Choosing AI agent frameworks for enterprise

Evaluate

Durable state, human steps, observability, permission model, and how tests run in CI.

Ignore logo density on the readme.

Avoid

Rewriting the business every time a new framework trends.

Frameworks that hide tool credentials inside prompt templates.

Interface boundaries

Keep tools and schemas behind your interfaces so a framework swap does not rewrite the business.

Evaluate human steps and durable state first. Fancy planner demos second.

Team skill

Pick something your team can operate. An exotic framework with one champion is a bus-factor risk.

In practice

Map the workflow on a whiteboard before you open a framework: inputs, systems of record, humans, and irreversible writes. If that map is fuzzy, the agent will encode the fuzz.

Pick ten to fifty real historical cases as an eval set. Include the ugly ones. Run the agent offline against them until critical fields and hard rules are acceptable. Only then connect write tools.

Ship with a pause switch, a human queue, and a weekly review of override reasons. Promote repeated overrides into rules. That loop is how production systems improve—not another prompt brainstorm.

Common failure modes

• Treating a demo on clean samples as readiness for production volume.
• One shared service account with broad write access across systems.
• No owner for the exception queue, so failures pile up as noise.
• Changing prompts and models without regression gates on real cases.
• Measuring only model latency or thumbs-up, not completed-case cost and audit completeness.

What good looks like after ninety days

The first workflow is boring: stable override rate, known failure modes, operators who trust the queue. Config changes go through review. Traces answer "what happened to this case?" without archaeology.

At that point you can add a second document type or a second agent role. Expanding before the first path is boring is how programs stall with five half-built pilots.