

















How to make the best out of Agentforce
Years of learnings, open source. github.com/aquivalabs/my-org-butler
ExploreOrgSchema + QueryRecordsWithSoql — 2 simple actions replace a complex dozens.
CallRestApi + CallMetadataApi — read data, change config, all from a conversation.
QueryDataCloud for hybrid search, AnswerFromDataLibrary + AnswerWithCurrentFile for files.
SearchWeb — one Tavily API key, one Named Credential, done.
LoadCustomInstructions + StoreCustomInstruction — persistent preferences, zero code.
HeadlessAgent + PlanForLater — “Every Monday, check stale opps and Slack me.”
Testing Center for what it covers — then plug in custom tools for what it can’t: multi-turn flows, data resets, stronger judges.
A Claude Code Skill generates multi-turn YAML tests, runs them through the Agent API, judged by your own LLM.
Packaging, DevOps, analytics, security — it’s all worked through in the repo.
Robert Sösemann
Director of Engineering & AI Lead at Aquiva