Working Memory
How many things are you trying to hold in your head right now?
| Juggling | Writing it down |
|---|---|
| Forget where you were | Know where you left off |
| Shallow work all day | Deep work by design |
| Drag from the last thing | Clean start every time |
Working memory is volatile. Task switching can evict the state needed for the current decision and force you to reconstruct it later.
Treat five things as a local interface budget, not a universal biological law. The useful rule is simpler: externalize volatile state, then retrieve only the context needed for the decision in front of you.
Flow State
Overloading and needless Context Switching is the enemy of flowing progress.
Your brain is for having ideas, not holding them.
Deep work needs a clear head. A clear head needs a place to put things. That place needs a rhythm — morning to load, day to capture, evening to clear. A text file does this. Everything else exists to protect the conditions for deep work.
Four Types
The same types show up in people and machines:
| Type | You | A Machine | What to Do |
|---|---|---|---|
| Working | The active decision state | Context window | Externalize volatile state |
| Episodic | What happened to you | Logs, conversation history | Journal it while fresh |
| Procedural | Skills you practised | Trained behaviours | Repeat until automatic |
| Semantic | Facts you know | Knowledge bases | Look it up, don't memorise it |
Better memory management means better thinking. True for people. True for machines.
Get It Out
Put everything into a system you trust:
| What | Where | Why |
|---|---|---|
| Tasks | One task list | Unwritten tasks nag in the background |
| Decisions | Shared notes, right after | You forget the details within hours |
| Ideas | A capture tool you always have | Good ideas rot fast |
| Context | "Where I left off" notes | Saves twenty minutes tomorrow morning |
| Facts | A searchable place | Never memorise what you can look up |
The test: can you forget about it and trust the system to hold it? If not, your head is still carrying the weight.
Five as a Design Budget
Five is a useful compression constraint for the Tight Five and small decision interfaces. It is not a claim that every person, task, or machine has exactly five fixed slots.
| Try four | What falls out |
|---|---|
| Drop Performance | No scoreboard — you drift without knowing |
| Drop Players | No ecosystem — you build alone without calibration |
| Try six | What blurs |
|---|---|
| Add "Culture" | Already inside every slot — not a separate thing |
| Split Platform in two | Same lens, same slot — you just can't see it yet |
Four loses a dimension. Six hides a duplicate. Five is the minimum viable picture of the whole. The Tight Five is not a framework you adopt. It is a constraint you discover.
The same five recurs here because a stable local pattern reduces retrieval and comparison cost:
| Scale | The Five |
|---|---|
| Working memory | Five slots in your head |
| Tight Five — inner | Performance, Principles, Platform, Process, Players — what you control |
| Tight Five — outer | Purpose, Principles, Platform, Perspective, Performance — how you serve |
| Business hats | Strategy, Production, Technology, Finance, Compliance |
| Customer journey | Attraction, Persuasion, Navigation, Validation, Renewal |
| PromptDeck | Five slides, five questions, five answers |
| Work fronts | Strategy, Project Mgt, Marketing, Platform, Performance |
| Week plan | Five bets max. Five days. Five lenses per session. |
Same pattern, different zoom. If five hides a needed distinction, change the local interface rather than treating the number as doctrine.
Chunking
Five slots. Make each slot hold more:
| Scattered | Chunked |
|---|---|
| Eight random digits | Four two-digit pairs |
| Twelve loose tasks | Three projects, four tasks each |
| A long argument | Setup, core point, conclusion |
Expertise changes how information is chunked and retrieved. The design goal is not to maximize what stays in mind; it is to make the next relevant chunk cheap to recover.
Protect It
| Threat | What it costs | Defence |
|---|---|---|
| Notifications | Twenty minutes per interruption | Silent mode during deep work |
| Switching tasks | Nearly half your productive time | One theme per day |
| Too many tabs open | Attention split across all of them | Close what you don't need now |
| Back-to-back meetings | Residue from the last one | Five-minute gap between them |
| No clear next step | You stall and drift | Write the next step before you stop |
The Text File
A plain text file. One section per day. Three parts. Nothing else.
## 2026-03-25
### Plan
- [ ] The work that fits today
- [ ] One more thing, maybe two
### Capture
- thing that came up during work
- idea that arrived uninvited
### Clarify
- Done: what got finished
- Moved to Friday: what didn't
- Killed: what turned out not to matter
The rules:
- Nothing carries over. If it didn't happen today, give it a future date or kill it.
- Plan the night before. Your sleeping brain loads context overnight.
- One theme per day. Switching themes costs almost half your output.
- Capture without stopping. When something comes up, write it down and keep going.
- Clarify every evening. Move it, finish it, or kill it. Nothing stays in capture overnight.
- Five to seven items. More than that means you haven't grouped them.
- Keep old days. The file grows down. You can search it later.
Plan loads the buffer. Capture keeps it from overflowing. Clarify empties it. The file is today's workspace, not a permanent record.
Human and Machine
The same file works for both:
| You | Your AI agent | |
|---|---|---|
| Plan | Morning — what matters today | Session start — what to work on |
| Capture | Things that come up | Discoveries mid-session |
| Clarify | Evening — move it or kill it | Session end — update the log or kill it |
| Handoff | Your "where I left off" is the agent's morning briefing | The agent's summary is your context next session |
Your evening writes the agent's morning. The agent's close writes your next start. The text file is where the two meet.
The Day
- Morning — Read your file. Pick the one thing.
- Deep work — Best hours. One task. No interruptions.
- Admin — Inbox, replies, updates. Batch it.
- Close — Write where you left off. Clear the capture list. Shut down.
- Rest — Trust the system. Let your brain recover.
The Trap
Collecting instead of doing. Refusing to write it down because you think you should remember it. Perfecting the system instead of using it. Organising as a substitute for output.
The system exists to free your mind for work. If you spend more time on the system than on the work, the system won.
By Archetype
| Archetype | How they use memory |
|---|---|
| Engineer | Holds complex systems — needs external scaffolding |
| Philosopher | Connects across domains — needs long unbroken stretches |
| Coach | Remembers people — needs context about relationships |
When To Use
Use this pattern the moment your day fragments across too many open threads. The principle is one trusted place to put everything, cleared on a fixed rhythm. Reach for it when you notice yourself re-deriving where you left off, or when an agent session reboots with no memory of the last one.
Use the Knowledge Schema for durable memory: one canonical home, stable chunks, progressive disclosure, retrieval triggers, and typed relationships. Working memory should carry only the current decision and the evidence it needs.
Retrieval trigger: return when a person or agent must reconstruct the active decision after a task switch. Store durable context in its canonical Playbook or governed project home; keep only volatile session state in the daily buffer. Evidence of success is less re-derivation without a larger active context.
Failure Modes
- The system becomes the work. Perfecting the file instead of clearing it. The rhythm exists to free the mind, not to be tuned.
- Backlog creep. Letting yesterday's uncleared items ride into today. Nothing carries over — date it forward or kill it.
- Overloading a slot. Cramming eight threads into five. When the picture blurs, group before you add.
- Silent staleness. Trusting a buffer that has gone cold. If you cannot state the next step from the file, the buffer failed.
Context
- Focus — Memory management sustains deep work
- Planning — Working memory enables execution
- Deep Work — Protecting the workspace
- AI Data Pipelines — How AI extends memory
Links
- Cal Newport — WorkingMemory.txt — The volatile session buffer
- Jeff Huang — One Text File for 14 Years — Date-separated, no backlog, night-before planning
- Megabite — Working Memory Text File System — Daily logs, end-of-day review
Signal
Changes my mind: show that externalizing and retrieving decision state adds more cost than it saves across repeated task switches; the case for the buffer would narrow.
Next question: what is the smallest shared file format that a human and an agent can both write to and read from without translation?
Questions
What happens when a person and a machine share the same memory file?
- What is the smallest file that supports both a human day and an agent session?
- When you write "where I left off" and a machine reads it tomorrow, what survives and what gets lost?
- Which chunk and retrieval cue let an expert recover the needed model with the least noise?
- How do you know your buffer is stale before it costs you?