Comparing the current Fabro marketing site fonts against 3 alternatives
Display: Space Grotesk · Body: DM Sans · Mono: JetBrains Mono
Stop babysitting agents. Define your process as a workflow graph, let AI agents execute it, and intervene only where it matters.
Define multi-step processes as Graphviz directed graphs. Each node is a stage with its own prompt, model, and tools.
Hexagonal approval gates let humans review, revise, or override at any point in the workflow.
Assign models per-stage with CSS-like selectors. Use Haiku for triage, Sonnet for code, Gemini for review.
digraph PlanImplement { graph [ goal="Plan, approve, implement, and simplify" ] plan [label="Plan"] approve [shape=hexagon, label="Approve Plan"] implement [label="Implement", class="coding"] start -> plan -> approve -> implement -> exit }
Every workflow can include build gates, test assertions, and human approval stages. When a stage fails, Fabro routes back to the appropriate fix loop — no manual re-runs, no git stash gymnastics.
The retrospective engine runs after every workflow, surfacing what went wrong and why. Over time, your workflows get smarter.
Display: Outfit · Body: Lexend · Mono: Fira Code
Stop babysitting agents. Define your process as a workflow graph, let AI agents execute it, and intervene only where it matters.
Define multi-step processes as Graphviz directed graphs. Each node is a stage with its own prompt, model, and tools.
Hexagonal approval gates let humans review, revise, or override at any point in the workflow.
Assign models per-stage with CSS-like selectors. Use Haiku for triage, Sonnet for code, Gemini for review.
digraph PlanImplement { graph [ goal="Plan, approve, implement, and simplify" ] plan [label="Plan"] approve [shape=hexagon, label="Approve Plan"] implement [label="Implement", class="coding"] start -> plan -> approve -> implement -> exit }
Every workflow can include build gates, test assertions, and human approval stages. When a stage fails, Fabro routes back to the appropriate fix loop — no manual re-runs, no git stash gymnastics.
The retrospective engine runs after every workflow, surfacing what went wrong and why. Over time, your workflows get smarter.
Display: Instrument Serif · Body: Instrument Sans · Mono: IBM Plex Mono
Stop babysitting agents. Define your process as a workflow graph, let AI agents execute it, and intervene only where it matters.
Define multi-step processes as Graphviz directed graphs. Each node is a stage with its own prompt, model, and tools.
Hexagonal approval gates let humans review, revise, or override at any point in the workflow.
Assign models per-stage with CSS-like selectors. Use Haiku for triage, Sonnet for code, Gemini for review.
digraph PlanImplement { graph [ goal="Plan, approve, implement, and simplify" ] plan [label="Plan"] approve [shape=hexagon, label="Approve Plan"] implement [label="Implement", class="coding"] start -> plan -> approve -> implement -> exit }
Every workflow can include build gates, test assertions, and human approval stages. When a stage fails, Fabro routes back to the appropriate fix loop — no manual re-runs, no git stash gymnastics.
The retrospective engine runs after every workflow, surfacing what went wrong and why. Over time, your workflows get smarter.
Display: Syne · Body: Manrope · Mono: Source Code Pro
Stop babysitting agents. Define your process as a workflow graph, let AI agents execute it, and intervene only where it matters.
Define multi-step processes as Graphviz directed graphs. Each node is a stage with its own prompt, model, and tools.
Hexagonal approval gates let humans review, revise, or override at any point in the workflow.
Assign models per-stage with CSS-like selectors. Use Haiku for triage, Sonnet for code, Gemini for review.
digraph PlanImplement { graph [ goal="Plan, approve, implement, and simplify" ] plan [label="Plan"] approve [shape=hexagon, label="Approve Plan"] implement [label="Implement", class="coding"] start -> plan -> approve -> implement -> exit }
Every workflow can include build gates, test assertions, and human approval stages. When a stage fails, Fabro routes back to the appropriate fix loop — no manual re-runs, no git stash gymnastics.
The retrospective engine runs after every workflow, surfacing what went wrong and why. Over time, your workflows get smarter.