Skip to content

Section A · 6 prompts · 5 free

Agent Design

The reasoning core: decision contracts, planning, risk envelopes, deliberation, self-critique.

6 prompts

A1Free

Decision Loop Scaffold

The core decision contract an LLM-orchestrated agent uses each cycle. Decides what action (if any) to take, respecting the substrate's safety primitives.

A2Free

Tool-Use Planning Template

Plan a sequence of tool calls (price fetches, position queries, oracle reads, etc.) before committing to an action. Reduces the "agent acts then fetches data" failure mode.

A3Free

Risk Envelope Reasoner

Evaluate whether a proposed action respects the configured risk envelope, including derived constraints (concentration, drawdown headroom, time-of-day if configured).

A4Free

Multi-Step Deliberation Chain

When a decision is non-trivial (e.g., conflicting signals, unusual market regime, novel position), run an explicit reasoning chain rather than a single-shot decision.

A5Free

Self-Critique Loop

Before submitting any action, have the agent critique its own reasoning. Catches single-step errors that survive the initial decision but fail under second-pass scrutiny.

A3-QW Paid

Risk envelope · quirks-wired variant

The A3 reasoner with venue parameters bound live to the Quirks feed — thresholds update when the venue changes, not when you remember to.