Results for “experiment”

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Manage Arize datasets and examples using the ax CLI: create, list, get, export, and append datasets for evaluation and experimentation.

Run autonomous optimization loops that iteratively improve artifacts against evaluators using hypothesis tree refinement, without overfitting.

Compiles research inputs—PDFs, code, logs, notes—into structured Agent-Native Research Artifacts with cognitive and physical layers.

Train and experiment with a minimal GPT implementation in ~300 lines of PyTorch, from character-level Shakespeare to GPT-2 scale.

Run interpretability experiments on neural network internals using nnsight, with optional NDIF remote execution for massive models.

Design, simulate, and run quantum circuits on Google Quantum AI and partner hardware using Cirq, including noise modeling and characterization experiments.

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

Design, simulate, and run quantum circuits on Google Quantum AI hardware and other providers using Cirq, including noise modeling and characterization experiments.

Automates scientific research workflows from data analysis to publication, orchestrating multiple agents for hypothesis generation, methodology development, computational experiments, and LaTeX paper writing.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Pattern for creating new Colab notebooks. Trigger when: (1) Creating a new notebook for experiments, (2) Adding notebook-based functionality, (3) Agent or validation notebooks, (4) Any notebook that uses GPU training infrastructure.

Train reinforcement learning models using torchforge, Meta's PyTorch-native RL library for scalable, algorithm-focused experimentation with GRPO, DAPO, and custom loss functions.

Runs an autonomous optimization loop that iteratively improves an artifact against an objective and evaluator using Hypothesis Tree Refinement, with subagent executors in isolated git worktrees.

Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.

Debug LLM applications using the Phoenix CLI: fetch traces, analyze errors, structure trace review with open and axial coding, inspect datasets, review experiments, and query the GraphQL API.

Records research provenance as a post-task epilogue, scanning conversation history to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with provenance tags.

ML / research person pack for Content Factory. Use when the user says person ml, @person-ml, ML person, research scientist person, or LLM researcher person. Auto-loads ml-research-engineer, llm-researcher, ai-research-scientist plus experiment-tracking, evaluation, cf-llm-model-usage.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Derive a portable product-idea kickoff prompt from the invoking repository for use with $idea-scope-brief in a different repository. Use when a repo suggests an adjacent product, SaaS, devtool, library, workflow, or experiment worth briefing elsewhere, but the user wants an idea prompt rather than code extraction or repo creation.

Identifies the weakest samples per ground-truth label in NVIDIA TAO VCN Classify experiments by running a Docker container that performs threshold sweep, weakness scoring, and per-lighting expansion, then surfaces top-K weak samples for downstream augmentation or relabeling.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Route LangSmith work into one workflow packet before touching SDK code. Use when the user needs LangSmith tracing, offline evals, annotation/review queues, prompt-registry decisions, audit/gap review, or cross-service trace propagation for an LLM app or agent workflow. Choose one packet: trace-debug, eval, review, prompt-registry, propagation, or audit. Triggers on: LangSmith, LangChain tracing, `@traceable` / `traceable`, `wrap_openai` / `wrapOpenAI`, datasets, experiments, annotation queues, feedback criteria, Prompt Hub, run trees, trace IDs, or production confidence for an AI feature. Not for generic SLO/alert design, non-LangSmith deployment orchestration, or runtime guardrails outside LangSmith.

Predict biomolecular complexes with Chai-1, an open AlphaFold3-style model that folds multi-entity assemblies (proteins, ligands, nucleic acids) from a single typed FASTA — strong on antibody–antigen and protein–ligand complexes, with optional MSA and restraint inputs. Use when predicting an antibody–antigen complex, folding a mixed protein/ligand/nucleic-acid assembly described in one FASTA, or generating a complex with experimental restraints. For binding-affinity prediction or a ligand-focused co-fold prefer alterlab-boltz; for protein-only or protein–protein folding prefer alterlab-alphafold; to dock into a fixed receptor prefer alterlab-diffdock. Part of the AlterLab Academic Skills suite.

Use when developing in packages/agent-core-v2 (the DI × Scope agent engine) — adding or modifying a domain Service, choosing a LifecycleScope, wiring DI dependencies, splitting a domain across scopes, owning or migrating a config section, gating behavior behind an experimental flag, raising coded errors, working on the permission system, writing DI/Scope tests, porting business logic from agent-core (v1) to v2, triaging a main-branch commit against v2, or exposing a v2 domain over server-v2 while keeping the /api/v1 wire contract compatible with released clients. Self-contained guide organized by development stage (orient → design → implement → test → verify) plus align workflows for v1→v2 migration, main-branch commit triage, and server-v2 wire exposure; each file carries the rules, examples, and red lines for its step.