Almost nobody sets out to build an AI agent platform. They set out to ship one agent. But production has requirements, and each requirement has a best-in-class tool, so the stack assembles itself: a framework, a vector database, an observability tool, an eval tool, an experimentation tool, a secrets manager, and a layer of glue holding it all together.
Each piece is a reasonable choice on its own. The cost isn't in any single tool. It's in the seams between them, and that bill arrives later, as maintenance rather than a line item.
The resulting stack
Map the requirements of a production agent to the tools teams reach for, and a familiar shape appears. Each of these is a category leader. None of them was designed to know about the others.
Consolidate the agent stack in one runtime
Retrieval, observability, evals, A/B testing, and connectors in one platform, so the seams do not become maintenance code.
The tax nobody prices in
Add up the subscriptions and the number looks manageable. The expensive part isn't on any invoice.
Integration becomes permanent maintenance code
Wiring the framework to the eval tool, the eval results to the experimentation tool, and the traces to the observability backend is custom code. It has no product owner, it's the first thing to break on an upgrade, and it's the last thing anyone wants to maintain.
Version drift compounds
Six tools means six release cadences. A breaking change in one ripples through the integration code. The team spends a steady fraction of every sprint keeping the seams intact instead of improving the agent.
The on-call surface is the whole stack
When an agent misbehaves at 2 a.m., the question is which layer failed, and the answer requires correlating across tools that don't share a request ID. There is no single trace from trigger to tool call to evaluation, so debugging is a join across dashboards.
It looks a lot like self-hosting
This has the same shape as operating infrastructure internally, just one level up: the cost lives in people and time, not compute. We put hard numbers on the infrastructure version in the hidden costs of self-hosting AI agents and the managed vs. self-hosted TCO comparison; the assembled-stack tax stacks on top of it.
When an internal stack is the right call
Building the stack internally can be the right choice. If a company sells observability or relies on retrieval quality as its moat, owning that layer end to end can justify the investment; a general platform may impose limits. The same is true for unusual requirements no integrated product serves or an existing stack the team knows thoroughly and will not outgrow. Internal development fits differentiating layers; an integrated product fits standard layers.
What an integrated platform changes
The alternative to assembling is a platform where these layers already share a data model. We combine retrieval, observability, evaluation, A/B testing, connectors, and secrets in one runtime: one trace runs from trigger to tool call to judge score, upgrades are the platform's problem, and there is no glue to own. Teams define the agent in YAML, write tools in Python, and push to Git. The deployment options are compared in our guide to AI agent deployment platforms in 2026.