AI Weather Report
AI Weather Report
Source: StrongDM Software Factory — Last synced: February 23, 2026
What models they’re running today, how they’re configured, and what role each one plays in the factory.
As of February 13th, 2026
Happy with gpt-5.3-codex-spark. gpt-5.3-codex continues to be their preferred default implementation model with critiques and suggestions from Opus. Modified: Sprint Planning. Added: UX Ideation, Agentic dialogues, Voice (interactive).
Model Assignments
| Use | Updated | Models (by preference) | Parameters | Notes |
|---|---|---|---|---|
| CS/Math Hard Problems | Feb 6 | gpt-5.3-codex | default | |
| Image Comprehension | Feb 6 | gemini-3-flash-preview | default | |
| Frontend Aesthetics | Feb 6 | opus-4.6 | default | |
| Frontend Architecture | Feb 6 | gpt-5.3-codex | default | |
| Architectural Critique | Feb 6 | gpt-5.2 | extra high | |
| Sprint Planning | Feb 13 | consensus(opus-4.6, gpt-5.2) | high / extra high | |
| DevOps Tasks | Feb 6 | opus-4.6 | default | |
| QA Orchestration | Feb 6 | opus-4.6 | default | |
| Security Review | Feb 6 | gpt-5.3-codex | high | |
| Bulk Classification | Feb 6 | Any | default | Go up cost and strength as needed |
| Bulk MapReduce | Feb 6 | Any | default | Go up cost and strength as needed |
| UX Ideation | Feb 13 | gemini-3-pro-image-preview | default | Nano Banana Pro |
| Agentic Dialogues | Feb 13 | gemini-3-flash-preview | default | General message handling loops with user interaction and limited tool calling |
| Voice (interactive) | Feb 13 | gpt-realtime-mini | default |
Consensus operator refers to an LLM merge of the points from independent plans.
Log
February 13th, 2026 — Happy with gpt-5.3-codex-spark. gpt-5.3-codex continues to be their preferred default implementation model with critiques and suggestions from Opus. Modified: Sprint Planning. Added: UX Ideation, Agentic dialogues, Voice (interactive).
February 6th, 2026 — New models this week. Very happy with gpt-5.3-codex. No problems with Opus 4.6 so far.