# AI Weather Report — StrongDM Software Factory

*Synced from [factory.strongdm.ai/weather-report](https://factory.strongdm.ai/weather-report) on 2026-03-02.*

## Current Status (as of February 23rd, 2026)

No specific changes in defaults, but please note for anyone evaluating Gemini 3.1, the `gemini-3.1-pro-preview-customtools` may significantly outperform `gemini-3.1-pro-preview` depending on your harness. We've switched to `gpt-realtime-1.5` for our internal use cases but aren't officially defaulting to it yet. Very happy with Sonnet 4.6, it may overtake Opus for some of our everyday use cases.

## Model Assignments

| Use | Models (by preference) | Parameters | Notes |
|-----|----------------------|------------|-------|
| CS/Math Hard Problems | `gpt-5.3-codex` | default | |
| Image comprehension | `gemini-3-flash-preview` | default | |
| Frontend Aesthetics | `opus-4.6` | default | |
| Frontend Architecture | `gpt-5.3-codex` | default | |
| Architectural Critique | `gpt-5.2` | extra high | |
| Sprint Planning | `consensus(opus-4.6, gpt-5.2)` | high / extra high | |
| Devops Tasks | `opus-4.6` | default | |
| QA Orchestration | `opus-4.6` | default | |
| Security review | `gpt-5.3-codex` | high | |
| Bulk classification | Any | default | Go up cost and strength as needed |
| Bulk MapReduce | Any | default | Go up cost and strength as needed |
| UX Ideation | `gemini-3-pro-image-preview` | default | Nano Banana Pro |
| Agentic dialogues | `gemini-3-flash-preview` | default | General message handling loops with user interaction and limited tool calling |
| Voice (interactive) | `gpt-realtime-1.5` | default | Internal use; not yet an official default |

*Consensus operator refers to an LLM merge of the points from independent plans.*

## Change Log

### February 23rd, 2026
No specific changes in defaults, but please note for anyone evaluating Gemini 3.1, the `gemini-3.1-pro-preview-customtools` may significantly outperform `gemini-3.1-pro-preview` depending on your harness. We've switched to `gpt-realtime-1.5` for our internal use cases but aren't officially defaulting to it yet. Very happy with Sonnet 4.6, it may overtake Opus for some of our everyday use cases.

### February 13th, 2026
Happy with `gpt-5.3-codex-spark`. `gpt-5.3-codex` continues to be our 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. We're very happy with `gpt-5.3-codex`. No problems with Opus 4.6 so far.