CoreWise Academy

Foundations · Layer I / Broad

A practical guide to Claude's features

Choose where Claude should work, what it should make, which instructions to save, and when to use a goal or scheduled task.

Nº 066 · Vol. I·14 min read· Updated November 2026

To turn weekly sales exports into a report, Claude needs the files, instructions for calculating the totals, and an output you can review. Each feature handles a different part of that job. Choose the feature by what is missing.

Nate Herk’s Every Claude 2.0 Concept Explained for Non-Coders groups Claude’s features by models, apps, outputs, saved context, and independent work. “Claude 2.0” is his nickname for recent changes, not a model name. The distinctions below follow that grouping, with product details checked on October 30, 2026.

Austin Marchese’s 7 NEW Claude Features To Get You Ahead of 99% of People Using AI adds practical uses for Google Workspace, dashboards, mods, and remote sessions. Those additions were checked against Anthropic’s documentation on November 5, 2026.

01Separate the settings

Model choice and effort answer different questions. Haiku, Sonnet, Opus, and Fable are model names; effort controls how much work the chosen model spends on a response. Anthropic’s model settings let you change them separately.

TermWhat it controlsWhat to check
ModelWhich model performs the taskWhether it can produce an acceptable result on your actual work
EffortHow much work that model spends respondingWhether more effort improves the result enough to justify the time and usage
TokenA unit of text processed by the modelInput as well as output contributes to usage
Context windowHow much information a model can work with at onceFiles, instructions, conversation, and room for the response
Usage limitHow much work your plan permits over timeYour current allowance and reset time

Herk’s seven-workflow comparison favored Sonnet for clearly specified tasks and Opus for vague planning work. Treat that as a reason to compare models on your own tasks, rather than assuming a more expensive model will win.

Herk also reports a comparison on one task where extra-high effort beat max: roughly 90 minutes and $26 versus 150 minutes and $50, with bugs remaining at max. Those are his reported results for that task. They do not establish the best setting for yours.

Anthropic’s effort guidance starts at the model’s default and adjusts based on results. Ultracode also coordinates work across agents; it is a separate setting, not another effort level.

For a hard decision within a larger task, Claude Code’s advisor tool lets the main model consult a stronger model. Recheck your model choices each release covers comparing settings on work you can judge.

Try a cheaper model on a copy of work you have already checked. Marchese suggests testing Haiku 5.5 on your own task. For the sales report, compare its totals, missing-data warnings, and drafting time with your current model. Count retries and corrections when comparing cost.

As of November 5, 2026, Haiku 5.5’s standard API rates are $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 100,000 tokens. Above that threshold, the rates are $0.50 and $2.50. These rates apply when software sends requests through Claude’s API. Your Claude app subscription has a separate allowance.

A large context window does not give unlimited usage. Anthropic’s limits documentation distinguishes context capacity from shared usage across Claude products. Most paid plans have five-hour and weekly limits; verified Ultra accounts are exempt from the five-hour limit. Context capacity varies by model and product.

Check Settings > Usage before buying more capacity. Usage credits pay for work beyond included limits. The monthly API credits included with Max and Ultra are separate and do not pay for extra usage inside Claude or Claude Code. Stop hitting your token limit covers reducing unnecessary input.

02Choose where the work runs

PlaceUse it forCheck first
Claude chatQuestions, research, and documents using supplied or connected materialWhether the needed files and tools are available
Claude CodeWork in a project folder, including reading files, editing them, and running commandsWhich folder and actions the session can access
CoworkDelegated work across files and toolsYour current interface: Cowork and chat are merging
DuetOngoing help through connected apps, such as an email and calendar briefWaitlist access, connected accounts, and background usage

Anthropic announced the Cowork and chat merger on September 16, 2026. Herk’s separate categories may not match the tabs on your screen. Choose by available capabilities. A local Code session is useful for the sales report when the exports already live in a folder on your computer.

A session is one conversation and its working context. Several sessions can work in parallel. Give them distinct outputs or coordinate edits so two sessions do not overwrite the same file. The desktop documentation covers parallel sessions and communication between them.

Google Workspace. When the report already lives in Google Docs, Sheets, or Slides, use Claude in the file. The Workspace add-on can work on selected text, cells, or slides and use your Claude skills and connectors. Sheets supports native formulas and charts; Slides can use the deck’s layouts and themes. This is the practical benefit behind Marchese’s Workspace example.

Install the add-on from Google Workspace Marketplace, then open a file and choose Extensions > Claude > Open Claude, following the setup guide. It is a paid-plan beta, and your organization may restrict installation. Start with Ask before edits so you can inspect proposed changes.

The separate Google Docs, Sheets, and Slides connectors let you create or edit Google files from Claude. Choose that route when starting a new report or combining several files. Choose the add-on when reviewing a file already open in Google Workspace.

Remote Control. To continue a local Code session from your phone, enter /remote-control in that session and open its link in Claude on the other device. Remote Control needs an eligible paid subscription and may require organization approval. The files, tools, and running process stay on your computer.

Marchese pairs phone access with keeping the computer awake. Current desktop guidance places Keep computer awake under Settings > Desktop app or Settings > This computer > System. Keep the app running and the computer online; closing a laptop lid still puts it to sleep. Before leaving a long task, send a harmless message from your phone and confirm that the local session receives it.

A side chat asks about the current session without adding its question and answer to the main conversation. In the Windows desktop app, use Ctrl+; or /btw. Side chats are not saved to disk, so move any decision the main task needs into the main conversation. Improve your Claude Code workflow covers when a side question belongs there.

Duet is a US research preview accessed through a waitlist on Pro, Max, and Ultra. It works on its own cloud computer and is designed to ask before consequential actions. Its background work consumes your plan’s usage. Review drafts and approval requests; access to an app does not prove the result is correct.

03Choose the output

An artifact is an output you can open and work on beside a conversation. It is different from the model or app that made it.

OutputChoose it when you need
DocsA written report that people can read and edit
SlidesA presentation you can deliver or export
DesignA visual layout, screen, or mockup
DashboardsCharts connected to data that changes
MotionAn animated explanation you can export as video

Anthropic’s October 8 announcement puts Docs, Slides, and Design on every plan, including Free. Dashboards are a paid-plan beta; Motion is a Team and Enterprise beta. Organization settings can affect access.

For a weekly sales report, choose a document if someone needs to read commentary and a dashboard if they need to explore refreshed figures. A dashboard’s query is the instruction that selects and totals its source data. Marchese’s dashboard demonstration shows why access to that calculation helps you check the result.

Click a dashboard number to inspect its query, or ask Claude to explain it. Check:

  1. Which source rows, dates, and refund rules produced the total.
  2. Whether your own calculation from those rows matches it.
  3. When the chart last refreshed, and whether newer records are missing.

The query can still use the wrong definition of revenue. Agree on that definition before treating the chart as a business report.

For written commentary, ask for a Docs artifact and select the passage you want changed. Marchese uses selected-text edits for longer documents. Check the revised passage and its surrounding text before accepting it. If collaborators already work in a Google Doc, use the Workspace route above.

For a deck, give Claude the claim the audience needs to understand and any brand files or reference slides. Marchese recommends an original idea, design references, and several versions. Ask for five opening-slide directions, choose one, then build the deck from it. Review a visual plan before you build covers comparing directions before completing the work.

Check delivery before spending time polishing a deck. Current sharing rules depend on the artifact and access method: Docs and email invitations require a Claude account; most artifacts shared with Anyone with the link allow viewing without one. Organization rules can restrict sharing, and connected data needs its own access. Test the intended recipient’s access, or export to PowerPoint, PDF, or editable Google Slides and inspect the exported file.

Motion animates text, charts, shapes, and images with code and exports MP4; it does not generate video footage.

Design now works inside Claude conversations. The standalone Design site is due to close on December 14, 2026. Follow Anthropic’s Move from standalone Claude Design to Claude for existing work. The older Move design work into Claude Design guide describes the earlier interface and the design workflow.

04Save the right thing

Instructions, procedures, and access solve different problems. Herk’s skills explanation starts with a repeated request that becomes a saved procedure.

“A skill is a saved set of instructions for one specific job”

Nate Herk, “Every Claude 2.0 Concept Explained for Non-Coders” · 13:44
FeatureWhat it saves or addsSales-report example
Auto memoryNotes Claude writes for later sessionsA correction about how your team names a region
CLAUDE.mdStanding project instructionsWhere exports live and which definition of revenue to use
SkillA reusable procedure in SKILL.mdCalculate the weekly totals, compare periods, and draft commentary
ConnectorTools for a connected service, often using MCP, the Model Context ProtocolRead the approved sales data
PluginA package of extensionsDistribute the reporting skill and related tools to a team
ModCode that changes Claude Code’s tools or interfaceAdd a panel showing report progress

Claude Code memory carries notes across sessions by reading saved files. It does not retrain the model. Keep CLAUDE.md short and put detailed procedures in skills, whose full instructions load when needed. Review saved notes when a correction stops applying. Audit what your agent saved to memory covers that check.

A connector provides access; a skill explains how to use that access for your task. A plugin packages extensions for reuse. Anthropic’s extension overview explains those boundaries. Write smaller Claude skills that work covers saving repeated instructions, and One skills library for your whole team covers sharing them.

Install a mod with the same care as other software. It runs with your account’s permissions and can read files, start programs, and make network requests. A friendly panel does not limit what its code can do. Use an existing skill or connector when that already meets the need.

Choose a mod for a repeated problem you can name. Marchese’s examples are a usage display and a reminder to save corrections. A usage display should help you decide when to shorten a session; compare it with Settings > Usage before treating it as a measure of your remaining allowance. A correction reminder should show the proposed rule for review so a one-off request does not become a permanent instruction. Turn repeated fixes into rules covers deciding what deserves to persist.

If you keep a mod, install it as a plugin and confirm that it loads in a fresh session. Its availability can differ between the terminal, desktop, and remote interface.

05Control independent work

Permission modes determine how Claude Code approves actions. Current documentation lists these modes:

ModeApproval behavior
ManualPrompts for actions that need approval
Accept editsAllows file edits and common file commands in permitted directories
PlanExplores and proposes work without editing source files
AutoUses a background classifier for actions that would otherwise need routine approval
Don’t askDenies actions that would require a prompt, subject to documented exceptions
Bypass permissionsSkips most permission prompts

Auto is not a guarantee that every action is safe. Use permission rules to control access, and inspect the work. Writing “never send email” in CLAUDE.md does not remove a sending tool. Assume your agent uses every tool it has explains that distinction.

The features that organize independent work also differ:

FeatureJobLimit to remember
SubagentHandle a bounded task in separate context and return resultsIts requests still consume usage
Code projectCoordinate ongoing work through separate task threadsCloud threads need their own available files and tools
/goalKeep a session working toward a completion conditionCompletion depends on the evidence in the conversation
Scheduled taskStart work at a later time or on a supported triggerLocal and cloud runs have different access and runtime requirements

Subagents keep research out of the main context; they do not make it free. Give a report-checking subagent the draft report and the totals you calculated from the exports. Ask it to identify any differences. Delegate to your agent in stages covers reviewing work before expanding responsibility.

Code projects coordinate a stream of tasks, usually through cloud sessions. That is different from the classic chat project that groups conversations with shared instructions and files. A cloud project does not automatically inherit your local skills, settings, or tools. Check its configuration before moving a working process there.

Coordinating projects are a staged public beta on Pro, Max, and Ultra; they are not yet offered on Team or Enterprise. Use a coordinating project when work keeps arriving for the same purpose. For reporting, one thread could investigate a data discrepancy while another drafts commentary from totals you have approved.

Marchese’s project example describes a coordinator that starts task threads and reports which need your input. Check the results each thread returns before combining them into the report.

With /goal, specify a result and the evidence for it. The evaluator reads what the session reports; it does not independently inspect your files. A goal can end as impossible or stop on an error requiring your action. Give your coding agent a finish line covers defining the evidence Claude must report before calling a task complete.

Scheduled tasks start a new run. Local tasks need the computer awake and the app open. Cloud scheduled tasks, formerly called routines, can run while your computer is off. They need access to their inputs in the cloud. Test the scheduled run itself, as described in Keep Claude automations working.

06Try one complete report

Herk’s starting advice is a project instruction file, one useful skill, and a clear goal. Start with sample exports and a report you can check before connecting live accounts or adding a schedule. Set up Claude Code in seven steps covers the broader setup.

Use this original prompt in a local Code session:

Read the sample sales exports in this folder. Ask me how revenue, refunds, and the reporting week should be defined if the files do not make those rules clear.

Create a draft weekly report showing the source files, reporting dates, revenue total, and any missing or conflicting data. Show the calculation behind the total. Keep the source files unchanged. Do not connect accounts, send the report, or create a schedule.

Finish when the draft and calculation are saved and you have compared the reported total with the source rows. If a missing definition prevents a reliable total, stop and ask me.

FAQ

Claude knows how to write your weekly report but cannot read the sales system. Do you need another skill?

First check access. A skill supplies the procedure; a connector supplies tools for reaching the sales system. An exported sample file may be enough for the first run.

A subagent returns only a short summary. Does that mean its research used no tokens?

No. Its separate context keeps the research out of the main conversation, but the subagent makes its own model requests and consumes usage.

You want a report every Monday while your laptop is off. Is a local /goal enough?

No. A goal keeps one session working toward a finish condition; it does not schedule next Monday or move the session to the cloud. Use a cloud scheduled task and verify its access to the inputs.

Sources
  1. Nate Herk · “Every Claude 2.0 Concept Explained for Non-Coders”
    cited at 0:16 · 0:34 · 1:22 · 2:24 · 2:34 · 3:21 · 3:43 · 4:37 · 5:45 · 6:16 · 7:07 · 7:45 · 8:28 · 8:53 · 9:33 · 10:08 · 10:55 · 11:25 · 12:16 · 13:02 · 13:42 · 13:44 · 15:21 · 16:02 · 16:41 · 17:45 · 18:30 · 19:10 · 19:52 · 20:22 · 20:58
  2. Austin Marchese · “7 NEW Claude Features To Get You Ahead of 99% of People Using AI”
    cited at 0:00 · 0:40 · 1:43 · 2:30 · 3:00 · 3:23 · 3:46 · 6:20 · 7:09 · 8:48 · 10:37 · 12:00 · 12:50 · 13:39 · 14:07 · 14:24 · 14:35 · 14:44 · 15:24 · 15:34
  3. Anthropic · “Claude now works with Google Docs, Sheets, and Slides”
  4. Anthropic · “Use Claude in Google Docs, Sheets, and Slides”
  5. Anthropic · “Claude Haiku 5.5”
  6. Anthropic · “Share artifacts”
  7. Anthropic · “Continue local sessions from any device with Remote Control”
  8. Anthropic · “Change the model, effort, and thinking settings”
  9. Anthropic · “Choosing the right effort level in Claude Code”
  10. Anthropic · “Escalate hard decisions with the advisor tool”
  11. Anthropic · “How do usage and length limits work?”
  12. Anthropic · “Manage usage credits for paid Claude plans”
  13. Anthropic · “Claude Cowork and chat are now one Claude”
  14. Anthropic · “Desktop application”
  15. Anthropic · “Get started with Claude Duet”
  16. Anthropic · “Build live dashboards and animate explainers with Claude”
  17. Anthropic · “Move from standalone Claude Design to Claude”
  18. Anthropic · “How Claude remembers your project”
  19. Anthropic · “Extend Claude with skills”
  20. Anthropic · “Extend Claude Code”
  21. Anthropic · “Mods overview”
  22. Anthropic · “Configure permissions”
  23. Anthropic · “Create custom subagents”
  24. Anthropic · “Let Claude coordinate ongoing work with Projects”
  25. Anthropic · “Keep Claude working toward a goal”
  26. Anthropic · “Schedule recurring tasks in Claude Code Desktop”
  27. Anthropic · “Automate work with scheduled tasks”