Gallery

Contacts

405 W. Greenlawn Ave Lansing, Michigan 48910

contact@techjacksolutions.com

+1-616-320-4064

2nd reference vertical — kit generalization
Track 03 · Applied & Agentic Novice → Intermediate ~8 min

What are AI agents?

A chatbot answers once. An agent is given a goal, tools, and memory — then runs a loop that decides its own next step. Learn the anatomy, the loop, the patterns, and how to keep autonomy safe, right here on the page.

Module progress
0%

01Chatbot → agent → agentic AI

Think of the difference between a vending machine and an assistant. A plain chatbot is the vending machine: you press a button, it hands back one answer, and it forgets you instantly. An AI agent is more like an assistant you hand a goal to — "book me a flight" — and it takes the steps to get there on its own, using software tools and remembering what it has already done. Agentic AI is the bigger paradigm — often many specialized agents coordinating on a workflow no single one could finish. Agentic AI is the bigger paradigm — often many specialized agents coordinating on a workflow no single one could finish.

ExploreClimb the autonomy ladder
Reactive
autonomy level

A chatbot waits for you. It's stateless — every answer depends entirely on the prompt you just typed.

  • The jump from chatbot to agent is autonomy — acting toward a goal without a prompt at every step.
  • The jump from agent to agentic is orchestration — multiple agents collaborating.
  • More autonomy = more usefulness and more risk. Governance scales with it (see the wizard below).

02The anatomy of an agent

An agent is an LLM plus the parts that let it act. Tap each pillar to see what it adds.

ExploreTap a pillar
AI Agent
Model / brainreasoning core
Memoryshort + long term
Toolsthe hands
Planninggoal → sub-tasks
The reasoning core

Model / brain

An LLM acts as the agent's "brain" — it processes inputs, understands context in natural language, and decides how to navigate the problem. On its own it only thinks and talks; the other three pillars are what let it act.

03The loop that makes it autonomous

Autonomy comes from a cycle: perceive → reason → act → observe, repeated. Because the agent checks the real result of each action before deciding the next one, it can course-correct without you prompting it. Step through a real task.

WalkthroughGoal: "Summarize a competitor's new pricing" — step the loop
Perceive Reason Act Observe Goal
Perceive
Read the goal & context. "Summarize Competitor X's new pricing." Available tools: web search, page reader.
Reason / Plan
Decompose the goal. Plan: search → open the pricing page → extract tiers → summarize.
Act
Use a tool. Call web_search("Competitor X pricing 2026").
Observe
Read the result & update memory. Top hit is the official pricing page — that's the one to open.
Act → Observe
Loop again. Open the page, extract the three tiers and prices. Enough to answer? Yes.
Done
Goal met. Produce the summary. No human prompt was needed between steps — that's autonomy.

04How agents are wired: design patterns

Developers shape the loop with proven orchestration patterns. The four you'll meet most:

ExploreSwitch pattern

ReAct — reason + act, interleaved

The model alternates a reasoning trace ("Thought") with an environment action ("Action"), and observes each result before its next thought. Staying grounded in real data after every step is what keeps it from hallucinating its way forward.

Thought: I need the current price.
Action: web_search(...)
Observation: $20/mo → continue.

Plan-and-Execute — full plan upfront

The agent writes a complete multi-step plan first, then executes it in order. Best for predictable, well-defined workflows. Approaches like ReWOO and Microsoft's Semantic Kernel Planner use this shape.

Plan: 1) search 2) open page 3) extract 4) summarize
Execute: run steps 1→4 in sequence

Reflection — the agent critiques itself

After acting, the agent evaluates its own output, writes a natural-language critique of what went wrong, and stores it in memory to avoid repeating the mistake. Frameworks like Reflexion formalize this.

Critique: "My summary missed the enterprise tier."
Adjust: re-read page, add the tier, retry.

Multi-agent — a team of specialists

Work is split across specialized agents. Common topologies: hierarchical / star (a supervisor delegates to workers), sequential / chain (a waterfall pipeline), and peer-to-peer / mesh (agents debate to consensus).

Supervisor: "Researcher, gather; Writer, draft; Critic, review."

05Wizard: should this task run autonomously?

The more an agent can do unattended, the bigger the blast radius if it goes wrong — "excessive agency" can mean a deleted database or an unauthorized transfer. Answer five questions about your deployment and get an instant read on whether it's safe to let it run.

WizardAnswer yes / no
Does the agent have only least-privilege permissions?Broad/unchecked access turns one bad step into a major incident.
Are its tools sandboxed & individually authorized?Attackers coerce agents into abusing legitimate tools.
Is there human approval on high-stakes actions?Full autonomy on irreversible actions = an accountability blind spot.
Are there spend/iteration limits & a kill switch?Runaway loops and cascading failures exhaust budgets fast.
Do you have observability, audit logs & memory validation?Without traces you can't see what an agent did — or roll back a poisoned memory.

06Check your understanding

TJS Quiz
window.onload=function(){window.print()}<\/scr'+'ipt>'; var w=window.open('','_blank'); if(w){ w.document.write(html); w.document.close(); } } function accentHex(){ var v=getComputedStyle(root).getPropertyValue('--tjq-accent').trim(); return v||'#2095e9'; } function dlCanvas(cv){ var a=document.createElement('a'); a.download=(D.id||'quiz')+'-result.png'; a.href=cv.toDataURL('image/png'); a.click(); } function shareCard(pct,cat){ var cv=$('#tjqCardCv'); if(!cv||!cv.getContext) return; var x=cv.getContext('2d'),W=cv.width,H=cv.height,acc=accentHex(); var g=x.createLinearGradient(0,0,W,H); g.addColorStop(0,'#0E1F40'); g.addColorStop(1,'#10294f'); x.fillStyle=g; x.fillRect(0,0,W,H); x.save(); x.globalAlpha=.16; x.fillStyle=acc; x.beginPath(); x.arc(W*.85,H*.16,160,0,7); x.fill(); x.restore(); x.fillStyle='rgba(255,255,255,.55)'; x.font='600 21px DM Sans, sans-serif'; x.fillText('TJS QUIZ · AI KNOWLEDGE HUB',58,76); x.fillStyle='#fff'; x.font='700 60px Fraunces, serif'; x.fillText(D.topic||'Quiz',56,168); x.fillStyle=acc; x.font='700 28px "Space Mono", monospace'; x.fillText(String(cat||'').toUpperCase(),58,H-150); x.fillStyle='#fff'; x.font='700 104px "Archivo Black", sans-serif'; x.fillText(pct+'%',54,H-52); x.fillStyle='rgba(255,255,255,.55)'; x.font='400 21px DM Sans, sans-serif'; x.fillText('scored on the '+(D.topic||'')+' quiz',58,H-22); x.strokeStyle=acc; x.lineWidth=8; x.strokeRect(0,0,W,H); if(cv.toBlob && navigator.canShare){ cv.toBlob(function(blob){ try{ var file=new File([blob],'quiz-result.png',{type:'image/png'}); if(navigator.canShare({files:[file]})){ navigator.share({files:[file],title:'My quiz result',text:'I scored '+pct+'% ('+cat+') on the '+(D.topic||'')+' quiz.'}).catch(function(){dlCanvas(cv);}); return; } }catch(e){} dlCanvas(cv); }); } else dlCanvas(cv); } function certPrint(pct,cat){ var raw=(($('#tjqCertName')||{}).value)||''; var name=esc(raw.trim()); var ds=new Date().toLocaleDateString(undefined,{year:'numeric',month:'long',day:'numeric'}); var id='TJQ-'+String(Math.floor(Math.random()*1e9)); var acc=accentHex(); var html='Certificate
Certificate of Completion

'+esc(D.topic||'Quiz')+'

This recognizes

'+(name||'—')+'

for completing the assessment at the '+esc(cat)+' level ('+pct+'%).

'+ds+' · TJS AI Knowledge Hub · ID '+id+'

A self-assessment summary recognizing completion of an educational module — not a professional certification.

window.onload=function(){window.print();}<\/scr'+'ipt>'; var w=window.open('','_blank'); if(w){ w.document.write(html); w.document.close(); } } renderStart(); })();

07Take it with you & go deeper

"AI agents in 5 minutes" — one-page summary
The whole module distilled to a printable cheat-sheet.
▸ Already on the site — go deeper
▸ Coming next — deeper progression (specced & grounded)
Planned

Agent memory systems

Short vs long-term memory, vector DBs, and memory poisoning.

In the pipeline
Planned

Multi-agent systems explained

Hierarchical, sequential & mesh topologies — and cascade control.

In the pipeline

Continue learning

Sources & review

Published by Tech Jacks Solutions · Reviewed June 2026. This lesson explains established concepts and is grounded in the references below; figures shown in the interactives are illustrative and labelled as such.

AI Agents — in 5 minutes

Tech Jacks Solutions · AI Knowledge Hub · educational summary

Chatbot vs agent vs agentic

Chatbot/LLM = reactive, stateless, answers one prompt. AI agent = proactive, goal-directed; uses tools + memory to run a sequence of steps autonomously. Agentic AI = the broader paradigm orchestrating many agents.

Anatomy (4 pillars)

Model/brain — reasoning core. Memory — short-term (context window) + long-term (vector DB). Tools — the hands (APIs, DB, web, code). Planning — decompose a goal into sub-tasks.

The loop

Perceive → reason/plan → act → observe, repeated. Checking each real result before the next step is what makes the agent autonomous (course-correct, retry) without per-step prompting.

Design patterns

ReAct — interleave thought + action, observe each result (reduces hallucination). Plan-and-execute — full plan upfront. Reflection — self-critique stored in memory. Multi-agent — hierarchical / sequential / mesh teams.

Top governance controls

Least privilege (RBAC/ABAC, JIT creds) vs excessive agency · sandboxed + authorized tools · human-in-the-loop on high-stakes actions · spend/iteration limits + kill switch · observability + immutable audit logs + memory validation.