The agentic enterprise
Generic agents are the scaffolding. Custom agents are the building.
Why production AI agents need purpose-built design, native tooling and embedded security.
Kevin Keller · kevinkeller.org
Why it matters
Every enterprise is experimenting. Few are in production.
"We're going to see agents in every single part of every single company."
Jensen Huang, GTC 2026
The question is no longer whether, but how. The gap from pilot to production is an architecture problem, not a technology problem.
Three phases
Most pilots stall between demo and production
| Phase | What happens |
|---|---|
| Experimentation, 2024 to 2025 | LLMs call tools, MCP servers appear everywhere |
| Disillusionment, 2025 to 2026 | Demos fail in production |
| Production architecture, 2026 onwards | Specific agents for specific tasks |
Why pilots fail
Four problems appear at production scale
- Security gaps: credentials per server, not per user
- Reliability: same prompt, different tool sequences
- Compliance: audit trails span four systems
- Cost: round trips, discovery tokens and retries add up
MCP in production
What helps exploration hurts production
- Dynamic discovery is a liability: capabilities can change without code changes, the "rug pull".
- Authentication fans out across independent trust boundaries.
- The audit trail fragments across systems.
- Protocol overhead grows with thousands of invocations an hour.
The idea
Build specific agents for specific tasks
Not a retreat from the agentic vision. Its maturation.
What works
Five traits of production-grade agents
- Purpose-specific design: one job, done well.
- Native tool integration: platform APIs, no protocol layer.
- Embedded security: own identity, platform RBAC, native audit.
- Deterministic tools: a fixed set, defined in code and testable.
- Evaluation before deployment: domain test suites gate every release.
Secure by construction
An agent can't run what isn't in its code
- No Bash, no dynamic discovery: the code is the security boundary.
- Containers: network and filesystem isolation, resource limits, immutable images.
- Inference proxy: prompt policy, FinOps, observability and a central audit trail.
Maturity model
Most organisations sit at level 1 or 2
| Level | Architecture | Governance |
|---|---|---|
| 1. Experimentation | Generic agent + MCP | None |
| 2. Standardisation | Generic + curated MCP | Approved tools list |
| 3. Production | Custom + native tooling | Identity, RBAC, audit, evaluation |
| 4. Enterprise-scale | Custom + orchestration | Governance as code |
Where MCP still wins
The mistake is MCP as the production integration layer
- Prototyping: discover what an agent should do, fast.
- Multi-vendor glue: tools with no shared platform.
- Reference implementations: study MCP servers when building native tools.
For leaders
Agents are workloads. Treat them like it.
- CIOs: one governed agent for your most painful workflow beats a hundred generic ones
- CTOs: invest in agent-building capability, not the protocol ecosystem
- Security leaders: minimise trust boundaries between agents and data
The takeaway
Not what agents can do, but what they reliably do, under governance, at scale.
Kevin Keller · kevinkeller.org