Salesforce
From Agent-Retrofit to Agent-Native
The real strategic choice behind AI agents
AI agents are moving from demos to operating reality. They can reason across steps, use tools, act inside workflows, maintain state, and escalate when confidence is low. But the most important question is not whether agents can perform useful work. They already can, in the right settings. The real question is, what kind of organization are you building around them?
Over the next few years, two adoption patterns will define the market. Most established companies will take the agent-retrofit path. They will add agents to existing systems of record, existing workflows, and existing management structures. That is the practical near-term play. It can reduce friction, improve throughput, and lower the cost of repetitive digital work.
The more consequential path is agent-native. This is where startups, new departments, and greenfield teams design the product, the workflow, the org chart, and the cost model around agent capacity from the start. This changes what a company can do, how it scales, and where value is created.
Agent-retrofit is the efficiency play
Agent-retrofit is where most enterprise adoption will begin. A company already has a CRM, service desk, ERP, ticketing system, document repository, data warehouse, or security console. Agents are added around those systems to summarize cases, triage alerts, draft responses, update records, route exceptions, or prepare reports.
This approach makes sense because the enterprise already has the governance foundation agents need. Permissions, data models, workflows, approval paths, and audit trails are often already in place. That makes it easier to deploy agents safely.
The limitation is that retrofit agents inherit the constraints of the process around them. If the workflow is fragmented, the data is inconsistent, or the handoffs are unclear, the agent will not magically fix the operating model. It may reduce toil, but it will still be working inside a structure designed for human execution.
That is why agent-retrofit is mostly about doing the same work better. It is valuable. It is also only the first phase.
Agent-native changes the operating model
Agent-native teams start from a different assumption. They do not ask how agents can help an existing team. They ask what the team would look like if agents were part of the operating model from day one.
That changes the product. Instead of selling software seats and leaving the work to the customer, agent-native companies increasingly sell completed outcomes. A resolved support conversation. A qualified lead. A completed workflow. A reviewed document. A cleared invoice. The unit of sale moves from access to result.
It changes the org chart. Instead of staffing every function with layers of junior execution roles, agent-native teams can pair senior operators with fleets of specialized agents. Humans define goals, review exceptions, improve workflows, and own quality. Agents handle production, monitoring, research, routing, drafting, and repetitive execution.
It also changes the cost model. The key metric becomes cost per accepted output, not just software spend or token usage. Evaluation, observability, and proof artifacts become core infrastructure because the product is not the agent itself. The product is the reliability of the agentic workflow.
The agent market is forming in three layers
The technology landscape is easier to understand when viewed in three layers.
Layer 1 is enterprise application agents. These include Microsoft Copilot agents, Salesforce Agentforce, and ServiceNow AI Agents. They operate inside systems of record and approved workflows. Their strength is governability. They inherit permissions, data structures, audit trails, and enterprise deployment controls.
Layer 2 is model-platform agents. These include OpenAI Operator and Codex, Anthropic computer use, and Devin-like coding systems. They push the frontier of what agents can do across browsers, files, software tools, codebases, and user interfaces. Their strength is capability, but they usually require more integration and risk management.
Layer 3 is orchestration frameworks and self-hosted operators. These include LangGraph, CrewAI, AutoGen, browser-use, OpenClaw, and Hermes Agent. They provide infrastructure for persistent, tool-using, multi-agent systems. Their strength is flexibility. They are especially useful for builders who want custom workflows, self-hosting, memory, scheduling, browser control, and delegated work.
The right layer depends on the job. A regulated incumbent may choose enterprise application agents because governance comes first. A greenfield team may choose an operator framework because flexibility and speed matter more. A product or engineering team may use model-platform agents to push the edge of coding, testing, research, or browser-based execution.
The strategic question for executives
For technology leaders, the decision is not simply which agent platform to buy. The better question is where the organization should retrofit and where it should rethink the operating model.
Retrofit agents are the right first move for high-volume workflows with clear rules, visible data, measurable outcomes, and safe escalation paths. Customer service, IT operations, security triage, AP processing, contract review, CRM hygiene, and recurring research are strong candidates.
Agent-native thinking belongs in places where the organization has room to redesign the workflow. New service lines, new internal functions, new digital products, and greenfield teams are better suited to this model. That is where agents can change the structure of the work, not just the speed of the work.
The near-term winners will not be the companies with the flashiest demos. They will be the companies that combine model capability with workflow discipline, strong permissions, observable execution, human fallback, and a clear economic case.
The dependable digital operator is already here. The agent-native company is what comes next.
To explore the use cases, market layers, evidence, maturity levels, and governance requirements in more detail, read the full white paper From Chatbots to Digital Operators. It provides a practical framework for choosing where to start, how to evaluate readiness, and how to move from agent experimentation to scalable operating capability.
Contact us today to schedule a personalized consultation. You can email us at info@westcoastconsulting.com or call us at 415-626-3493.
San Jose-based Outset Medical, a pioneer in medical technology, has reimagined dialysis with its innovative “Tablo” system. Designed to simplify dialysis for both patients and healthcare providers, Tablo improves patient experience, reduces setup time, and streamlines operations in clinics and at home. As Outset Medical experienced rapid growth, the need for a seamless, efficient sales and fulfillment process became critical.
