Case study · personal ops · 2026
fredis: the assistant that runs my working day.
A private assistant: 24 skills, persistent memory, and agents wired into Slack, Gmail and HubSpot that draft everything and send nothing. I hold the only send key.
My own live product, built outside this concept. Not work for Fin.
- skills, loaded per task
- 24
- repos on one board
- 9
- advisors: researcher, analyst, PA, CEO, builder
- 5
- send key, held by me
- 1
The context
Five products in a year, solo, means a studio’s operations land on one person. fredis carries that load and holds research, notes and decisions across sessions, so nothing resets between working days.
The bet
An assistant earns trust through what it is not allowed to do. Every agent drafts; none sends. Every outbound word stays mine.
The design decisions
Agents draft everything, send nothing.
Agents prepare replies, follow-ups and outreach inside Slack, Gmail and HubSpot, and stop there. The send is mine. Every product in this portfolio inherited the rule.
Nothing runs without an approved PRD.
An approved PRD first, one session at a time, and the work arrives as a reviewable draft. A diff is a proposal; a deploy is a decision.
Advisors carry rungs.
Each advisor has a rung setting how much it may do alone. The run history keeps every run with its cost, including the failed ones.
Skills, not one long prompt.
Skills load by task. When a way of working improves, the skill is edited once and every later session inherits it.
Memory is the product.
Research, notes and decisions persist across sessions. An assistant that forgets yesterday is a search box; one that remembers is an advisor.
The test bench for everything else.
Every pattern the other four products ship was proven here first, on my own work, where a failure costs me an afternoon instead of costing a client.
Where it stands
Private, in daily use across nine repos. The console is what can be shown; the contents stay out of frame. Ask for the walkthrough and I will run it live.
What I learned
The rules matter more than the model. Nearly everything on these screens is a limit, and those limits let one person hand real work to agents and still own every outcome.