tensorfolk

Salesforce adds Agent Evals, API Evals and spend caps with a kill switch to its Agent Fabric control plane

Salesforce extended Agent Fabric with automated tests that check agents, models and MCP servers before and during deployment, plus API tests to catch breaking changes. A FinOps dashboard and Model Wallet enforce usage limits, and failing benchmarks can trigger an agent kill switch. Some pieces, including cross-platform evals, are not due until early 2027.

Why it matters

Brings eval gates and hard budget limits into enterprise agent governance, a pattern teams running many agents will likely need.

Source: Read the full story on Tech Monitor

agent-governanceevalsfinopssalesforce

More in AI Tools & Open Source

AI Tools & Open Source / No-code & Automation

Sakana AI launches Aquarium, an ontology-based platform for governed enterprise agents

Aquarium combines an ontology that maps company data and rules in place, managed agents that run YAML-defined workflows with human approval steps, and a governance layer for permissions and audit logs. It grew from Sakana's work with Japanese banks, and access is by consultation.

Why it matters: A frontier lab is moving into governed agent platforms for regulated industries.

Read on Sakana AI
AI Tools & Open Source / Coding Assistants

GitHub makes Copilot Fusion multi-model routing generally available at Universe 2026

At GitHub Universe, Copilot Fusion left research preview and became available on every Copilot plan. Picking Fusion in the model picker hands each prompt to a router that decides which models to call and how to combine them, with Standard, High and Max effort levels. GitHub says Fusion Max lands near top single models on a coding-agent index at roughly half the cost.

Why it matters: Teams can stop hand-picking models per task; admins still control which models Fusion may route to, and billing stays per underlying model.

How to try it

Copilot Fusion is a routing system you select instead of a single model; it works in VS Code, the GitHub Copilot app, Copilot CLI and JetBrains IDEs on all Copilot plans, billed at each routed model's rate.

  1. Update VS Code (1.144+), the GitHub Copilot app, Copilot CLI or your JetBrains Copilot plugin.
  2. Open the Copilot model picker and select Fusion.
  3. Choose an effort level: Standard, High or Max.
  4. Org admins: set which models Fusion may use via enterprise/organization model policies, and optionally make Fusion the default via enterprise managed settings.
Open the docs
Big newsRead on The GitHub Blog
AI Tools & Open Source / Coding Assistants

Android Dev Summit: Android CLI ships as official Claude Code and Codex plugin; bring-your-own-agent goes stable

Google's Android tooling update makes the Android CLI an installable plugin for Claude Code, Codex and Antigravity, giving agents commands for Compose previews without an emulator, remote real devices, profiling and Play-style bundle analysis. Android Studio Rabbit 2 also makes its Agent Client Protocol support stable, so 40+ third-party coding agents can run inside the IDE.

Why it matters: Android teams can use their preferred coding agent with first-party device, preview and profiling tools; Google reports 77% faster UI tasks with fewer tokens.

Read on Android Developers Blog