Tool Use

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.

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.

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.

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.

Agent authorization should scale with stakes and reversibility: logs may cover coding changes, while open-ended payments need scoped, time-bound, independently verifiable mandates.

SAGE uses an expensive VLM only when a learner is uncertain, tests its advice against environment rewards, and distills useful guidance into a policy that needs no VLM at runtime.

A wallet-equipped agent crossed paywalls and completed paid email and phone actions under a spending cap. The engineering lesson is to enforce budgets in the wallet, not in prompts.

For fuzzy requests, an agent should identify the missing constraint with the most decision value, elicit it in the right modality, then choose a response format suited to the task.

Agent checkout needs more than payment tools: enforce user-set limits outside the agent, expose structured merchant data, honor cancellation, and log every decision.

An AWS demo treats a robot as an agent tool: an LLM selects existing hardware policies while separate agents handle thinking, communication, and voice. The live failures expose the safety gap.

Maersk’s production agents depend less on a clever loop than on executable SOPs, bounded tools, replayable traces, and a correction system shared by experts and engineers.

Once agents mutate external state, timeouts mean unknown outcomes. Builders need idempotent tools, bounded retries, scoped credentials, durable traces, and explicit recovery paths.

Vercel CLI 59.6.2 adds agent-friendly control over DNS, domains, projects, observability, and membership, with JSON output and confirmation gates for risky actions.

Ling 3.0 Flash Fin adds a finance-focused reasoning and tool-calling option to AI Gateway, with separate model IDs for automatic billing or a hard stop after the free period.

Exa’s internal agent clone combines writing examples, decision evals, and permission-scoped tools—a concrete pattern for encoding judgment without sharing full access.

Notion treats GTM automation as a shared context system for humans and agents, not an AI layer over disconnected tools. The key design choice is keeping risky customer actions human-approved.

Web agents should validate fetched content before spending model tokens on it and reserve browser automation for interactive steps. Explicit failures beat silently passing CAPTCHAs or blocked HTML downstream.

Qwen 3.8 Flash is now selectable in Vercel AI Gateway and coding agents, with text-and-image input, a 1M-token context window, and responses up to 65k tokens.

GLM 5.3 Flash joins Vercel AI Gateway with text and vision input, a 1M-token context window, function calling, structured output, and streaming.

Vercel Connect gives agents runtime-minted, task-scoped credentials instead of stored provider tokens, adding per-user identity, revocation, audit logs, and usage visibility.

Run SDK executes agent-generated JavaScript or TypeScript behind narrow host functions, with resumable approval and auth boundaries instead of application-level eval access.

Production agents need bounded write authority, infrastructure-stamped identity, and human-only overrides; a broad token and tool list cannot control blast radius.