GPT WORLD / INDEPENDENT CODEX FIELD MANUAL Source review · 2026-07-26

Field guide / 9 min

Keep model choice at the edge

Route by tested capability instead of embedding a fashionable name.

Track
OpenAI Platform / API
Level
Platform architecture
Maturity
Stable

The OpenAI model catalog changes over time. Product code should ask for a tested capability profile—quality, latency, modalities, tool support, and budget—then resolve that profile through configuration and evaluations.

A

Working principles

01

Names are deployment data

Keep active model identifiers in configuration or a registry. Historical fixtures may remain pinned for reproducibility.

02

Capabilities need tests

Documentation narrows candidates; your fixtures establish whether a candidate works for your prompts, tools, schemas, and latency target.

03

Preserve routing roles

Do not collapse every workload onto one model. Separate quality-sensitive, latency-sensitive, realtime, and background roles.

B

Field procedure

  1. 01

    Define capability profiles

    For each workload, record required modalities, tools, structured output, context, latency, and budget.

  2. 02

    Create a model registry

    Map profile names to deployable model identifiers and keep the mapping outside feature code.

  3. 03

    Build representative fixtures

    Include normal, edge, adversarial, refusal, and tool-use cases with observable acceptance rules.

  4. 04

    Run a shadow comparison

    Compare candidate and current deployments on quality, schema success, tool outcomes, latency, and cost before switching.

  5. 05

    Roll out reversibly

    Use a staged percentage, monitor product-level outcomes, and retain a fast rollback path.

PASS / FAIL

Acceptance checklist

  • No feature branch embeds a volatile model name.
  • Profiles state hard and soft requirements.
  • Evaluation data includes tool and schema behavior.
  • Rollout and rollback are configuration changes.

WATCH / REJECT

Failure patterns

  • Choosing solely from a leaderboard or marketing label.
  • Updating examples and production defaults without behavioral tests.
  • Using one global model setting for unrelated workloads.