Briefs

BriefsNewsRolling out1 min read

Salesforce adds evaluation tools and cost controls to Agent Fabric

Salesforce announced new evaluation features and spending limits in Agent Fabric to monitor AI agent quality and prevent runaway costs.

Salesforce adds evaluation tools and cost controls to Agent Fabric — image from Salesforce
Image: Salesforce

Summary

Salesforce has updated its Agent Fabric control plane with Agent Evals, API Evals, and advanced cost controls. These tools help teams monitor AI agent quality, catch breaking API changes, and manage token spending.

What changed

  • Agent Evals generates tests and evaluates agents, LLMs, and MCP servers in production against quality thresholds, with beta in November 2026 and general availability in January 2027.
  • API Evals automatically generates functional and performance tests from API specifications to catch breaking changes before production.
  • Advanced cost controls introduce hard spending limits, a FinOps Dashboard, and Cost Optimization Policies to manage token usage and spending.

Availability

Rolling out

“Agent Evals: Beta in November 2026. Generally available January 2027.”

Founder takeaway

There is nothing to do yet since the evaluation tools are scheduled for beta and general availability in late 2026 and early 2027.

Source

SalesforceSalesforce Expands Agent Fabric to Automatically Stop Runaway Costs and AI Agent Failures Before They Impact Customers

Announced Checked

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. AWS logo on a FounderHeist card

    NewsAvailable now

    Amazon Quick adds smart approvals for agentic AI actions

    Amazon Quick introduces smart approvals to automate routine agentic tasks while keeping human oversight for high-impact actions.

    AWS1 min read

  2. ElevenLabs introduces Cue forced alignment AI model — image from ElevenLabs

    NewsAvailable now

    ElevenLabs introduces Cue forced alignment AI model

    ElevenLabs releases Cue, an AI forced alignment model that places every character in an audio file on a precise timeline and powers its Scribe model family.

    ElevenLabs1 min read

  3. GitHub makes Copilot Memory generally available on paid Copilot plans — image from GitHub

    NewsAvailable now

    GitHub makes Copilot Memory generally available on paid Copilot plans

    GitHub introduces new AI intelligence capabilities including Copilot Memory, dreaming, and multi-repository code search.

    GitHub1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.