptions, column meanings, data quality notes.

knowledge/queries/ for validated SQL patterns that are known to work.

knowledge/business/ for metric definitions, business rules, and common gotchas.

Load or update knowledge at any time:

python -m dash.scripts.load_knowledge            # upsert changes
python -m dash.scripts.load_knowledge --recreate  # fresh start

Run Evals

Dash ships with an evaluation suite: string matching, LLM grading, and golden SQL comparison.

docker exec -it dash-api python -m dash.evals.run_evals         # string matching
docker exec -it dash-api python -m dash.evals.run_evals -g      # LLM grader
docker exec -it dash-api python -m dash.evals.run_evals -g -r   # both + golden SQL

Source

For architecture details, knowledge format reference, and local development setup, see the GitHub repo.