Agentic AI for Applied Learning
A one-day course ↯Learn agent principles, scale them, and design real-world patterns
Uncheck any slide to skip it. Jump menu, counter, and next/prev follow your selection. Changes save automatically.
For every SaaS company, there will be an AI agent company.
- Harj Taggar, Partner Y Combinator
flip to reveal ↗Agents democratize economic opportunities.
Fast experimentation drives invention.
- Andrew Ng, Computer Scientist, former head of Google Brain & Chief Scientist at Baidu
flip to reveal ↗The key enabler of AI is fast development and iteration, and that allows for more experimentation.
A model that perceives inputs, reasons about what to do, takes actions - and keeps going, step by step, until the goal is met.
The LLM enables the agent's reasoning. You swap models to change its reasoning engine. The agent is not its model.
By default an agent remembers your conversation up to a limit and forgets anything mentioned earlier. You can give it more memory like documents, past conversations or research papers and it will behave like a personal librarian.
The trade-off: the more it remembers, the more it costs to run and the easier it loses focus.
Without tools the agent can only chat. Tools can let it search the web, read files, write spreadsheets. Think of tools as the agent's hands - they give it the ability to do things.
Some agents ask for permission at every step while others just run until the job is done. The right level of autonomy depends on what's at stake. You wouldn't let an agent send emails to 10,000 students without a human checking the draft first.
It doesn't just answer once and stop. It tries something, checks if it worked, and decides what to do next, looping until the goal is met. This is what separates an agent from a chatbot. A chatbot responds. An agent persists.
Task with no examples - just the instruction. You trust the model to figure out format and approach.
"Summarise this paper in three bullets."
One example first, then the task. The example shows the format, tone, or structure you want.
"Here's an example: [...]. Now do this one the same way."
i.e., could you draw the whole flowchart before writing a line of code?
emails, documents, chat transcripts, free-form text, images.
a self-review loop - draft, check, revise - before returning an answer.
Predictable steps on structured data. You don't need an LLM - a script or if/then rules will be faster, cheaper, and more reliable.
You know the steps, but one of them needs to make sense of messy human content. Add one AI call into your pipeline - you don't need a full agent.
The path is open-ended - the system has to figure out each step as it goes, take actions, and decide what to do with the results.
Open-ended path and a second pass makes the output better. The agent drafts, checks its own work, then revises before handing back the answer.
Before you build, fill in the text for this design canvas to form a complete brief for your agent. Flip each card to see how the six elements work together in this example of a billing support assistant that reads customer emails and decides what to do next.
passes / total × 100%
e.g. support agent resolves a refund request end-to-end
sensible paths / total × 100%
e.g. research agent actually reads the papers, not just titles
correct tool calls / total × 100%
e.g. sales agent queries the right CRM field with the right filters
avg. $ & seconds per run
e.g. coding assistant holds $0.12 / 8s avg, not drifting to $0.40 / 30s
rescued runs / total × 100%
e.g. how often a human rep has to take over a support conversation
| Tool | What it is | Pick it for… | No-code | Lift |
|---|---|---|---|---|
| Claude / Cowork↗General | Strong reasoning assistant plus an agentic desktop that works across your files and apps. | Knowledge workers who need deeper reasoning, polished writing, or a desktop agent across files and apps. | Yes | Low–Med |
| Gemini + Workspace↗General | AI built into Gmail, Docs, Meet, plus Gemini app and NotebookLM through Workspace plans. | Orgs already in Google - meeting notes, docs, slides, and classroom prep in one plan. | Yes | Low |
| Perplexity Computer↗General | Cloud-hosted agentic task runner that coordinates 19 AI models to browse the web, control apps, fill forms, and complete multi-step workflows from natural language. | Business users who want to delegate browser-based research and multi-step workflows in plain English - no setup, runs entirely in the cloud. | Yes | Low |
| NotebookLM↗General | Source-grounded research and learning tool that works on your uploaded materials. | Grounded learning and teaching prep - synthesise, query, and audio-overview your own sources. | Yes | Low |
| Zapier Agents↗No-code | No-code agents connected to thousands of apps, designed to act on business data and triggers. | Quick no-code automations connecting business apps - the fastest path from idea to running agent. | Yes | Low |
| Gumloop↗No-code | Visual, AI-native agent builder where you drag-and-drop nodes (130+ integrations, MCP support) to create reasoning agents and multi-step automations, with a meta-agent that scaffolds flows from plain-language prompts. | Teams wanting AI-native automation over simple triggers - agents that reason mid-flow, not just chain apps; step up from Zapier when logic and branching matter. | Yes | Low–Med |
| n8n↗No-code | Workflow automation for technical teams with AI agents, traceable reasoning, visual builder, and self-hosting. | Technical teams bridging workflow automation and real agent systems, with self-hosting options. | Yes +code | Medium |
| Relevance AI↗No-code | Low/no-code platform for building AI agents and multi-agent teams, especially around GTM and operations. | Sales, onboarding, and GTM teams building AI agent workflows without writing code. | Yes | Medium |
| MindStudio↗No-code | No-code visual builder for designing, deploying, and managing AI agents and apps across 200+ models and 1,000+ integrations - publishable as web apps, APIs, browser extensions, or scheduled automations. | Teams and agencies building user-facing AI products without engineers - step above prompt wrappers, with 150K+ deployed agents and an approachable visual interface. | Yes | Low |
| OpenAI Codex↗Developer | Autonomous coding agent - available as web UI, desktop app, open-source CLI, and IDE extensions - that writes features, fixes bugs, runs tests, and orchestrates parallel sub-agents in sandboxed cloud environments. | Engineering teams wanting an agent that writes, tests, and ships code autonomously - hands-off software engineer, accessible via CLI, API, or ChatGPT web UI. | Partial | Medium |
| LangChain↗Developer | Developer framework and platform (LangGraph + LangSmith) for building, testing, observing, and deploying custom agents. | Developers building bespoke agent systems with full control over evals, memory, and observability. | No | High |
| Sierra↗Enterprise | Enterprise customer-experience AI platform with agent studio, SDK, live assist, voice, and trust tooling. | Enterprise CX teams deploying branded, voice-ready customer agents at scale. | Platform-led | Med–High |
| OpenHands↗Open-source | Open platform for cloud coding agents. Formerly OpenDevin; now stewarded by All Hands AI. | Software engineering agents and sandboxed dev workflows - the leading open-source coding agent. | No | High |
| OpenClaw↗Open-source | Open-source self-hosted personal AI assistant with tool use, plugins, browser/canvas/actions, and companion apps. | Power users building a personal agent layer with plugins, browser actions, and self-hosting. | Partial | Med–High |
| Hermes Agent↗Open-source | Self-improving open-source agent by Nous Research with persistent memory, reusable skills, and a learning loop. | Long-running autonomous agents that need cross-session memory and self-improving skills. | Partial | Med–High |
How quickly you can go from signing up to a working agent.
AskCould someone without a coding background build their first agent in an afternoon?
Red flagThe "getting started" guide asks you to install software on your computer before you can try anything.
Swap the AI brain without rebuilding the agent.
AskCan I switch from Claude to GPT to a cheaper model with a single setting?
Red flagYou're locked to one AI company — switching means starting over.
A big library of apps and tools it works with, and a way to add your own.
AskCan I connect the agent to something that isn't on the default list?
Red flagOnly the apps they've pre-built work. Your internal tools aren't welcome.
The ability to see exactly what the agent did, step by step.
AskWhen the agent gets something wrong, can I quickly see why?
Red flagWhen it breaks, you get an error message and no trail back to the cause.
Permissions, sensitive data handling, approvals, and a clear record.
AskCan I require a human to approve before the agent does anything risky or permanent?
Red flagAnyone logged in can do anything, and nothing is recorded.
The thing you demo is the thing you ship to real users.
AskWhen real usage picks up, can this tool help me scale — or do I rebuild somewhere else?
Red flagGoing live means rebuilding the whole agent in a different system.
Subject: research: transformer architecture
Searches the web via Tavily, pulls the top 5 sources, synthesises them into a tight 200-word brief with 3 key takeaways. Emails it back to you.
Subject: teach me: vector databases
Returns a structured 5-minute lesson - concept explained in plain English, one worked example, and a single practice exercise. Emails it back.
One workflow. Two modes. Routing is just a subject-line check.
Node: Email Trigger (IMAP)
| Host | imap.gmail.com |
| Port | 993 |
| User | your@gmail.com |
| Password | app password ← not your login password |
| Mailbox | INBOX |
| Action | Mark as read |
| Poll every | 1 minute |
Getting a Gmail app password
myaccount.google.comn8n - copy the 16-char codeIF condition: {{ $json.subject.toLowerCase().startsWith('research') }} → True branch runs web search; False runs lesson generator
Add node → connect Gmail credentials (app password). Set poll: every 1 minute. This is your workflow entry point.
Value 1: {{ $json.subject.toLowerCase() }}
Operation: Contains · Value 2: research
URL: https://api.tavily.com/search · POST
Body: {"query":"{{ $json.subject.replace('research:','').trim() }}","max_results":5}
System prompt: "Synthesise these search results into a 200-word brief with 3 key takeaways. Be concise."
System prompt: "Create a 5-minute lesson on {{ topic }}: plain-English concept, one worked example, one practice exercise."
To: {{ $json.from.emailAddress.address }}
Subject: Re: {{ $json.subject }}
Body: {{ $('AI Agent').item.json.text }}
In n8n - step by step
Test emails to send
research: transformer architectureteach me: vector databaseshello thereSwap Send Email for a Slack node. Post the AI response to a channel. Entire team sees it.
After Send Email, add a Notion node. Create a database row: topic, summary, timestamp.
Swap email trigger for Schedule node. Run every morning at 7am with a hardcoded topic.
Connect a Simple Memory node to the AI Agent. It now remembers your previous queries.
Every extension is one more node. That's the point.
At the end each team shares: problem, design, one surprise.
Fill in each card to form the brief for the agent you want to build.
The meta-skill is learning to evaluate, switch, and compose tools - not mastering any one. What you built today is the muscle for everything that comes next.