Consilix
AI Toolkit v2
HomeWorkflow recipes
Tools
Claude (Anthropic)
  • Claude.ai (Pro and Max)
  • Claude Code
  • Claude Cowork
  • Claude API (developer platform)
  • Claude Mobile and Desktop apps
ChatGPT (OpenAI)
Microsoft 365 Copilot
Perplexity
Grok (xAI)
Gemini (Google)
Libraries
PromptsSkills
Reference
About this toolkit
v2 · June 2026
  1. Home›
  2. Tools›
  3. Claude (Anthropic)
Tool overview · last verified Verified against the May 2026 product surface: Opus 4.8 launched 28 May 2026 with dynamic workflows and Ultra Code mode; Sonnet 4.6 current since February 2026; Haiku 4.5 since October 2025. Live Artifacts shipped April 2026. Cowork enterprise expansion February 2026, Computer Use GA on claude.ai March 2026. Re-research when Opus 4.9 or a new Sonnet drops, or when Anthropic ships native image generation (still not present at May 2026).

Claude (Anthropic)

The thinking tool. If the work needs care, hand it to Claude.

Overall 10/10draftingresearchcodingdocument_reviewstructured_outputsagent_workflowsdeep_researchsales_proposals
Consilix take

For UK operators who actually read what the model produces, Claude is the default. The writing has a steadier register than ChatGPT, Projects plus Artifacts turn it into a proper desk for proposal work, and Claude Code has quietly become the centre of gravity for anyone building internal tools. The price of admission, if you go beyond the free tier, is that you need to learn Projects, Skills, and at least one MCP connector; without those it is just a smarter chatbot.

Reach for it when

Reach for Claude when the work is reading-and-writing heavy and quality matters: contracts, proposals, board papers, code reviews, long-form research that the recipient will actually read. Reach for it as the default model whenever Projects and Artifacts let you load the full context once and iterate against it. For any UK SME that drafts client-facing documents weekly, Claude Pro or Max plus a couple of good MCP connectors (Drive, Gmail) is the single best AI investment available.

Do not reach for it when

Do not reach for Claude when you need native image generation (use ChatGPT's DALL-E or Midjourney directly). Do not reach for it for full voice conversations on a phone (ChatGPT or Gemini are ahead). Do not reach for it when the job is genuinely real-time web research with cited sources at the URL level (Perplexity is sharper, ChatGPT search is fine). Do not pay for Max if you only use the chat for a few prompts a day; Pro is enough.

Core strength

Long-form reasoning, document work, and developer-grade agentic execution. Claude is the model you trust with the contract, the board pack, the codebase migration; it is not the model you reach for to generate a hero image or scrape Twitter in real time.

Within Claude (Anthropic) · choosing between sub-products

Choosing between claude.ai, Claude Cowork, and Claude Code

All three are Claude. What differs is where the conversation happens, what Claude can touch, and how the output persists. Pick the one that matches the SHAPE of the work, not the difficulty of the task.

The single-rule decision

If the output needs to be…Reach for
A response you read in the chat (draft, summary, answer)claude.ai
A persistent dashboard that refreshes against live dataCowork (Live Artifacts tab)
A file (or files) on your local diskCowork (agentic tasks)
A scheduled recurring job (e.g. every Monday 07:00)Cowork (scheduled tasks)
Code in a repo, agent infrastructure, custom skills you shipClaude Code

Full comparison

claude.ai (browser + app)Claude Cowork (desktop)Claude Code (CLI)
AudienceEveryoneOperators, knowledge workersDevelopers, agent builders
Where it runsBrowser, mobile, desktopDesktop only (macOS + Windows)Local CLI on macOS / Linux / Windows
Output typeChat responses + inline ArtifactsLive Artifacts (persistent tab) + files on diskCode, agent runs, structured output
PersistenceTied to chat (saveable to Project)Live Artifacts tab is permanentFiles persist in your repo
File accessNone (only via upload to a Project)Yes — read, edit, create local filesYes — same as Cowork
Multi-step executionOne prompt at a timeAgentic plan + approval flowAgentic; usually scripted via skills
Scheduled tasksNoYes (Cowork scheduled tasks)Yes (via cron + claude -p)
MCP connectorsYes (Gmail, Drive, Calendar, etc.)Yes (same connectors)
Sub-products · 5

Sub-products

Each sub-product has its own focused page. Tap any card to open the full breakdown.

Claude.ai (Pro and Max)

10/10

Reach for this when the deliverable needs to read like a competent senior wrote it.

View details →

Claude Code

10/10

Reach for this when you would otherwise hire a junior developer for two weeks of glue work.

View details →

Claude Cowork

8/10

Reach for this when the work lives across local files, email, and Drive and you do not want to script it yourself.

View details →

Claude API (developer platform)

9/10

Reach for this when you are wiring Claude into your own product or back-office and want production-grade behaviour.

View details →

Claude Mobile and Desktop apps

7/10

Reach for this when you are on site or in a car and need the same Claude you use at your desk.

View details →
MCPs and connectors · 8

MCPs and connectors worth knowing

Useful connectors worth knowing for this tool. Ranked by everyday usefulness.

Filesystem MCP

Gives Claude direct read and write access to nominated local folders. The non-negotiable MCP for anyone using Claude as a desk agent over real client files.

9/10
GitHub MCP

Read repos, open issues, comment on PRs, and run Claude reviews on diffs without leaving the chat. Essential for any team using Claude Code alongside GitHub.

9/10
Google Drive and Gmail connectors (official)

OAuth connectors in Settings that let Claude read attachments and threads. The right way to give Claude inbox context without exporting to a Project.

9/10
Slack MCP

Reads channel history, summarises threads, and posts messages. Pairs neatly with Cowork scheduled tasks for a weekly digest.

8/10
Context7 (Upstash)

Injects version-correct library documentation into Claude Code sessions. Stops the model hallucinating against a 2024 version of your framework.

9/10
Computer Use (built-in)

Drives the desktop and browser directly. Useful for legacy web apps with no API; treat as a junior assistant, not a fire-and-forget agent.

7/10
Claude Skills marketplace (claudemarketplaces.com, KissMySkills)

Pre-built skill packs for vendor contract review, marketing outreach, financial modelling. The fastest way for a non-developer to get value from Claude beyond chat.

8/10
Web fetch MCP / Firecrawl

Gives Claude a proper page-fetcher and crawler. Closes the gap with ChatGPT and Perplexity on web research inside a Project.

8/10

Last verified: Verified against the May 2026 product surface: Opus 4.8 launched 28 May 2026 with dynamic workflows and Ultra Code mode; Sonnet 4.6 current since February 2026; Haiku 4.5 since October 2025. Live Artifacts shipped April 2026. Cowork enterprise expansion February 2026, Computer Use GA on claude.ai March 2026. Re-research when Opus 4.9 or a new Sonnet drops, or when Anthropic ships native image generation (still not present at May 2026).

Yes (same connectors)
Best learning surface for first-timersYesOnce chat is comfortableLast; assumes CLI fluency

When this matters in practice

A non-technical operator does 90% of their AI work in claude.ai. The browser is the iteration loop. Projects hold context that travels across conversations. Custom Instructions hold voice rules so output is consistent. Artifacts emerge inline when you ask for "an interactive…" or "an editable…".

A senior operator moves to Cowork when the work is recurring or file-shaped. A weekly digest that refreshes from Gmail goes here. A folder of contractor RAMS that needs scanning goes here. A dashboard you reopen every Monday morning goes here.

An engineer reaches for Claude Code when the work is code, skills, or agent infrastructure. Skills written here ship via .claude/skills/ and become callable from anywhere. Agent runs orchestrate multiple tools and produce structured output for downstream pipelines.

Most teams use all three. The skill is knowing which to start in for a given task. The wrong starting point is reversible but costs minutes.

Inside claude.ai: Projects, Skills, Artifacts, Custom Instructions

These four often confuse people. Here is how they relate.

  • Custom Instructions live at the account level (Settings → "What preferences should Claude consider"). They apply to every chat in every Project, everywhere. Use for: voice rules, what to never produce, how to format. Set once.
  • Projects are persistent workspaces. Each has its own uploaded files (Project knowledge), its own system instructions (Project-level rules that layer on top of account-level Custom Instructions), and its own conversation history. Use for: a topic or client where the same documents are needed repeatedly.
  • Artifacts are interactive outputs (HTML, React components, Mermaid, SVG, docx/xlsx/pptx) that render inline in the chat. Ephemeral by default; saveable to a Project. Use for: when the user needs something to interact with, not just read.
  • Skills are reusable instruction modules — a prompt that lives IN Claude so calling it is one click instead of pasting. Installable in a Project's Custom Instructions or globally in Claude Code. Use for: any task you run more than 3 times a month.

The decision rule: a skill is a graduated prompt. A Project is a graduated chat. Artifacts are what the model produces when you ask for interactivity. Custom Instructions are how you bake your voice into every output.

Inside Cowork: Live Artifacts, agentic tasks, scheduled tasks

Cowork has three modes of work:

  • Live Artifacts — persistent interactive dashboards in their own tab. Refresh from MCPs on reopen. Best for any tracker, calculator, or status view you reopen frequently.
  • Agentic tasks — multi-step work that touches files on your disk. "Read every contractor RAMS in this folder and produce a compliance summary spreadsheet." Best for jobs where the output is a file (or several files).
  • Scheduled tasks — recurring autonomous runs. "Every Monday 07:30, regenerate this dashboard from this week's Gmail data and save a snapshot to ~/dashboards." Best for any work that should run without you needing to remember.

You often combine them. A Live Artifact you maintain manually + a scheduled task that refreshes it every Monday morning. An agentic task that produces files + a Live Artifact that lets you browse those files interactively.

Last verified

May 2026. Anthropic ships new features fast; if a date below disagrees with the current product, the product wins.

  • Claude Cowork: launched January 2026, GA April 2026
  • Live Artifacts in Cowork: launched 20 April 2026
  • Scheduled tasks in Cowork: launched alongside GA
  • Custom Instructions at the account level: long-standing
  • Projects: long-standing; Live Artifacts in April 2026 added Project-saved live state