Notes / tag / tools-and-environment-interaction

#tools-and-environment-interaction

14 notes

1. Tool Calling Architecture

Covers the mechanics of function/tool calling in modern LLM APIs -- schema definition, the model's structured-call output, execution, and result injection back into the conversation -- as the foundational primitive every agent framework builds on.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

2. APIs as Tools

Covers wrapping arbitrary external APIs as agent tools -- authentication handling, request/response schema translation, and error surfacing patterns so API failures degrade gracefully instead of confusing the agent's reasoning.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

3. REST & GraphQL Integration

Covers integrating REST and GraphQL services as agent tools specifically, including schema introspection for GraphQL, pagination handling, and rate-limit-aware retry design distinct from generic API wrapping.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

4. Database Tools

Covers giving an agent direct database access as a tool -- text-to-SQL generation, read-only scoping, query validation before execution, and the injection-attack surface unique to letting an LLM generate queries against production data.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

5. Search Tools

Covers search as an agent tool -- web search APIs, retrieval-augmented search over internal corpora, and result-ranking/summarization strategies that keep search results from overwhelming the agent's context budget.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

6. Browser Automation

Covers browser automation as an agent tool -- headless browser control, DOM parsing and accessibility-tree extraction for the agent to reason over, and the reliability challenges of dynamic, JavaScript-heavy pages.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

7. Computer Use Agents

Covers computer-use agents that operate a full desktop GUI via screenshots and coordinate-based actions rather than structured APIs, and the accuracy, latency, and safety tradeoffs versus API-based or browser-DOM-based tool access.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

8. Code Execution

Covers sandboxed code execution as an agent tool -- isolation boundaries, resource limits, and output capture -- for tasks better solved by generating and running code than by reasoning about the answer directly.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

9. Model Context Protocol (MCP)

Covers the Model Context Protocol as a standardized interface between agents and external tools/data sources, why it emerged to replace bespoke per-framework tool integrations, and its client-server architecture for tool discovery and invocation.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

10. Tool Discovery

Covers how agents discover which tools are available and applicable at runtime -- static registration versus dynamic discovery, tool metadata/schema design, and scaling tool catalogs beyond what fits in a single prompt.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

11. Tool Selection Strategies

Covers strategies for selecting the right tool among many candidates -- embedding-based tool retrieval, hierarchical tool routing, and the accuracy degradation observed as the number of available tools grows past what a single LLM call can reliably discriminate.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

12. Tool Security

Covers the security model for agent tool use -- least-privilege scoping, output sanitization against prompt injection carried in tool results, approval gates for destructive actions, and audit logging for what an agent actually executed.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

13. Agents in CI/CD & SDLC Workflows

Covers how coding agents establish execution context, get scoped to a single repository and branch, get triggered by CI/SDLC events, and act autonomously via branch/PR creation while merge stays gated -- using GitHub Copilot's coding agent as the reference implementation.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026

14. Safe Execution Paths & Error Handling

Covers the error-handling taxonomy, retry design, rollback mechanics, escalation paths, and traceability record that let an agent operate safely when a tool call fails -- grounded in GitHub Copilot coding agent's CI-driven retry loop and git-native audit trail.

agentic-ai-engineering tools-and-environment-interaction book
Aug 8, 2026