Your First 30 Minutes with G6¶
This tutorial walks you through connecting G6, exploring its capabilities, running your first goal, and seeing the self-training loop in action.
Prerequisites¶
- G6 installed — see Setup
- Claude Code installed and working (for the MCP steps)
Minutes 0-3: Connect¶
Add the G6 MCP server to Claude Code:
claude mcp add g6 --transport sse \n --url https://g6solver.com/mcp/sse \n --header "Authorization: Bearer YOUR_API_KEY"
Verify the connection by asking Claude:
"Check the G6 system status"
You should see a response showing the system is healthy with 270 registry components available.
Minutes 3-8: Discover¶
G6 has built-in discovery tools. Try these natural language queries:
"What G6 tools are available for data analysis?"
This invokes nav_recommend and returns relevant components like adapt_pandas, adapt_sklearn, and align_evals.
"Give me an overview of the G6 system"
This invokes guide_system_overview and explains the architecture, component model, and available intelligence classes.
"Find G6 tools that can verify safety properties"
This shows the formal methods and CSF components — the tools G6 uses for formal property checks (proven where a named backend is installed and the property is formally specified) and for pre-execution risk bounds (CSF: policy priors, not guarantees).
Minutes 8-13: Your first goal¶
Let's decompose a simple goal. Ask Claude:
"Use G6 to decompose this goal: Research the current state of quantum error correction and summarise the key approaches in 300 words"
G6 will:
- Break the goal into subtasks (search, filter, synthesise)
- Identify which components to use (
ctx_search,ctx_rag, LLM summarisation) - Estimate resource requirements
- Return a SearchTree showing the decomposition
You'll see the goal broken into manageable steps with resource bounds for each.
Minutes 13-18: Run a pipeline¶
G6 has pre-built pipeline templates. Try:
"Run the G6 research pipeline on: advances in protein structure prediction since AlphaFold 3"
This executes the research template pipeline which chains:
- Search — finds relevant sources via
ctx_search - Retrieve — fetches and parses documents via
ctx_rag - Synthesise — produces a structured summary with citations
The result includes the summary, sources used, and confidence scores.
Minutes 18-23: Add safety¶
Now let's see the safety framework in action. Ask Claude:
"Use G6 to verify this claim using formal methods: If all inputs are positive and the function multiplies them pairwise, then all outputs are positive"
G6 will:
- Formalise the claim into propositional logic
- Run the built-in DPLL solver (no external dependencies needed)
- Return SAT/UNSAT with a proof or counterexample
This is the same formal verification pipeline CSF uses to check safety properties before code execution — proven when the named backend returns verified=True, otherwise recorded as auditable evidence, not proof.
Minutes 23-28: Self-training preview¶
The self-training loop is G6's core innovation. Here's how it works conceptually:
"Use G6 to explain how the self-training loop works"
The 7-step cycle:
- Audit — assess current harness maturity
- Observe — gather execution traces
- Orient — classify failure modes
- Diagnose — identify root causes
- Decide — choose improvement strategy
- Improve — modify prompts, tools, or logic
- Record — update competence model
Each iteration improves the harness without retraining the underlying model. This is what enables G6 to achieve 58-77% accuracy improvements on validated benchmarks.
Minutes 28-30: What's next¶
You've now seen G6's four core capabilities:
| Capability | What you tried |
|---|---|
| Discovery | nav_recommend, guide_system_overview |
| Goal decomposition | Breaking a research task into subtasks |
| Formal verification | Proving a mathematical property |
| Pipeline execution | Running the research template |
Next steps¶
- Research Pipeline tutorial — build a complete research workflow with citations
- Safety-Guarded Goals — add CSF guardrails and breakpoints to any goal
- Custom Component — build your own G6 extension component
- Use Cases — 13 real-world application recipes
- Example goals — graduated
GoalInputJSON files ship with G6; ask the GUI to load one, or see Use Cases
Explore by persona¶
- Business operators: See the Business Operators quick start
- Domain workers: Ask Claude to run any of the 39 job agents (e.g., "Use G6 job_researcher to...")
- Engineers: Check the Architecture docs and API reference