Autonomous Agents · Agentic AI for working professionals
Give AI a goal.
Build the Agent that follows through.
Before week 1 — what you need
- R1Basic programming
- R2Bring a laptop
- R3Active ChatGPT Plus subscription + working Codex access
Build an Agent that uses tools, checks results, and knows when to stop. Turn your work experience into the judgment that guides its next move.
Fig. 01 · The Agent loop — step-through walkthrough
Idle — press the button to step through three full cycles.
Your expertise.
An Agent that acts on it.
Businesses are building AI tools around their own processes. You know where work stalls, which exceptions matter, and what a useful result looks like. Learn to turn that experience into an Agent that can act on it.
Find the decision that went wrong, improve it, and show that the fix works.
Four phases, sixteen weeks, one Agent you built yourself.
Phase 01 · Weeks 01–04
Build an Agent that acts — and stops.
From LLM APIs and tool calls to a hand-written Agent loop.
W01 From a request to a working program
Use Codex as a coding partner. Call an LLM API, inspect its response, and keep credentials outside source code.
DELIVERABLEA small program that calls a language model and records its output.
W02 Give the model tools
Define tools with clear inputs and outputs. Validate requests and return useful errors when a tool fails.
DELIVERABLEAn assistant that can choose and call two safe tools.
W03 Build the Agent loop
Write the decide–act–observe loop yourself. Add a step limit, a stopping rule, and a readable action log.
DELIVERABLEAn Agent that completes a bounded task and explains why it stopped.
W04 Know when to ask a person
Handle missing information, retries, and tasks beyond the Agent's permissions. Add approval before consequential actions.
DELIVERABLEAn Agent that pauses for help instead of guessing or looping forever.
Phase 02 · Weeks 05–08
Give it a real piece of work.
Choose document research or data analysis. Make every result inspectable.
W05 Research across documents
Search a supplied document set, compare claims, and attach sources to the findings.
DELIVERABLEA research Agent with traceable citations.
W06 Analyze data with code
Let the Agent inspect a table, run analysis, read errors, and revise its code. Verify the result with simple checks.
DELIVERABLEA data-analysis Agent with code and execution records.
W07 Make the work inspectable
Choose document research or data analysis. Define success, retain tool records, and specify when a person must take over.
DELIVERABLEA complete, inspectable first application.
W08 Application demonstration PROGRESS CHECK
Demonstrate the application on new instructor-provided cases. Submit sources or data provenance, execution logs, and human handoff conditions.
DELIVERABLEProgress check: a working research or analysis Agent.
Phase 03 · Weeks 09–12
Make its decisions worth trusting.
Evaluate failures, control budgets, and build an Autoresearch prototype.
W09 Evaluate decisions, not fluent answers
Build a small test set. Score task completion, tool choices, evidence quality, and stopping behavior.
DELIVERABLEAn evaluation harness and a clear success rubric.
W10 Diagnose and repair failures
Read a failed run, locate the decision that went wrong, make a targeted change, and rerun the case.
DELIVERABLEA before-and-after failure analysis backed by logs.
W11 Control the experiment budget
Set limits on tool calls, runtime, retries, and GPU use. Use the supplied YOLO training and evaluation tools without studying their architecture.
DELIVERABLEA bounded experiment runner with comparable measurements.
W12 Autoresearch prototype PROGRESS CHECK
Connect the Agent to the experiment tools. Let it propose a permitted setting, run an experiment, read validation results, and choose its next step.
DELIVERABLEProgress check: an Autoresearch Agent with a visible decision trail.
Phase 04 · Weeks 13–16
Prove what it can do.
Compare fairly, reproduce a peer's work, and verify the final system.
W13 Compare against fixed search
Run the Agent and a predefined parameter search with the same data, allowed settings, and budget. Compare quality, cost, and reliability.
DELIVERABLEA fair comparison, including unsuccessful experiments.
W14 Have a peer rerun your work
Exchange projects. Reproduce a run, identify missing assumptions, repair a decision problem, and verify the fix.
DELIVERABLEA peer reproduction record and a verified revision.
W15 Prepare the final demonstration
Freeze the evaluation procedure, check records, and rehearse a live run. Explain limitations and when a person should intervene.
DELIVERABLEA reproducible submission and a concise demonstration.
W16 Final demonstration and assessment FINAL PROJECT · 50%
Demonstrate the Agent, justify its decisions, and evaluate it with the instructor-held test set. Explain one failure and the evidence for its repair.
DELIVERABLEFinal project: final system, comparison report, and verified repair.
Build an Autoresearch Agent.
Your Agent chooses settings for YOLO image-detection experiments, runs them, and uses the results to choose the next experiment. Can it use its budget more effectively than a fixed list of settings?
Provided by the instructor
- Fixed image dataset and data splits
- Working YOLO training and evaluation tools
- Allowed parameter settings and a fixed compute budget
- A fixed-search baseline for comparison
You build
- An Agent loop that selects its next experiment from evidence
- State, logs, stopping rules, and failure recovery
- Equal-budget comparison and reproducible results
The final test set stays with the instructor. A higher YOLO score is not required.
Attendance and one final project.
Throughout the semester
50%
Attendance
Attend the scheduled class sessions.
Week 16
50%
Final project
Demonstrate your Autoresearch Agent and explain its decisions.
- SUBMISSION
- Working system and execution records
- Equal-budget comparison and peer rerun
- Held-out evaluation and one verified decision repair
Weeks 8 and 12 are progress checks to help you prepare the final project.
Before we begin.
For working professionals who want to build useful AI tools around the documents, data, and processes they know.
Frequently asked
Q1 Do I need machine-learning experience?
No. The course starts at LLM API calls and tool use. The YOLO experiment tools arrive ready to run — you never train a network from scratch or study its internals.
Q2 How much time does it take each week?
One 3-hour session for 16 weeks (weekly time: to be announced), plus your own build time — most weeks you are extending your own Agent between sessions.
Q3 Can I use material from my own work?
The first application can use documents or data you are allowed to share. The final Autoresearch project uses the same instructor-provided dataset for everyone.
Questions? Just write.
Instructor: Magi Chen · chenmagi@cc.ncue.edu.tw