Nick

Create container-based hosted agents in Azure AI Foundry using Python and the Azure AI Projects SDK. Follow examples for resource settings, authentication, version management, and checks needed before treating a deployment as healthy.

中文简介正在准备中。当前显示英语简介。

• Creating a hosted agent from a custom container image
• Configuring CPU, memory, and environment variables
• Listing and deleting agent versions

Inspect local AI coding session logs with agenttrace to identify cost spikes, delays, failed tools, and retry loops. Produce readable reports, compare attempts, and configure automated checks for unusual or unhealthy runs.

中文简介正在准备中。当前显示英语简介。

• Investigate slow or expensive AI coding sessions
• Review failed runs before retrying
• Compare tool usage and verification across attempts

Design scheduled AI workflows for document ingestion, batch processing, and model training using Prefect, Airflow, or Dagster. Compare orchestration tools and plan task dependencies, retries, caching, and monitoring through implementation fragments.

中文简介正在准备中。当前显示英语简介。

• Schedule document ingestion and RAG index refreshes
• Design batch workflows for LLM requests
• Connect model training with quality evaluation

Compare prompt revisions on a fixed set of test cases to identify regressions, meaning behavior that gets worse after a change. Record model settings, case-level evidence, missing results, costs, and evaluation limits for a reviewable decision.

中文简介正在准备中。当前显示英语简介。

• Comparing original and revised prompts
• Checking required JSON fields after prompt changes
• Reviewing tool selection and task completion

Design or review command-line tools that AI agents can call. Use 98 proposed rules to define structured output, input validation, error handling, safety controls, and help information, with three levels for gradual adoption.

中文简介正在准备中。当前显示英语简介。

• Design a new command-line tool for AI agents
• Adapt an existing tool for agent use
• Standardize interfaces for automated workflows

Design layered protections for AI agents against malicious instructions, tool misuse, and data leakage. Provides guidance and code examples for input checks, isolated tool execution, permission limits, and audit logging to help review and strengthen agent security.

中文简介正在准备中。当前显示英语简介。

• Review defenses against malicious instructions
• Isolate tool execution and restrict permissions
• Assess data leakage risks between tenants

Design and implement LLM applications, AI agents, and RAG systems that retrieve documents to support answers. Cover model selection, search quality, testing, monitoring, safety measures, and cost controls for applications intended for production use.

中文简介正在准备中。当前显示英语简介。

• Building an AI assistant that answers from company documents
• Improving search with keyword and vector retrieval
• Designing AI agents with multiple specialized roles

Inventory local skills within a requested scope, rank candidates against a task, and prepare a coordination plan showing their order and data flow. Project assignments help prioritize relevant skills without automatically launching agents or executing skills.

中文简介正在准备中。当前显示英语简介。

• Inventory locally installed skills
• Compare skills suited to a task
• Plan a workflow using several skills

Organize supplied health records, including sleep, exercise, nutrition, and test results, to describe trends, relationships, and risk factors. Prepare general health information, summaries, and questions for a doctor, with clear limits on medical interpretation.

中文简介正在准备中。当前显示英语简介。

• Summarize sleep, exercise, nutrition, and health records together
• Explore changes and relationships in health metrics
• Prepare questions to discuss with a doctor

Define security controls for AI coding agents used by a team. Covers command and file permissions, secret scanning, isolated execution environments, code review gates, and audit trails, with configuration examples to adapt.

中文简介正在准备中。当前显示英语简介。

• Set team rules before introducing AI coding agents
• Restrict access to credentials and infrastructure files
• Design an isolated environment for agent execution

Configure permission checks for unattended Antigravity CLI runs. The setup combines blocking rules, automatic approval for scoped operations, AI classification for ambiguous calls, and single-use approval tokens to control tool access within a verified workspace.

中文简介正在准备中。当前显示英语简介。

• Setting up permission checks for unattended Antigravity CLI runs
• Defining rules for shell commands, file changes, and network access
• Configuring a local model to classify ambiguous tool calls

Helps design focused AI products built on APIs such as OpenAI and Anthropic. Covers product strategy, prompts, model selection, user experience, usage tracking, and cost management for tools aimed at solving specific customer problems.

中文简介正在准备中。当前显示英语简介。

• Planning an AI SaaS product for a specific problem
• Designing prompts for product features
• Balancing model choices, costs, and user experience

Plan structured adversarial tests for AI applications to assess safety bypasses, data leaks, and unauthorized tool use. Organize test prompts, record findings, and prioritize fixes using reporting guidance and an adaptable testing template.

中文简介正在准备中。当前显示英语简介。

• Assess an AI feature before release
• Compare security behavior of candidate models
• Retest after a prompt injection or jailbreak incident

Generate realistic photo-style images with Google AI Studio for social posts and educational materials. Adjust aspect ratios, lighting, settings, and subtle imperfections to create a natural smartphone-photo look suited to each use.

中文简介正在准备中。当前显示英语简介。

• Natural lifestyle images for social posts
• Photo-style illustrations for courses and tutorials
• Portrait or landscape images for different platforms

Give an AI agent an email address through the AgentMail API for theagentmail.net. Covers account creation, sending and reading messages, retrieving attachments, setting up incoming-email notifications, and checking organization billing balances.

中文简介正在准备中。当前显示英语简介。

• Creating an email account for an AI agent
• Retrieving verification emails for authorized service signups
• Sending authorized messages and checking replies

Plan AI features for products, covering language model integration, RAG architecture that retrieves information for answers, prompt design, user experiences people can trust, and cost optimization. Use it to guide development decisions for production use.

中文简介正在准备中。当前显示英语简介。

• Plan language model integration in a product
• Consider RAG architecture for reference-based answers
• Review prompt design and AI user experience

Delegate a clearly scoped coding task to Google Antigravity CLI when explicitly requested. Provides a workflow for preparing instructions, reading the implementer’s report, reviewing changes, rerunning project checks, and committing verified work.

中文简介正在准备中。当前显示英语简介。

• Delegate a clearly scoped coding task to Google Antigravity CLI
• Prepare an implementation brief with constraints and checks
• Review delegated changes and rerun project checks

Plan and build AI agents through selected stages of design, implementation, tool integration, memory, and evaluation. The workflow points to specialized skills for single agents, coordinated agent teams, and stateful workflows using CrewAI or LangGraph.

中文简介正在准备中。当前显示英语简介。

• Designing an autonomous AI agent
• Building a team of agents with distinct roles
• Creating stateful workflows with LangGraph

Create consistent records for evaluating AI agents, including task success, invalid tool calls, token use, and actual costs. Produce CSV tables, database definitions, and JSON validation schemas to support reproducible comparisons and checks for performance declines.

中文简介正在准备中。当前显示英语简介。

• Recording agent evaluation results in a shared format
• Comparing a candidate agent with a baseline
• Tracking actual cost per solved task

Hand a scoped coding task to Aider while the coordinating agent reviews changes, runs project checks, and commits the result. Covers task briefs, execution tracking, and follow-up edits, but the executable helper is not bundled.

中文简介正在准备中。当前显示英语简介。

• Delegating a scoped code change to Aider
• Reviewing changes and tests before committing
• Requesting follow-up edits after a review

Design tools that AI agents can understand and call, covering input schemas, clear descriptions, validation, and error handling. The guidance includes JSON Schema, a format for defining inputs, and MCP, a protocol for connecting agent tools.

中文简介正在准备中。当前显示英语简介。

• Design inputs for a new agent tool
• Improve tool descriptions that guide model choices
• Review validation and error handling

Plan security controls for LLM applications and AI agents, covering malicious instructions, data leakage, model tampering, and API access. Includes guidance and code examples for filtering outputs, enforcing permissions, isolating networks, and recording audit events.

中文简介正在准备中。当前显示英语简介。

• Reviewing defenses against prompt injection in AI agents
• Filtering personal information from LLM responses
• Designing authentication and rate limits for LLM APIs

Plan AI application development by selecting relevant phases and companion skills. The workflow covers language model integration, retrieval from documents, agents, machine learning pipelines, monitoring, and security, with prompts and quality checklists.

中文简介正在准备中。当前显示英语简介。

• Plan AI features and language model integration
• Organize RAG retrieval design and implementation
• Map agent roles, tools, and memory

Investigate failed Agent QA runs using recorded steps, logs, and saved evidence. Classify each failure, explain confidence and supporting findings, and identify the likely area to fix and the next action.

中文简介正在准备中。当前显示英语简介。

• Investigating a failed or interrupted Agent QA run
• Reviewing saved evidence and execution logs
• Comparing recurring failures across recent runs