Agent Test Suite
For agents you already have: scenarios and answer tests written from your team's real questions, pass thresholds agreed with you, and a re-run after every Salesforce release.
Price.
- Duration
- 1 to 2 weeks
- Who it’s for
- For agents you already have. If we build the agent, testing comes with Groundwork.
What’s included.
- Scenarios and answer tests written from your team's real questions and confirmed true answers
- Pass thresholds agreed with you before we start
- Run in the tool you have: Agentforce Testing Center, or Agent Evals once available, with French scenarios where needed
- A pass rate against the agreed thresholds before go-live, and a re-run after each Salesforce release
Is Salesforce’s own feature enough?
Often, yes, if someone on your team owns the tests. Agentforce Testing Center comes with Agentforce, and tests run there don't use credits. It generates test cases from your agent's subagents, actions and knowledge, takes your own uploaded cases, works in the languages Salesforce's AI platform supports, including Canadian French, and tests full conversations in beta (up to 20 turns, customer-facing agents only, no handoff to a person). Agent Evals in MuleSoft Agent Fabric, a separate product, goes to beta in November 2026. What none of them supplies is the test content: generated tests come from how the agent was built, not from the questions your customers and staff really ask, and nobody agrees what counts as a pass. That is the part we write.
Verified on 2026-11-02.
What it costs, split three ways.
All prices in USD.
- What you pay Salesforce
- Nothing for tests run in Testing Center. Data 360 queries during tests, and tests run from Agentforce Grid, use credits billed by Salesforce. We confirm metering against your licences.
- What you pay anyone else
- Nothing.
- What you pay ArkeAgents
- $2,500 per agent, agreed before we start.
Start with a call.
Tell us what your org looks like today. We’ll confirm the scope and the price before anything starts.
Not sure yet? Explore the Readiness Assessment →