AI Education for operators who ship
Original Brainyx AI operator tracks plus curated Anthropic Academy catalog links. Full lesson pages render in the app; this snapshot lists the catalog for crawlers and answer engines.
Start with Claude for knowledge-work fluency, or Hermes for agentic CLI, messaging gateways, and tool use. Each lesson includes objectives you can apply the same week.
Claude Operator Track
From first chat to agents, Claude Code, APIs, and MCP — taught for people who ship systems.
- Meet Claude — capabilities, limits, access — Treat Claude as a strong generalist teammate with no lived context until you give it some.
- Briefs, prompts, and the iteration loop — Great outputs come from clear jobs, constraints, and ruthless iteration — not magic words.
- Projects, memory, and durable context — Stop re-explaining your company every chat — put standing instructions where Claude can reuse them.
- Chat vs Cowork — when files are in the loop — Chat thinks with you; Cowork-style modes work against a folder and connectors with permissions.
- Claude Code — agentic coding without chaos — Plan, steer, verify — then let the agent loop touch the repo under your rules.
- Claude Developer Platform & your first API call — Move from ‘ask Claude’ to ‘Claude is a component in software you own’.
- Agents, tools, and MCP — An agent is a loop with tools — MCP is how you plug in external capabilities cleanly.
- Large knowledge — RAG vs stuffing the prompt — When docs don’t fit, retrieve the right chunks — don’t drown the model in PDFs.
- AI fluency, values, and what you own — Close the loop: intentions, principles, boundaries — then decide what to productize.
Hermes Agent Operator Track
From install to always-on messaging agents — taught for builders who ship.
- What Hermes Agent actually is — An autonomous, self-improving agent — not an IDE plugin wrapped around one API.
- Install, setup, and verify a chat — Desktop installer or one-liner CLI — then hermes setup --portal and a real response.
- Your ~/.hermes home and config.yaml — All settings live under ~/.hermes/ — learn the map before you edit YAML by hand.
- CLI, TUI, and daily operating rhythm — Master the terminal interface you’ll use every day before you expose a public bot.
- Tools, toolsets, and terminal backends — Tools are functions the agent can call — toolsets and backends decide how powerful (and risky) that is.
- Skills system and persistent memory — Procedural skills + durable memory are Hermes’ closed learning loop — learn to steer them.
- Messaging gateway — put Hermes where you live — One gateway process: Telegram, Discord, Slack, WhatsApp, Feishu, Teams, and more.
- MCP integrations — borrow tools you already have — Connect stdio or HTTP MCP servers so Hermes can use GitHub, filesystems, DBs, and internal APIs.
- Security layers and architecture map — Defense-in-depth before public bots — then a mental map of entry points and subsystems.
AI Education — Brainyx AI
Canonical: https://www.brainyxai.co.za/education
Markdown: https://www.brainyxai.co.za/md/education.md
Author: Brainyx AI
Original operator tracks on-site. Anthropic Academy courses stay on anthropic.skilljar.com (catalog links only).
Who these tracks are for
Brainyx AI Education is written for operators — people who have to make AI produce a business result, not people studying it academically. That includes founders deciding what to build, operations leads who own a workflow, and engineers who need production judgment rather than another API tutorial.
The tracks assume no prior AI experience but do assume you have real work to apply it to. Every lesson has a lab that only makes sense if you bring an actual task, and the labs are where the learning happens. Reading the tracks without running them produces familiarity, not capability.
What makes this different from vendor courses
Vendor documentation is authoritative about what a product does. It is not written to tell you when the product is the wrong choice, what it costs to run at your volume, or how it fails in front of a customer. Those are the questions operators actually face.
These tracks cover product mechanics only as far as needed, then spend their length on judgment: which pattern fits which problem, what to verify before trusting output, where the human gate belongs, and when personal fluency stops being enough and you need a system somebody owns.
Content is original Brainyx AI instructional writing. We link to official documentation as the source of product truth and do not republish vendor lesson bodies.
How to work through a track
Take one lesson per working session rather than binge-reading. Run the lab on real work before moving on — sanitise any personal information first. Keep a running note of failure modes you hit and the fix you found, because that note becomes more valuable than the lessons themselves.
Both tracks end at the same place: the point where the constraint is no longer your skill but the absence of a reliable system. That is the handoff to [AI implementation](https://www.brainyxai.co.za/services/ai-implementation) or [AI training](https://www.brainyxai.co.za/services/ai-training) for your team.
Every lesson has a Markdown mirror under `/md/education/{track}/{slug}.md` so AI assistants and crawlers can read the full text without executing JavaScript.
Claude Operator Track
From first chat to agents, Claude Code, APIs, and MCP — taught for people who ship systems.
Path: https://www.brainyxai.co.za/education/claude
Outcomes:
- Run high-signal Claude chats with briefs, constraints, and iteration loops
- Choose Chat vs Projects vs Cowork vs Claude Code for the job
- Use CLAUDE.md / project context and verification habits that stick
- Orient to the Messages API, model tiers, and tool-using agents
- Connect MCP safely and know when RAG beats stuffing the prompt
Lessons (titles + teasers; full bodies on-site):
1. [Meet Claude — capabilities, limits, access](https://www.brainyxai.co.za/education/claude/meet-claude) — Treat Claude as a strong generalist teammate with no lived context until you give it some. · Markdown: https://www.brainyxai.co.za/md/education/claude/meet-claude.md
2. [Briefs, prompts, and the iteration loop](https://www.brainyxai.co.za/education/claude/briefs-and-prompts) — Great outputs come from clear jobs, constraints, and ruthless iteration — not magic words. · Markdown: https://www.brainyxai.co.za/md/education/claude/briefs-and-prompts.md
3. [Projects, memory, and durable context](https://www.brainyxai.co.za/education/claude/projects-and-context) — Stop re-explaining your company every chat — put standing instructions where Claude can reuse them. · Markdown: https://www.brainyxai.co.za/md/education/claude/projects-and-context.md
4. [Chat vs Cowork — when files are in the loop](https://www.brainyxai.co.za/education/claude/chat-vs-cowork) — Chat thinks with you; Cowork-style modes work against a folder and connectors with permissions. · Markdown: https://www.brainyxai.co.za/md/education/claude/chat-vs-cowork.md
5. [Claude Code — agentic coding without chaos](https://www.brainyxai.co.za/education/claude/claude-code-basics) — Plan, steer, verify — then let the agent loop touch the repo under your rules. · Markdown: https://www.brainyxai.co.za/md/education/claude/claude-code-basics.md
6. [Claude Developer Platform & your first API call](https://www.brainyxai.co.za/education/claude/api-and-platform) — Move from ‘ask Claude’ to ‘Claude is a component in software you own’. · Markdown: https://www.brainyxai.co.za/md/education/claude/api-and-platform.md
7. [Agents, tools, and MCP](https://www.brainyxai.co.za/education/claude/agents-tools-mcp) — An agent is a loop with tools — MCP is how you plug in external capabilities cleanly. · Markdown: https://www.brainyxai.co.za/md/education/claude/agents-tools-mcp.md
8. [Large knowledge — RAG vs stuffing the prompt](https://www.brainyxai.co.za/education/claude/rag-vs-context) — When docs don’t fit, retrieve the right chunks — don’t drown the model in PDFs. · Markdown: https://www.brainyxai.co.za/md/education/claude/rag-vs-context.md
9. [AI fluency, values, and what you own](https://www.brainyxai.co.za/education/claude/fluency-and-ownership) — Close the loop: intentions, principles, boundaries — then decide what to productize. · Markdown: https://www.brainyxai.co.za/md/education/claude/fluency-and-ownership.md
Hermes Agent Operator Track
From install to always-on messaging agents — taught for builders who ship.
Path: https://www.brainyxai.co.za/education/hermes
Outcomes:
- Install Hermes and complete a verified first chat
- Configure providers, models, and ~/.hermes/config.yaml with confidence
- Use tools, skills, and persistent memory as a closed learning loop
- Connect messaging platforms and MCP servers safely
- Apply defense-in-depth security before exposing a bot publicly
Lessons (titles + teasers; full bodies on-site):
1. [What Hermes Agent actually is](https://www.brainyxai.co.za/education/hermes/what-is-hermes) — An autonomous, self-improving agent — not an IDE plugin wrapped around one API. · Markdown: https://www.brainyxai.co.za/md/education/hermes/what-is-hermes.md
2. [Install, setup, and verify a chat](https://www.brainyxai.co.za/education/hermes/install-and-setup) — Desktop installer or one-liner CLI — then hermes setup --portal and a real response. · Markdown: https://www.brainyxai.co.za/md/education/hermes/install-and-setup.md
3. [Your ~/.hermes home and config.yaml](https://www.brainyxai.co.za/education/hermes/configuration-home) — All settings live under ~/.hermes/ — learn the map before you edit YAML by hand. · Markdown: https://www.brainyxai.co.za/md/education/hermes/configuration-home.md
4. [CLI, TUI, and daily operating rhythm](https://www.brainyxai.co.za/education/hermes/cli-and-daily-use) — Master the terminal interface you’ll use every day before you expose a public bot. · Markdown: https://www.brainyxai.co.za/md/education/hermes/cli-and-daily-use.md
5. [Tools, toolsets, and terminal backends](https://www.brainyxai.co.za/education/hermes/tools-and-backends) — Tools are functions the agent can call — toolsets and backends decide how powerful (and risky) that is. · Markdown: https://www.brainyxai.co.za/md/education/hermes/tools-and-backends.md
6. [Skills system and persistent memory](https://www.brainyxai.co.za/education/hermes/skills-and-memory) — Procedural skills + durable memory are Hermes’ closed learning loop — learn to steer them. · Markdown: https://www.brainyxai.co.za/md/education/hermes/skills-and-memory.md
7. [Messaging gateway — put Hermes where you live](https://www.brainyxai.co.za/education/hermes/messaging-gateway) — One gateway process: Telegram, Discord, Slack, WhatsApp, Feishu, Teams, and more. · Markdown: https://www.brainyxai.co.za/md/education/hermes/messaging-gateway.md
8. [MCP integrations — borrow tools you already have](https://www.brainyxai.co.za/education/hermes/mcp-integrations) — Connect stdio or HTTP MCP servers so Hermes can use GitHub, filesystems, DBs, and internal APIs. · Markdown: https://www.brainyxai.co.za/md/education/hermes/mcp-integrations.md
9. [Security layers and architecture map](https://www.brainyxai.co.za/education/hermes/security-and-architecture) — Defense-in-depth before public bots — then a mental map of entry points and subsystems. · Markdown: https://www.brainyxai.co.za/md/education/hermes/security-and-architecture.md
FAQ
Are the tracks free?
Yes. Both operator tracks are free to read and work through, with no signup required.
Do I need a paid Claude or Hermes subscription?
No. Every concept can be practised on free tiers or a local install. Paid tiers matter when you hit usage limits or need higher-capability models.
Which track should I start with?
Start with the Claude Operator Track if your work is mostly documents, decisions, and drafting. Start with Hermes if you are comfortable in a terminal and want an always-on agent you run and configure yourself.
Is this a certification?
No. There is no certificate, because a certificate would prove you read the pages rather than that you changed a workflow. The evidence that the track worked is a measurable improvement in real work.
Can you run these as training for our team?
Yes, as a tailored engagement built around your systems, documents, and risk rules rather than generic material. See https://www.brainyxai.co.za/services/ai-training
Related: AI services · Operations diagnostic · Markdown catalog
Book a consultation · joshua@brainyxai.co.za · Markdown mirrors