Documentation Index
Fetch the complete documentation index at: https://2bd.l48a.de/llms.txt
Use this file to discover all available pages before exploring further.
Ada is your interface
Ada is your Executive Assistant - the primary way you interact with 2bd. Rather than managing templates, archives, and workflows manually, you simply talk to Ada. She coordinates everything behind the scenes.
When you say “Ada, run my morning ritual” or invoke /ada plan daily, Ada orchestrates a team of specialized assistants to prepare your day, fetch calendar context, and compose your working notes.
The ritual loop
2bd operates on a simple cycle: plan - work - reflect - archive.
This loop is powered by the GPS methodology - Goal, Plan, System - which cascades from yearly vision down to daily execution.
2bd organizes notes by metabolic state - how active and volatile they are - rather than by topic.
| State | Purpose | Location |
|---|
| Captive | Working notes - high-velocity, volatile intake | 00_Brain/Captive/ |
| Synthetic | Active drafts - projects in progress | 00_Brain/Synthetic/ |
| Periodic | Archives - the permanent timeline | 00_Brain/Periodic/ |
| Semantic | Reference - crystallized knowledge | 00_Brain/Semantic/ |
| Systemic | Structure - templates, workflows | 00_Brain/Systemic/ |
Metabolic states solve the “where does this go?” problem by organizing around information lifecycle. Fresh notes go to Captive. Active work lives in Synthetic. Completed work archives to Periodic. The system moves information naturally without you deciding where things belong.
Ada’s assistant team
Ada manages a team of domain-specific assistants:
| Assistant | Handles |
|---|
| brief | Context synthesis, leadership intention |
| goals | 1-3-5, Major Moves, Quests, Annual Goals |
| calendar | Meeting prep and review |
| journal | Reflection and personal insights |
| achievements | Win capture and impact evidence |
| relationships | People touchpoints |
| projects | Project status tracking |
Each assistant specializes in one domain and knows how to handle that domain across all timescales.
How rituals run
The orchestration process
- Parse the action (plan/reflect) and timescale
- Run each assistant’s action for that timescale
- Each assistant writes to
Synthetic/Assistants/{name}/
- Compose outputs into Captive (plan) or Periodic (reflect)
- Learn patterns from observations
Parallel Execution
As of v1.2, Ada runs assistants in parallel for 70-80% faster rituals.
The parallel flow:
- Draft generation - All assistants run as background agents simultaneously
- Context analysis - Each agent reads vault, generates template section with placeholders
- Draft collection - Ada gathers all drafts and extracts questions
- Intelligent ordering - Ada orders questions for natural conversation flow
- User interaction - Ada asks questions, collects answers
- Placeholder filling - Ada fills all placeholders with answers
- Composition - Ada assembles final note from filled sections
Placeholder format:
Assistants use HTML comment syntax for unknowns:
<!-- ASK:unique-id
What's your top priority today?
-->
After you answer, Ada replaces placeholders with your responses.
Error handling:
If an assistant agent fails:
- Other assistants continue normally
- Failed sections noted in final output
- Partial results still usable
Configuration:
Control via vault/00_Brain/Systemic/Config/ada.yaml:
Set to false to use legacy sequential mode.
Template architecture
Templates are split between Ada and assistants:
| Location | Purpose |
|---|
.claude/skills/ada/templates/ | Ada’s base templates (frontmatter, navigation, changelog) |
.claude/skills/_assistant-{name}/templates/ | Each assistant’s section templates |
vault/00_Brain/Systemic/Templates/Ada/ | Vault copy of Ada templates |
vault/00_Brain/Systemic/Templates/Assistants/{name}/ | Vault copy of assistant templates |
Ada composes Captive notes by:
- Loading the base template for the timescale
- Reading section order from
vault/00_Brain/Systemic/Ada/section-order.md
- Inserting assistant sections in the defined order
- Each assistant owns specific H2 sections in the final document
Reflect flow
During reflection, each assistant:
- Loads its template from vault
- Compares plan output to actual capture note section
- Returns findings (variance, coaching questions, entity learnings) to Ada
- Ada aggregates findings into a coaching conversation
- Confirmed entity learnings persist to vault (People, Projects)
Quick reference
# Planning rituals
/plan # Plan today (default)
/plan daily # Morning ritual
/plan weekly # Monday
/plan quarterly # Start of quarter
/plan yearly # Start of year
# Reflection rituals
/reflect # Reflect on today (default)
/reflect daily # Evening ritual
/reflect weekly # Sunday
/reflect quarterly # End of quarter
/reflect yearly # End of year
Planning rituals
Run in the morning (or start of period):
/ada plan daily # or "Ada, run my morning ritual"
/ada plan weekly
/ada plan quarterly
/ada plan yearly
Each assistant:
- Loads context from higher timescales
- Runs interactive conversation with you
- Writes structured output to Synthetic
Reflection rituals
Run in the evening (or end of period):
/ada reflect daily # or "Ada, let's reflect on today"
/ada reflect weekly
/ada reflect quarterly
/ada reflect yearly
Each assistant:
- Reviews planned vs actual
- Captures insights and patterns
- Records observations for learning
Time scales
The loop runs at four scales, each nesting into the next:
| Scale | Planning | Reflection | Working note | Archive |
|---|
| Daily | Morning | Evening | Today.md | Daily/ |
| Weekly | Monday | Sunday | Week.md | Weekly/ |
| Quarterly | Start | End of quarter | Quarter.md | Quarterly/ |
| Yearly | January | December | Year.md | Yearly/ |
Captive (composed by Ada) Periodic (archived by Ada)
-------------------- ----------------------------
Today.md --reflect--> Daily/YYYY-MM-DD.md
Week.md --reflect--> Weekly/YYYY-Www.md
Quarter.md --reflect--> Quarterly/YYYY-QN.md
Year.md --reflect--> Yearly/YYYY.md
Daily insights feed into weekly reviews. Weekly patterns inform quarterly direction. The system synthesizes upward automatically.
Self-learning
Ada’s learn assistant analyzes patterns across all assistants:
- Observe - Each assistant records observations
- Cluster - Similar patterns are grouped
- Graduate - High-confidence clusters move to Semantic
- Remember - Graduated insights inform future sessions
Your rituals evolve to match how you actually work.