Skip to main content

​
Key Concepts

Learn the foundational concepts that make SignalPilot a powerful context orchestration engine.

​
Context Aggregation

​
What is Context?

In SignalPilot, context refers to all the information the AI agent can access to help with your analysis:

Kernel State

Variables, dataframes, and objects in your Jupyter kernel

Database Schemas

Table metadata, column types, relationships

dbt Models

Model definitions, lineage, documentation

Query History

Past queries, performance stats

Collaboration Tools

Slack threads, Jira tickets, design docs

Analysis History

Past investigations, conclusions

​
Where Does Context Come From?

SignalPilot uses MCP (Model Context Protocol) to aggregate context:
Built-in context sources:
  • Jupyter kernel (variables, state)
  • Local files (notebooks, CSVs)
  • Database connections (via SQL)

​
How is Context Used?

When you ask a question, SignalPilot:
  1. Resolves relevant context (parallel, non-blocking)
  2. Aggregates it into the system prompt
  3. Passes it to the LLM for reasoning
  4. Uses it to generate code grounded in reality
This is why SignalPilot doesn’t hallucinate table names — it has real schema metadata.

​
Agents & Modes

SignalPilot has three modes that control how autonomous the agent is:

​
Agent Mode (Fully Autonomous)

Agent Mode

The agent can plan, write, and execute code autonomously in your notebook.Use when:
  • Exploring new datasets
  • Iterating on analysis
  • You trust the agent to execute code
Control:
  • Planning Mode: Requires approval before execution
  • Hooks: Enforce custom constraints

​
Hands-On Mode (Suggested Code)

Hands-On Mode

The agent suggests code, but you manually execute it in cells.Use when:
  • Learning SignalPilot
  • Working with sensitive data
  • You want full control over execution
Workflow:
  1. Ask a question
  2. Agent writes code in a cell
  3. You review and execute manually

​
Ask Mode (Read-Only)

Ask Mode

The agent only answers questions — no code execution.Use when:
  • Asking conceptual questions
  • Getting explanations
  • Understanding your data model
Example: “What’s the difference between revenue and revenue_net in my schema?”
Switch modes in the SignalPilot panel based on your task.

​
Planning & Iteration

SignalPilot supports multi-step workflows with planning and iteration:

​
Planning Mode

1

Agent creates a plan

You ask: “Why did revenue drop last week?”Agent responds with:
Plan:
1. Load revenue data for last 2 weeks
2. Compare to previous periods
3. Check for anomalies in key segments
4. Cross-reference with deployment logs
2

You approve or modify

Review the plan and approve, or ask for changes.
3

Agent executes the plan

The agent executes each step, streaming results in real-time.
Use Planning Mode for high-stakes analysis or production queries.

​
Iteration

SignalPilot can iterate on analysis: 
You: Analyze revenue trends
Agent: [Creates visualization]

You: Break it down by product category
Agent: [Adds category breakdown, updates viz]

You: What's driving the spike in Category B?
Agent: [Investigates Category B specifically]
Each question builds on previous context — SignalPilot remembers the conversation.

​
@ Mentions (Context Scoping)

Use @ mentions to scope context to specific sources:

​
Mention a Table

@revenue_table show me top 10 customers by revenue
SignalPilot will focus on the revenue_table schema.

​
Mention a dbt Model

@dbt:fct_revenue what's the lineage for this model?
SignalPilot will load the dbt model definition and lineage.

​
Mention a Slack Thread

@slack:data-team-channel what did we decide about revenue calculations?
SignalPilot will search the Slack channel for relevant discussions.
@ mentions are especially useful when working with multiple data sources.

​
Next Steps

Installation

Install SignalPilot

Quickstart

First analysis in 5 minutes

How It Works

Deep dive into architecture

Task Guides

Follow real-world examples