「llm」の検索結果

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

日本語の概要は準備中です。原文の説明を表示しています。

Busabase App-in-Skill dashboard over a fixed, deterministic mock user-behavior funnel dataset (browse → search → compare → booking attempt/abandon → complete) for a generic consumer booking product. Use when the user invokes $kelly-behavior-predict or /kelly-behavior-predict, wants to review funnel drop-off, per-segment predicted next actions, or backtest a rule-based "predicted next action" heuristic against a mock historical sample. Fully deterministic mock data and a hand-recomputable rule — never a real ML/LLM model, never a live system.

日本語の概要は準備中です。原文の説明を表示しています。

Busabase App-in-Skill review queue that scores candidate SME financing deals (revenue-based/RBF-style credit) with a deterministic, fully auditable rule-based rubric — never an LLM or API call. Use when the user invokes $kelly-deal-scorer or /kelly-deal-scorer, wants to review a deal-underwriting queue, score financing candidates, compute a composite score breakdown, see a suggested revenue-share rate range, or record approve/send-back/reject decisions for a private-credit or RBF-style lending pipeline.

日本語の概要は準備中です。原文の説明を表示しています。

Busabase App-in-Skill dashboard visualizing a generated MOCK fleet of LLM agents running behind a shared AI gateway for a generic organization. Use when the user invokes $kelly-agent-observability or /kelly-agent-observability, wants to review agent health, call volume, latency, error rates, cost, or trace-level chain breaks across an agent fleet. This is a demo/reference dashboard over a generated mock fleet snapshot seeded into Busabase by a trusted script — never a live monitoring integration, never a real gateway or real agents.

日本語の概要は準備中です。原文の説明を表示しています。

Review board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything.

日本語の概要は準備中です。原文の説明を表示しています。

Busabase-backed App-in-Skill control panel / kanban board for a BD or sourcing team triaging merchant and business financing leads for a lender or investment fund. Use when the user invokes $kelly-lead-funnel or /kelly-lead-funnel, wants to review the deal sourcing pipeline, funnel, lead board, or asks to move a lead's stage, reject a lead, add a note, score a lead, or see funnel conversion rates. Deterministic rule-based lead scoring only — never an LLM call — and never sends outreach, signs term sheets, or moves money.

日本語の概要は準備中です。原文の説明を表示しています。

Busabase-backed App-in-Skill low-code agent configuration and governance console for a platform team. Use when the user invokes $kelly-agent-builder or /kelly-agent-builder, wants to review or edit a catalog of mock LLM agent configs, check quota usage, find configs that need attention, move a draft to live, pause a live agent, or archive an agent. Mock config/governance console only — it never provisions or calls any real agent.

日本語の概要は準備中です。原文の説明を表示しています。

Detect NTLM relay attacks through Windows Security Event correlation by analyzing Event 4624 LogonType 3 for IP-to-hostname mismatches, identifying Responder/LLMNR poisoning artifacts, auditing SMB and LDAP signing enforcement across the domain, and detecting NTLM downgrade attacks from NTLMv2 to NTLMv1 using event log analysis.

日本語の概要は準備中です。原文の説明を表示しています。

Deploying Cloudflare Access with Cloudflare Tunnel to provide zero trust access to self-hosted and private applications, configuring identity-aware access policies, device posture checks, and WARP client enrollment for VPN replacement.

日本語の概要は準備中です。原文の説明を表示しています。

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

日本語の概要は準備中です。原文の説明を表示しています。

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

日本語の概要は準備中です。原文の説明を表示しています。

Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data warehouse, persons, etc.) and query analytics data (trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, LLM traces). Covers HogQL syntax differences from ClickHouse SQL, system table schemas (system.*), available functions, query examples, and the schema-discovery workflow.

日本語の概要は準備中です。原文の説明を表示しています。

Focused Signals scout for PostHog projects using AI observability. Rotates through a set of lenses — cost, latency, errors, volume, eval performance, eval/enrichment config, clusters, and tool usage — watching each for trends and spikes sliced by the dimensions it discovers over time. Leans on the sandbox's bundled `exploring-llm-*` deep-dive skills for the actual queries. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other scouts.

日本語の概要は準備中です。原文の説明を表示しています。

Focused Signals scout for PostHog projects running Replay Vision scanners — the standing LLM probes that watch session recordings and write `$recording_observed` events. Watches two promises: that enabled scanners are actually observing (throughput / success-rate cliffs, exhausted quota — a silent watch gap), and that what the scanners see in aggregate gets surfaced (a monitor's `yes`-rate or a scorer's score stepping away from its own baseline, a classifier tag or a recurring summarizer theme concentrating across many sessions). It is the agentic pull complement to the per-session push path: scanners with `emits_signals` already emit one signal per session into this same inbox, so this scout never repeats them — it adds the cross-session shape the per-session probe can't see. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet.

日本語の概要は準備中です。原文の説明を表示しています。

Write effective prompts for LLMs — structure, few-shot examples, chain-of-thought, system prompts, and output parsing.

日本語の概要は準備中です。原文の説明を表示しています。

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

日本語の概要は準備中です。原文の説明を表示しています。

Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email or Slack on each tick. Use when the user wants a recurring AI summary of X on any cadence (daily, weekly, monthly, yearly) rather than a one-off report. (To attach an AI summary to an existing insight/dashboard subscription instead of a free-text prompt, see `managing-subscriptions` and its `summary_enabled` option.)

日本語の概要は準備中です。原文の説明を表示しています。

Strategic clinical trial design feasibility assessment. Analyzes 6 dimensions (endpoint, population, comparator, effect size, duration, regulatory pathway) using precedent trials and FDA guidance. Produces enrollment projections, endpoint recommendations, and approval-pathway analysis. Use for trial-protocol design, power/sample-size estimation, comparator selection, and FDA submission strategy. Driven by precedent-based reasoning rather than first-principles math.

日本語の概要は準備中です。原文の説明を表示しています。

Cost modeling and ROI analysis for specialized LLM development. Use when deciding whether to train a custom model, estimating total cost, or calculating break-even vs frontier APIs. Covers training costs, inference costs, and time-to-ROI projections.

日本語の概要は準備中です。原文の説明を表示しています。

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

日本語の概要は準備中です。原文の説明を表示しています。

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

日本語の概要は準備中です。原文の説明を表示しています。

Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL formatting, data quality validation, deduplication, and train/eval splitting.

日本語の概要は準備中です。原文の説明を表示しています。

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

日本語の概要は準備中です。原文の説明を表示しています。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

日本語の概要は準備中です。原文の説明を表示しています。