A calmer way to make progress.

01 · The problem

Too many things in motion. Too little finished.

Messages arrive faster than you can read them. Work scatters across chat, boards, and people’s heads. Ask “what should I do right now?” and nothing gives you an honest answer.

Most tools respond with more: more dashboards, more views, more notifications. They demand your attention instead of protecting it. Now AI is joining in - another voice, another stream of work to manage.

02 · The approach

One thing, then done

123.do brings work back to a simple rhythm. Everything to do waits in DO, in order. You pull one Step into NOW. You finish it. It moves to DONE, and the next one is ready.

Only one Step in NOW per person - the same rule for humans and agents. That one constraint protects attention and lets a team move calmly together. No streaks, no scores, no guilt.

Agents join as teammates and do the boring parts. People conduct: agents act only where a person set them in motion, and you can pause d1on on any Track - nothing starts on its own while your own work continues.

The models are yours too. Plug in whatever AI you like, on your own keys, paid to the provider at cost. You bring the model; 123.do brings the consistent agent layer that drives it. That layer is your organisation’s memory, and it lives above the model: you are never locked into one LLM, and a cheaper model is one swap away. Your history is yours, in one place.

See how it works

03 · The maker

Made in Bath, England

Built by Nige Ltd.