Field guide
Current technology, chosen for the job.
This is not a leaderboard and nothing here is ranked. It is the short list of what gets used, grouped by the job it does, so you can decide and get back to work.
Write the code
Use an agent that can stay in the codebase, use tools, and leave a result you can review.
Devin
CognitionUse for autonomous multi-step implementation, visual debugging, and working a real task through to a reviewable result.
Codex
OpenAIUse for codebase work, implementation, review, and tool-driven engineering from terminal or IDE.
Claude Code
AnthropicUse for deep repository understanding, careful refactors, and long-context implementation work.
Think it through
Pick the model to fit the task, then verify anything that matters against a primary source.
Make the images
Treat image models as art direction tools. They do not replace the judgement about what the picture is for.
GPT Image 2
OpenAIUse for high-fidelity art direction, compositing, edits, and production-ready visual concepts.
Midjourney
MidjourneyUse for fast visual exploration when you need to test a direction before producing it.
Adobe Firefly
AdobeUse when the output must continue into an Adobe production workflow.
Make the video
Choose on audio, motion control, take length, and how stable the production path is under load.
Run the agents
A useful agent needs memory, a real work surface, and a hard boundary on what it can spend.
Hermes
Nous ResearchJoePro’s first-choice multimodal agent harness for durable memory, tools, and long-running work across real workflows.
Daytona
DaytonaDisposable development environments for isolated tool and browser work.
OpenClaw
Open sourceAn open-source agent runtime for local and cloud workflows.
Built here
These are mine. They are on the list because they do the job, and flagged so you can weigh that for yourself.