> ## Documentation Index > Fetch the complete documentation index at: https://docs.useslip.xyz/llms.txt > Use this file to discover all available pages before exploring further. # AI Rulebook prompt guide > Structured interpretation, exact labels, and deterministic rejection rules. # AI Rulebook prompt guide `@slip/sdk/ai` uses AI SDK structured output. The model emits a semantic team-stat expression and complete integer bands. It never emits trusted fixture IDs, stat keys, fees, deadlines, stakes, or settlement values. Consumer labels are immutable input. The prompt names them in exact order, and deterministic validation rejects any rename or reorder. The compiler then derives canonical TxLINE keys and rejects gaps, overlaps, missing outcomes, duplicate labels, player props, ambiguous periods, and unsupported statistics. Compilation is fixture-aware rather than phrase-only. The authenticated TxLINE lookup supplies the teams, competition, kickoff, fixture ID, and current game state alongside the room's question and exact ordered poll labels. Context can disambiguate references such as "home", "away", or the team names, but it cannot expand the proof contract: event-order markets such as "who scores first" remain unsupported until Slip has an on-chain ordered-event expression and corresponding TxLINE Merkle proof verifier. Use examples that vary meaning rather than phrases: * binary: both teams score, with `No` and `Yes`; * three outcomes: home win, draw, away win; * five outcomes: total goals or corners split into five complete bands; * periods: first-half or second-half cards and corners; * rejection: player shots, possession, or incomplete ranges. Run the MBP provider test with a real configured Ollama model: ```bash theme={null} SLIP_RULE_PROVIDER=ollama \ SLIP_RULE_MODEL=qwen3.6:35b-mlx \ OLLAMA_BASE_URL=http://:11434/api \ pnpm --filter @slip/sdk test:ai:ollama ``` This command is credential- and network-dependent. Do not replace it with fixed model output.