Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

Coverage configuration and thresholds

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

End-to-end DAG execution orchestrator that decomposes arbitrary tasks into agent graphs and executes them in parallel. The intelligence layer that makes DAG Framework operational.

Self-referential loop until task completion with architect verification

>

Quantify values with uncertainty bounds. Use when estimating metrics, calculating risk scores, assessing magnitude, or measuring any quantifiable property.

Assign labels or categories to items based on characteristics. Use when categorizing entities, tagging content, identifying types, or labeling data according to a taxonomy.

Watch and report current state of a target system, process, or entity. Use when monitoring status, inspecting live systems, checking current conditions, or observing runtime behavior.

>

>

Change persistent state with checkpoint and rollback support. Use when modifying files, updating databases, changing configuration, or any operation that permanently alters state.

>

Create representation of current world state for a domain. Use when modeling system state, building world models, capturing entity relationships, or establishing baseline snapshots.

Forecast future states or outcomes based on current data and trends. Use when estimating future values, projecting trajectories, forecasting outcomes, or anticipating system behavior.

Define how state changes over time through rules, triggers, and effects. Use when modeling state machines, defining workflows, specifying event handlers, or documenting system dynamics.

Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies, tracing effects, or building causal models.

Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.

Anchor claims to evidence from authoritative sources. Use when validating assertions, establishing provenance, verifying facts, or ensuring claims are supported by evidence.

Enforce policies, guardrails, and permission boundaries; refuse unsafe actions and apply least privilege. Use when evaluating actions against policies, checking permissions, or reducing scope to...