AI Agent & Automation Workflows

Build agentic LLM-driven robotic manipulation pipelines using the ALRM framework pattern: a ReAct-style reasoning loop with dual execution modes (Code-as-Policy for direct code generation, Tool-as-Policy for iterative tool-based execution). Generates modular robot control code with closed-loop planning, observation, and replanning.

Confidence-guided self-refinement for adaptive reasoning. Implements the CoRefine pattern: assess confidence in each reasoning step, then decide whether to halt, re-examine, or try a different approach -- reducing wasted compute while maintaining accuracy. Use when: 'solve this step by step with self-correction', 'refine your reasoning until confident', 'adaptively debug this problem', 'use confidence-guided refinement', 'self-correct with backtracking', 'try different approaches if stuck'.

Detect and fix cross-lingual evaluation instabilities in LLM-as-a-judge pipelines. Use when: 'audit my multilingual eval pipeline', 'check if my LLM judge is stable across languages', 'set up cross-lingual evaluation', 'calibrate judge scoring for non-English languages', 'diagnose ranking inversions in multilingual benchmarks', 'build controlled generation tests for eval reliability'.

Diagnose and mitigate feedback-loop risks (bias amplification, hallucination propagation, exposure polarization) in LLM-powered recommender systems using a role-aware, phase-wise diagnostic framework. Use when: 'audit my recommendation pipeline for bias', 'check feedback loop risks in my LLM recommender', 'diagnose hallucination propagation in recommendations', 'build a feedback-loop simulation for my recommender', 'trace popularity bias through my recommendation cycles', 'add risk monitoring to my LLM-based ranking system'.

Build multi-agent systems that discover causal rules from event sequences using specialized agents (causal discovery, contextual information, orchestrator). Use when asked to: 'find causal patterns in event logs', 'build a multi-agent diagnostic system', 'automate rule discovery from sequences', 'generate Boolean fault rules from data', 'create an agent pipeline for causal reasoning', 'detect error patterns in time-series events'.

Classify and diagnose intermittent CI/CD job failures from execution logs using the FlaXifyer few-shot approach and LogSift log reduction.

Automate library migrations by synthesizing reusable code transformation scripts. Uses LLM-generated migration examples distilled into structured, testable rewrite rules (PolyglotPiranha / comby / semgrep patterns). Triggers: 'migrate from X to Y library', 'generate migration script', 'automated API migration', 'rewrite all uses of library X', 'create transformation rules for migration', 'synthesize code edits for library swap'.