Speaking twice at Dreamforce · Sept 15-17 →

Use cases

Start with the process. Then the agent.

The first week is in the org, reading what already exists. The honest no: if the work is a software factory with a named delivery date, we are the wrong partner.

  1. 01Models · Claude, Gemini, OpenAI, Bedrock
  2. 02Agents · Agentforce, CrewAI, ADK, A2A
  3. 03Memory · Neo4j, Cognee, RAG
  4. 04Identity · IndyKite, SSO, entitlements
  5. 05Governance · policy, audit, human override

Use cases

Find the process that sounds like your week.

Open the one that matches the work. Each card says where it runs: Slack, WhatsApp or Salesforce. Search for Slack to see the Slack AI agents, including Agentforce in Slack and Claude in Slack. If none fit, clear the cut and tell us the process.

New100 decisions a System One model can take off your LLM bill. Ranked by the model itself.

How we work

From use case to production.

  1. 01Week 1 in the orgWe read what already exists before anyone adds a cloud.
  2. 02Written noteWhat is worth fixing, what is worth finishing, and what is not. Not a dashboard.
  3. 03Fixed scope and priceWe can fix-price a named, scoped piece once the process is clear. We will not fix-price a rescue we have not assessed.
  4. 04BuildWe implement around the process you already run.
  5. 05We stayAfter go-live, a person stays on the exceptions.

The brief

Tell us which one is yours.

One email starts it. We ask about the use case and the object after.