Tool Use & Environment
23 篇文章
Agent-First Tooling and Logging
Most developer tools, CLIs, and application logs are designed for human consumption. They use color-coded, multi-line, or summarized outputs that are easy for a person to scan but can be difficult for…
emergingAgent SDK for Programmatic Control
Interactive terminal or chat interfaces are suitable for many agent tasks, but not for all. Integrating agent capabilities into automated workflows (e.g., CI/CD pipelines, scheduled jobs, batch proces…
emergingAgentic Search Over Vector Embeddings
Vector embeddings for code search require: - Continuous re-indexing as code changes - Handling local uncommitted changes - Additional security surface area for enterprise deployments - Infrastructure…
best-practiceAI Web Search Agent Loop
Traditional LLMs have a training cutoff date, meaning they don't know recent facts or real-time information. Simply connecting a model to a search API isn't enough - the model needs to: - Decide when…
emergingCLI-First Skill Design
When building agent skills (reusable capabilities), there's tension between: - **API-first design**: Skills as functions/classes—great for programmatic use, but hard to debug and test manually - **GU…
emergingCLI-Native Agent Orchestration
Web chat UIs are awkward for repeat runs, local file edits, or scripting inside CI pipelines.
proposedCode Mode MCP Tool Interface Improvement Pattern
Traditional Model Context Protocol (MCP) approaches of directly exposing tools to Large Language Models create significant token waste and complexity issues. We've moved from telling LLMs what to do, …
establishedCode-Over-API Pattern
When agents make direct API or tool calls, all intermediate data must flow through the model's context window. For data-heavy workflows (processing spreadsheets, filtering logs, transforming datasets)…
establishedCode-Then-Execute Pattern
Plan lists are opaque; we want **full data-flow analysis** and taint tracking.
emergingDual-Use Tool Design
Building separate tools for humans and AI agents creates: - **Maintenance overhead**: Two implementations of similar functionality - **Inconsistent behavior**: Human tools work differently than agent…
best-practiceDynamic Code Injection (On-Demand File Fetch)
During an interactive coding session, a user or agent may need to inspect or modify files **not originally loaded** into the main context. Manually copying/pasting entire files into the prompt is: - …
establishedEgress Lockdown (No-Exfiltration Channel)
Even with private-data access and untrusted inputs, attacks fail if the agent has **no way to transmit stolen data**. Many real-world fixes simply removed or filtered outbound channels.
establishedIntelligent Bash Tool Execution
Secure, reliable command execution from agents is complex and error-prone: - **PTY requirements**: TTY-required CLIs (coding agents, terminal UIs) fail with direct exec - **Platform differences**: Li…
validated-in-productionLLM-Friendly API Design
For AI agents to reliably and effectively use tools, especially APIs or internal libraries, the design of these interfaces matters. APIs designed solely for human consumption might be ambiguous or ove…
emergingMulti-Platform Communication Aggregation
Users communicate across multiple platforms (email, Slack, iMessage, etc.) and need to search for information that might exist in any of them. Searching each platform manually is slow and error-prone.…
emergingMulti-Platform Webhook Triggers
An internal agent only provides value when its workflows are initiated. Building out a library of workflow initialization mechanisms (triggers) is core to agent adoption. Without easy triggers, employ…
emergingPatch Steering via Prompted Tool Selection
Coding agents with access to multiple patching or refactoring tools (e.g., `apply_patch`, `AST-refactorer`, `codemod`) may choose suboptimal tools if not explicitly guided. This leads to: - **Unneces…
best-practiceProgressive Tool Discovery
When agents have access to large tool catalogs (dozens or hundreds of available tools), loading all tool definitions upfront consumes excessive context window space. Most tools won't be used in a give…
establishedShell Command Contextualization
When an AI agent interacts with a local development environment, it often needs to execute shell commands (e.g., run linters, check git status, list files) and then use the output of these commands as…
establishedSubagent Compilation Checker
Large coding tasks often involve multiple independent components (e.g., microservices, libraries). Having the **main agent** handle compilation and error checking for every component in-context: - **…
emergingTool Use Steering via Prompting
AI agents equipped with multiple tools (e.g., shell access, file system operations, web search, custom CLIs) need clear guidance on when, why, and how to use these tools effectively. Simply having too…
best-practiceVirtual Machine Operator Agent
AI agents need to perform complex tasks beyond simple code generation or text manipulation. They require the ability to interact with a full computer environment to execute code, manage system resourc…
establishedVisual AI Multimodal Integration
Many real-world tasks require understanding and processing visual information alongside text. Traditional text-only agents miss critical information present in images, videos, diagrams, and visual int…
emerging