Module 3 · Files, tools and your own data Lesson 10 of 15
Where this fits next to a chat window and your first script
Autonomous agents are offered as products rather than raw endpoints, and the same planning loop can be built on any provider's API with tool calling. You do not need this to finish the course, and you do not need it for a fresher job either — but an afternoon here is what turns "I have used Manus" into "I have built with it", which is a different sentence in an interview.
The concept
Autonomous agents are offered as products rather than raw endpoints, and the same planning loop can be built on any provider's API with tool calling. The idea is simple: the same model you have been chatting with also answers a web request, so you can put it inside a script, a spreadsheet or a page. A key identifies you; a request sends the text; a response comes back as data.
The reason to try it once, even if you never build anything: it makes the chat version less mysterious. You see that the whole conversation is text in and text out, that your instructions are literally lines of a request, and that "the model" is one parameter among several.
A first call looks like this:
# The smallest version of the same loop, so you understand what you are buying:
#
# 1. plan ask the model for the steps, as a list.
# 2. act run one step with a tool (search, fetch, compute).
# 3. record append the result, with the source, to a file.
# 4. repeat until the plan is finished or a step fails twice.
# 5. deliver write the artefact, and list what could not be found.
#
# Step 3 is the difference between this and a chat: every result is written
# down with its source as it happens, so the output can be audited
# afterwards. A loop without step 3 cannot be checked, and therefore
# cannot be trusted with anything that matters.Common mistakes
The mistake is giving an agent credentials, a live account or the ability to send things. Read-only access and a sandbox is the only sensible starting point.
Worked example
A script that searches, summarises and writes a CSV is the smallest version of what the product does — building it once is the best way to understand when the product is worth its credits.
Your practice task
Get a key, run one request that works, and change one word in it to see the answer change. That is the whole of the first afternoon.
Do this before moving on. Reading a solution teaches the shape of it; typing it teaches you.
Key takeaway
Autonomous agents are offered as products rather than raw endpoints, and the same planning loop can be built on any provider's API with tool calling.
Keep your place in this course
A free account saves which lessons you have finished and unlocks the certificate. The lesson itself stays free to read.
Create free account or sign inCourse complete
You finished every lesson.
Your certificate is ready, and the projects you built are the proof to attach to an application.
Almost there
15 lessons left of 15
Finish every lesson to unlock the certificate. Each one ends in a practice task — do them and the final project brief writes itself.