Program profile · official sources
AI Agents in Practice
A practical step beyond simple chatbots for learners who already use Python and understand LLM interactions.
Commercial disclosure: Academies.ai has an affiliate agreement with 365 Data Science. If you enroll through links on this page we may earn a commission at no extra cost to you. This does not affect our assessment; rankings cannot be purchased.
Who it is for
The audience has already used LLMs and simple chatbots and wants planning, tools and multi-step agents.
Who should skip it
Delay this advanced course if functions, data structures, notebooks, prompts, tokens or message roles are new to you.
Facts checked 7 Oct 2026
- Price
- 365 Data Science Self-Study · USD 36/month for course content, billed monthly at the regular price365 Data Science Self-Study · USD 36/month for course content, billed monthly at the regular price. (seeUSD price displayed on the official English pricing page, checked 9 September 2026; regional checkout pricing and taxes are not established. ·
- Provider link
See price and enroll at 365 Data Science (official site) ↗
We may earn a commission. It does not change our facts.
- Time
- 2 hours
Listed content hours, not completion time. Official course-page advertised content duration, not total completion time; the 365 course catalog also showed 2 hours of content on 3 October 2026.
- Level
- Advanced
- Credential
- Course certificate
- Format
- Online self-paced course
- Prerequisites
- Intermediate Python skills (comfort with functions, basic data structures, and working in notebooks); Basic familiarity with large language models (e.g., using ChatGPT, prompts, tokens, system vs user messages); A general understanding of AI concepts is helpful but not required
Sources ↗
Course and activity access
Individual courses are included in Self-Study; the plan provides access to certification exams and accredited certificates. Free includes course previews.. Official source
What you actually do
You work on designing agentic systems that plan, use tools and carry out multi-step tasks. The stated audience has already worked with LLMs and simple chatbots, so the useful distinction is the move from a conversational response to a sequence of actions. The unusually long combined project-and-exam entry below needs to be read separately from the advertised instructional headline; it is not an exam-only duration.
Choose a concrete workflow you would like to understand before enrolling, such as a task where a chatbot needs more than one step to reach an answer. Use that workflow as a way to assess whether planning and tool use are the gaps you want to address. It is an evaluation exercise for choosing the course, not a promise that the provider teaches your particular use case. If your difficulty is still basic Python or interpreting LLM messages, address that preparation first rather than expecting an advanced practice course to supply it. If you already have a working chatbot, identify what you want it to do differently before choosing another course. That turns a broad interest in agents into a more specific question about planning, tool use or multi-step behaviour.
Before you start
Intermediate Python skills (comfort with functions, basic data structures, and working in notebooks); Basic familiarity with large language models (e.g., using ChatGPT, prompts, tokens, system vs user messages); A general understanding of AI concepts is helpful but not required
Curriculum
AI Agents in Practice includes a combined project-and-exam allocation, which cannot be counted wholly as assessment time. The detailed entry sum below remains distinct from the much shorter advertised instructional headline.
| Entry | Subject | Listed time | Share | Role | Observed |
|---|---|---|---|---|---|
| 1 | Introduction To The Course | 4 min | 0.2% | 2026-09-09 | |
| 2 | Rapid Foundations: Agentic Systems In Practice | 29 min | 1.8% | 2026-09-09 | |
| 3 | Project 1: Job-Helper Agent (ReAct) | 30 min | 1.8% | 2026-09-09 | |
| 4 | Project 2: ReWOO Job-Helper Agent | 22 min | 1.3% | 2026-09-09 | |
| 5 | Project 3: Business-Idea Evaluator | 21 min | 1.3% | 2026-09-09 | |
| 6 | Course Project And Exam | 1540 min | 93.6% | Provider-listed exam or combined project/exam section; duration kept separate from advertised content hours. | 2026-09-09 |
Allocation denominator: 1646.0 summed minutes; each displayed share = entry minutes / 1646.0 × 100, rounded to one decimal.
US price
| Purchase information | Recorded terms |
|---|---|
| Access and billing | As observed in the United States on 2026-09-09, USD 36 buys one month of Self-Study access at the regular monthly price. This is not a fixed cost to finish; third-party usage may cost extra. |
| Refund and retakes | Refund and retake terms are not established in these stored policy fields. |
Alternatives
The two alternatives let you narrow the decision around adaptive behaviour or data-oriented agents. Read their preparation and assessment conditions before deciding that the shared agent label means they teach the same workflow. A useful comparison is the kind of task you want to investigate and the evidence of learning you want to leave with. The time of an instructional sequence, a combined project entry and the time you personally need to practise are different measures. Choose using the recorded scope and your preparation rather than trying to rank these options by whichever displayed duration is shortest.
Building Adaptive AI Agents
| Provider and format | Level | Workload | Award | US price observation |
|---|---|---|---|---|
| DeepLearning.AI · Online self-paced learning with video lessons and listed activities | Intermediate | 1h3m listed course duration | DeepLearning.AI Accomplishment | Currency not specified 0. As shown in the United States on 15 October 2026, the provider help page states Short Courses are free; Accomplishments require a Pro subscription. This zero is scoped to free content access, not a credential-inclusive completion total. The captured membership page does not expose a numeric price in its visible text. External API, cloud, compute and tool costs are not quantified. |
| Entry and assessment questions | Recorded answer |
|---|---|
| Who is it aimed at? | AI builders who want agents to improve from their own experience. |
| What preparation is required? | Familiarity with Python is recommended for the hands-on labs. |
| How is the award earned? | A graded quiz is listed, but a passing threshold and separate final examination are not stated. |
| What remains unconfirmed? | As checked on 15 October 2026, the captured programme page does not establish academic credit, a separate final exam, expiry or renewal. |
Official source · 2026-10-15 | Official source · 2026-10-15 | Official source · 2026-10-15
Building and Evaluating Data Agents
| Provider and format | Level | Workload | Award | US price observation |
|---|---|---|---|---|
| DeepLearning.AI · Online self-paced learning with video lessons and listed activities | Intermediate | 1h59m listed course duration | DeepLearning.AI Accomplishment | Currency not specified 0. As shown in the United States on 15 October 2026, the provider support page allows free content access, excluding certificates and Accomplishments. Zero applies only to content access, not a credential-inclusive total. The course header marks its 1 graded assignment as Pro access. No complete third-party API, software or compute budget is established. The course page describes free access as limited to the platform beta; no end date is stated. No numeric Pro subscription price is established by this course page or the visible membership capture. |
| Entry and assessment questions | Recorded answer |
|---|---|
| Who is it aimed at? | AI builders extracting, analyzing and producing insights from multiple data sources. |
| What preparation is required? | Basic knowledge of Python and object-oriented programming is recommended. The course header marks its 1 graded assignment as Pro access. Free content access does not establish access to every listed assessment or project. |
| How is the award earned? | The outline lists 1 graded assignment. A separate comprehensive final examination and passing threshold are not stated. |
| What remains unconfirmed? | As checked on 15 October 2026, the captured programme page does not establish academic credit, a separate final exam, expiry or renewal. |
Official source · 2026-10-15 | Official source · 2026-10-15 | Official source · 2026-10-15
Questions before enrolling
Is finishing the agent project enough for the certificate?
The award is Course certificate, issued by 365 Data Science. Provider curriculum includes course exam; exact pass requirements not captured.
Change log
- : Registry admission from previously reviewed official evidence; individual fact dates are preserved. · Source