Luba Muzichenko Group / Field Manual 02
Five floors from better chats to repeatable work — without handing an algorithm the keys to your life.
Start here / two minutes
The useful question is not “Which AI is best?” It is “What work do I repeat, and how much authority should software have over it?”
The model landscape changes daily. New names appear, capabilities and prices move, and a rollout may reach one account, app, plan or region before another.S23 Treat this as a dated field guide, not a permanent rulebook. Follow the linked sources before you pay, publish, connect an account or automate a task.
Create one dedicated folder in Google Drive, iCloud Drive or another cloud service for your current branding, biography, writing examples, approved facts and active project files. When your AI tool supports it, connect only that folder—or upload the files you need manually. Treat the folder as your source of truth, not as permanent AI memory.
Core product facts were checked against first-party documentation on 31 August 2026. New tool additions were checked on 6 September 2026. Small source marks lead to a clickable appendix.
PracticeInstructions based on safe workflow design and hands-on use. These are recommendations, not universal facts.
OpinionTool preferences are clearly labelled. A preference is not disguised as a benchmark.
Projects are the foundation, not the destination. They organize context. Agents use context, tools and judgment to move work forward. The goal is no longer a better chat; it is a useful system that can gather, draft, check and stop for your decision.
The five-floor structure is adapted, with credit, from Grant Harvey’s 2026 guide for The Neuron.S1 The reporting, edits, examples and safety recommendations in this edition were rebuilt for a nontechnical reader.
How to Actually Use AI · Luba Muzichenko
The map
These are not five separate products. They are the layers of one agentic system: context, direction, reusable method, triggers and bounded action.
An agent with approved browser access can research, collect, draft, test and report back while you do something else. It should know exactly where to work and when to stop.
For a local run, open Terminal and enter caffeinate. The Mac stays awake until you press Control-C or close that Terminal window.S22 Keep it plugged in; closing the laptop may still stop the work.
The five-floor map
Floor one / foundation
Projects, folders and reference libraries are the context underneath an agent. They are the filing cabinet—not the employee.
01 · Projects
Floor 01 / Projects
ChatGPT Projects are available across plans. Current official limits list 5 files per project on Free, 25 on Go and Plus, and 40 on higher workspace tiers; OpenAI’s own file FAQ has not always matched those figures, so check before a large upload.S2
Claude Projects are also available to all users. Free accounts currently allow up to five projects. Paid plans add expanded project knowledge through retrieval, which means Claude can search a larger collection instead of loading every file at once.S5
More files are not automatically better. Upload the current version, use clear filenames, and remove duplicates. A project full of conflicting drafts creates conflicting answers.
ChatGPT account-level custom instructions currently allow 1,500 characters on Free and Go, and 5,000 on Plus and higher plans.S3 The earlier draft’s exact “8,000 characters in every Project” claim was removed because I could not confirm it in current OpenAI documentation.
01 · Projects
Floor two / conversation
Good prompting is not magic wording. It is a clear result, the context needed to produce it and a test for “done.”
02 · Prompting
Floor 02 / Prompting
What should be different when the work is finished?
What does the AI need to know that it cannot safely infer?
What must it preserve, avoid or ask before changing?
What should the finished answer look like, and how long should it be?
02 · Prompting
Floor 02 / Better checks
“Be brilliant” and “think harder” are not specifications. Say what to verify, what to preserve, what risk matters and what the finished object must contain.
A token is a unit of text, not a fixed number of words. The familiar “about three quarters of an English word” rule is only a rough English-language estimate. It varies by language, punctuation and content.
02 · Prompting
Floor three / reuse
When a conversation finally works, turn the successful method into instructions you can use again.
03 · Skills
Floor 03 / Skills
Claude currently supports custom Skills across Free, Pro, Max, Team and Enterprise plans; code execution must be enabled.S6 Other products may call the same idea a template, saved prompt, workflow or instruction file.
Run it on an easy example, a messy example and a missing-information example. If it only works on the conversation that created it, it is a transcript — not a skill.
03 · Skills
Floor four / repetition
An automation follows a known route. It should be boring before it is automatic.
04 · Automations
Floor 04 / Automations
Claude Cowork is a paid-plan feature on web, desktop and mobile.S7 Google and OpenAI also offer scheduled or action-taking features, but names, plan access and permissions change. Do not assume a tutorial for one app maps directly to another.
04 · Automations
Floor five / agency
An agent chooses its next step. That freedom makes it useful — and makes permissions, evidence and stopping rules part of the design.
05 · Agents
Floor 05 / Agents
One outcome a new assistant could repeat back correctly.
Only the accounts and actions required for that goal.
How it checks the world after each action instead of trusting its own story.
What needs approval; what it may never do.
A definition of done, a retry limit and a clear blocked state.
Anthropic describes agents as models using tools in a loop, checking results from the environment and pausing for human feedback or stopping conditions. It also warns that autonomy can compound errors and recommends testing in sandboxed environments.S9
Model Context Protocol, or MCP, is an open standard for connecting AI applications to data sources and tools. It is plumbing, not a safety guarantee.S10
05 · Agents
Floor 05 / Safety
Do not install it on your normal personal or work computer unless you can independently secure and isolate it. Microsoft’s security team says OpenClaw is not appropriate for a standard workstation and recommends an isolated environment.S11 The project also maintains an active list of security advisories.S12
This edition deliberately removes unstable vulnerability counts and the earlier recommendation of another self-hosted agent. A nontechnical guide should not turn a complicated server-security choice into a casual software suggestion.
05 · Agents
A useful agent / real estate
One transaction starts the workflow. The agent gathers approved facts, prepares the welcome package and stops before anything is sent.
The transaction reaches an agreed milestone, such as entering contract. A person confirms the trigger.
Read only the approved transaction summary, key dates, contacts, responsibilities and current client-facing templates.
Draft the welcome email, milestone checklist, contact sheet and a list of any missing or conflicting facts.
Create a short orientation script. HeyGen can turn an approved script into a video using your own digital avatar.S16
You verify every name, date and expectation. The system may prepare the package; you remain the sender.
Use an avatar for repeatable logistics: key dates, contacts and what happens next. Record yourself when reassurance, negotiation, celebration or bad news is the point. Never imply that a synthetic video was personally recorded for that client that day.
An agentic client workflow
Tool map / editorial, not a leaderboard
Opinion These are practical starting points, not permanent rankings. Product quality and plans move too quickly for a printed “best” list.
| Job | Start with | Why it is on the shortlist |
|---|---|---|
| Daily general work | ChatGPT, Claude or Gemini | Choose the one you will actually organize into Projects and use consistently. |
| Current web research | Perplexity | Searches the live web and places citations beside its summaries; open the cited pages before relying on them.S17 |
| Source-bounded notebooks | NotebookLM | Useful when the answer should stay close to a defined set of sources. |
| Meeting notes | Fathom or Fireflies | Purpose-built capture, transcript and summary workflows. |
| Your talking avatar | HeyGen | Useful for repeatable explainers and training; authenticity and disclosure still matter.S16 |
| Creative image and video | Higgsfield or Runway | Creative suites for generated visual work; use low-stakes assets while experimenting.S21 |
| Coding agent | Cursor | Can inspect a codebase, edit files and run commands; review its changes before shipping.S18 |
| Simple app prototypes | Lovable or Bolt | Fast route from plain-language brief to a working prototype. |
| Connect apps | Make or Zapier | Visual automation tools. Review each app permission before connecting it. |
| Persistent self-hosted agent | Hermes Agent | Advanced. Supports memory and scheduled work, but requires deliberate approvals and isolation—not a casual install.S19S20 |
One tool can research, your reference library can supply approved facts, another can draft or create video, and an agent can coordinate the steps. The human approval point is part of the system—not evidence that the system failed.
Tool map
Reality check / before you trust a tool
A polished demo proves that a tool worked once. Before you pay, connect client information or leave an agent running, check what is true for your account today.
Use the vendor’s current documentation—not a screenshot, social post or old tutorial.
A model may exist without being available in your app, plan, account or region.S23
Know what the tool can read, change, send, publish or delete before you connect it.
Plans, limits and usage charges move. Use the vendor’s live pricing page.
Use old or invented data. Watch what it does, where it stops and whether the result can be undone.
Save the source links, date checked, prompt, output and any approval you gave.
Can I see the source? Is it current? Is this feature available to me? What can the tool touch? Who approves the consequential action? If any answer is unclear, stop before connecting the account.
Published 31 August 2026 · Updated 6 September 2026
Reality check
Sources / clickable
Published 31 August 2026; updated 6 September 2026. New tool additions were checked against first-party pages on the update date. Product documentation can change without notice; use these links to confirm current details.
Sources · 1 of 3
Sources / clickable
Sources · 2 of 3
Sources / new tool additions
Luba Muzichenko is a San Francisco Realtor with two decades of experience helping buyers and sellers across the city. She builds practical AI systems for real estate and speaks about both the San Francisco market and everyday AI use.
Visit LubaSF.com for San Francisco real estate →
[email protected] · (415) 449-8488 · DRE #01768716
Prepared for Luba Muzichenko Group. The PDF may be shared intact with attribution. Product names belong to their respective owners.
Sources · 3 of 3