Tool Use

RAPID turns one visual demonstration into an executable, testable robot program, showing how agent loops can derive their own specifications, tools, and verification environment.

Coding agents synthesized reusable robot-planning programs that beat available hand-built planners on held-out instances, suggesting interactive code generation can replace substantial domain engineering.

An MIT prototype shows embodied agents need an interaction language, low-latency feedback, and human validation—not just a model connected to actuators.

TanStack AI agents can reach OAuth-protected MCP servers through Vercel Connect, with per-user token refresh and consent handled before model execution.

A2M shows how malicious MCP metadata can attract agent calls before crafted tool outputs steer behavior, making tool vetting and runtime isolation practical requirements.

A learned harness moved recurring control into reusable code, cutting model calls and inference cost while keeping web-agent performance stable across 4B–120B deployment models.

Claude Opus 5.5 reaches Vercel AI Gateway with stronger long-run agent positioning, but adaptive thinking and retired forced tool use can break existing requests with HTTP 400s.

Vercel AI Gateway adds three MiMo V2.6 variants spanning heavier agent work, efficient multimodal automation, and lower-latency Pro inference.

mcp-handler 2.2.0 can expose selected MCP tools to in-browser agents through one script, proxying calls as the signed-in user without separate browser OAuth.

Jev returns typed, probabilistic decisions for agent routing and guardrails; rapid first-day Gateway adoption is notable, but its speed and cost claims come from the vendor.

Harness components pay off differently by model and budget. Elide before summarizing, use planning selectively, and avoid elaborate tools when the model is already strong with bash.

GPT-Live 1 supports simultaneous listening and speaking plus delegation to a separate text model, enabling interruptible voice agents without coupling conversation and deep work.

Publishing agent instructions is not enough: tested agents mostly ignored llms.txt and navigated documentation directly, so agent readiness needs observed journey testing and discoverable interfaces.

Exa’s search API is shaped around agent constraints: low latency, narrow token extraction, structured results, and per-customer controls rather than a human search-results page.

Jev gives agent loops typed decisions and probabilities without generating prose, offering a smaller control primitive for routing tools, retries, reviews, and guardrails.

A low-latency voice harness can pair fast provisional work with slower corrections. The design speculates on transcripts and responses, runs tools in parallel, and reuses cached speech prefixes.

Voice agents trade reasoning time for latency, then fail on transcription, data capture, and pronunciation. Treat inputs as typed fields, validate them, and normalize speech output yourself.

Two Gemini 3.8 Live models add real-time audio to AI Gateway; the extended variant can reason alongside speech while the base model keeps tool calls in the background.

Gavel routes skills from a frozen model’s internal states without loading skill text into context. It suggests large skill libraries may need model-native selection rather than metadata-heavy prompts.

A GitHub review agent is rebuilt with progressively less orchestration code, ending as instructions and setup files around general tools. Evals still remain the builder’s job.

A production agent's harness is everything around the model: tools, memory, runtime, isolation, and deployment controls. The practical lesson is to standardize that layer across agents.

A solo conference designer scaled hundreds of assets by defining design primitives first, generating from live data, and using vision agents as a second QA pass.

Prefab lets Python teams compose constrained MCP app interfaces from components, then render them through a JSON protocol and React client without hand-writing frontend code.

The Agents API exposes a managed Codex-based harness for orchestration, long-running sessions, and tool use, reducing the agent runtime a builder must operate directly.

Tako Search gives any AI Gateway model current web and curated data through one AI SDK tool, without a separate account or key. The free window ends September 30.

Show-Harness puts a compact semantic action layer between VLM intent and robot-specific control, a harness pattern for reusing frontier or small open models across embodiments.

ACP lets editors, terminals, and custom apps control compatible agent harnesses through one protocol, including remote sessions, tool updates, and permission requests.

An MCP widget can reduce an agent’s useful work if rendering and retrieval share one tool. Keep data exploration separate, then render only the results the model selects.

LinkedIn scales a large internal agent catalog through search, schema lookup, and execution rather than exposing every tool at once. Its playbooks add task-specific operating knowledge.

Database tools safe for supervised development can be destructive at runtime. Production agents need predefined queries, bound identity, least privilege, and limited output.

Vercel’s CLI can now give coding agents searchable, machine-readable product updates, reducing stale recommendations about platform features.

An MIT researcher uses Codex with GPT-5.6 Sol across the experiment loop, including execution, result analysis, and qubit calibration. It is a concrete agent use case beyond software tasks.

EDGE synthesizes multi-step tool-call training data by retaining only API links verified through live execution. Its 9B model nearly matched an untuned 27B sibling on Korean public-API tasks.

Sentinel-RL keeps topology outside the LLM: a graph encoder and constrained policy choose SOC actions, while the model writes critic-gated narratives for human approval.

Knowledge-work agents need code-like infrastructure around tools: centralized context, action records, verification, enforced permissions, and preflight checks for irreversible work.

Shared agent memory needs user-scoped reads, human-approved writes, and per-request credentials. The talk offers a concrete security boundary for company-wide context and tools.

Zo packages a persistent Linux server, coding agents, files, integrations, and hosting into one personal cloud. The useful idea is collapsing build and deploy context into the agent’s workspace.

This talk proposes legally registered agent organizations, scoped JWT authority, and blockchain audit trails for open-internet commerce; it is an architecture proposal, not validation.

Generative UI needs more than a component catalog: agents require explicit layout rules, schemas, and design-system constraints to produce stable interfaces across repeated requests.

Paid agent tools turn a skill file into spending authority. Builders need budgets, transaction logs, and counterparty screening before letting agents purchase data or services unattended.