Test AI before you trust the workflow
Build a small evaluation that reveals errors as well as speed. Compare the whole workflow and write a decision that respects what ten examples can tell you.
Try the next course →Please wait while this page is prepared.
Applied AI / Free mini-course
Turn a vague request into a task another person can check. Practise defining the input, expected output, evidence and human decision before choosing an AI tool.
Free · ₹0 · about 20 minutes · self-paced reading + practice
By Dr. Swapnil Sahoo · for adult learners · no account required
01 / Read and try
A useful brief starts with a person and a decision. Specify the work the assistant may prepare and what remains outside its authority. ‘Help with customers’ leaves both unclear. ‘Draft a room-booking reply for a receptionist to check’ defines a smaller task. Then identify the only permitted inputs. Start this exercise with the invented information below; an AI account is optional. You can test the brief by swapping it with a classmate and asking what they would produce.
02 / Read and try
An instruction such as ‘be accurate’ gives the reviewer little to inspect. Specify an output structure and a rule for missing information. Require a short draft, a list of facts used and a list of unresolved questions. Ask the assistant to distinguish the supplied policy from its own suggestion. If an essential fact is absent, the draft should say what is missing rather than fill the gap. A tidy format helps review; it does not prove that the content is correct.
03 / Read and try
Name who checks the draft and what they check before it is sent. Include policy consistency, unsupported facts, unnecessary personal information, missing questions and tone. Choose at least one difficult example, such as a request that extends beyond closing time. The first trial should reveal whether the brief works, not merely whether a draft can be produced. Record what you changed after review. This is a practical exercise in the context, evaluation and responsibility emphasised by NIST’s voluntary risk guidance.
04 / Make a decision
Put the idea to work · guided practice
A public demonstration using original hypothetical material. Explore choices and compare your reasoning. This activity does not submit work, count towards assessed progress or issue a certificate.
Original hypothetical exercise: Sahaj Desk has an eight-person meeting room that closes at 6 pm. A customer asks for a six-person booking on Friday from 5:30–7 pm. You have the room policy but no dated availability or price sheet. An assistant writes: ‘Confirmed for Friday, 5:30–7 pm, at ₹800.’ The business, message and amount are invented learning inputs.
Rewrite the task brief and decide how the receptionist should handle the draft. Try a different choice to see how the reasoning changes. Feedback is written instructional guidance, not AI-generated advice.
Your notes stay on this page unless you choose to save them in this browser or download them. They are not sent to the Lab. Avoid personal, employer, customer or confidential information. Browser-saved notes can be read by someone using this browser profile.
This is one defensible response. Your recommendation may differ if you explain the assumptions and evidence.
Keep the momentum
Build a small evaluation that reveals errors as well as speed. Compare the whole workflow and write a decision that respects what ten examples can tell you.
Try the next course →Explore the proposed full programme, its capstone and assessment rubric. Dates and enrolment details are separate from this free course.
Explore the programme →This course provides self-practice and written guidance. It does not submit work, certify completion or promise a professional outcome.