Home
WSQ - Harness and Loop Engineering for AI Agents

Sessions 2 days
Duration 16 hrs
Level Beginner
Assessment 2 hrs

Venue

12 Woodlands Square #07-85/86/87 Woods Square Tower 1, Singapore 737715. 5 mins walk from Woodlands (NS9) MRT station.

The venue is disabled-friendly.

TSC Title: Text Analytics and Processing
TSC Code: ICT-DIT-4029-1.1

Funding for this course is valid from 22 Dec 2021 to 21 Dec 2027. Register and complete the course within this period to qualify for funding support.

By the end of the course, learners will be able to:

LO1: Setup Deep Learning frameworks.
LO2: Understand and code Neural Network models for Regression.
LO3: Understand and code Neural Network models for Classification.
LO4: Understand and code Convolutional Neural Network models for Image Classification.
LO5: Understand and use pre-trained models for transfer learning.

Download Course Brochure

Certificate of Achievement from Tertiary Infotech Academy Pte Ltd - Upon meeting at least 75% attendance and passing the assessment(s), participants will receive a Certificate of Achievement from Tertiary Infotech Academy Pte Ltd.
OpenCerts from SkillsFuture Singapore - After passing the assessment(s) and achieving at least 75% attendance, participants will receive a OpenCert (aka Statement of Achievement) from SkillsFuture Singapore, certifying that they have achieved the Competency Standard(s) in the above Skills Framework.

WSQ - Harness and Loop Engineering for AI Agents

Course Code: TGS-2021010367

WSQ
SFC
PSEA
SFEC
Absentee Payroll
MCES

2 Review(s) | Add Your Review

This course equips participants with practical skills to design reliable harnesses and execution loops for AI agents. Learners will explore how harness engineering combines instructions, context, tools, memory, permissions, validation rules, and evaluation mechanisms to guide agent behaviour and improve the quality of task execution.

Participants will learn to develop structured agent loops that enable AI agents to observe inputs, analyse information, plan actions, use tools, evaluate results, learn from feedback, and retry when required. The course covers loop controls such as stopping conditions, error recovery, state management, human approval, output validation, and performance monitoring to prevent repetitive, unsafe, or unsuccessful agent behaviour.

A key focus is the application of text analytics and text processing within agent harnesses and loops. Learners will prepare, clean, classify, summarise, and extract information from unstructured text such as documents, customer feedback, emails, reports, and online content. They will apply techniques including tokenisation, text normalisation, sentiment analysis, entity extraction, topic identification, semantic search, and text classification to help agents interpret inputs and make informed decisions.

Through hands-on projects, participants will build AI agent workflows that process text, retrieve relevant context, perform multi-step analysis, validate generated outputs, and refine results through iterative feedback loops. Emphasis is placed on reliability, traceability, security, human oversight, and measurable evaluation.

By the end of the course, learners will be able to design and optimise harness and loop engineering solutions that enable AI agents to process text effectively, complete complex tasks consistently, and generate dependable insights for real-world business applications.

This course is part of our AI training in Singapore, where you can browse all our AI courses. See more AI agents training.

Full Fee $720.00 Before GST

GST $64.80 9% of fee

Baseline Nett $424.80 SG/PR age 21+ · 50% funded

MCES / SME Nett $280.80 SG age 40+ · 70% funded

SkillsFuture Enterprise Credit (SFEC)

Eligible companies can use their $10,000 SFEC to cover up to 90% of out-of-pocket course fees for classes ending on or before 30 Nov 2026. A redesigned SFEC starts on 1 Dec 2026.

View on SkillsFuture for Business

SkillsFuture Credit (SFC)

Eligible Singapore Citizens can use their SFC to offset course fee payable after funding but the $4,000 Additional SFC (Mid-Career Support) cannot be used.

Direct Application on SkillsFuture Portal

PSEA

Eligible Singapore Citizens can use their PSEA funds to offset course fee payable after funding.

Check PSEA Eligibility

Scroll down to “Keyword Tags” to verify for PSEA eligibility.
If there is “PSEA” under keyword tags, the course is eligible for PSEA.

Once you are eligible for PSEA, please download and fill up the PSEA Withdrawal Form, then submit the completed form to us:

PSEA Withdrawal Form Submit PSEA Form

Please bring your own laptop for hands-on training. If you don't have laptop, we can provide spare laptop for training use.

We provide free consultation related to the subject matter after the course.
Please email your queries to enquiry@tertiaryinfotech.com and we will forward your queries to the subject matter experts.

You can register your interest without upfront payment. There is no penalty for withdrawal of the course before the class commences.
We reserve the right to cancel or re-schedule the course due to unforeseen circumstances. If the course is cancelled, we will refund 100% for any paid amount.
Note the venue of the training is subject to changes due to availability of the classroom.

Course Details

Topic 1: Harness and Loop Engineering for AI Agent Text Analytics

Topic 2: Text Collection, Cleaning and Pre-processing for Agent Workflows

Topic 3: Text Analytics, Information Extraction and Feature Engineering

Topic 4: Sentiment Analysis and Iterative Agent Evaluation Loops

Topic 5: Sentiment Summarisation, Visualisation and Agent Output Optimisation

Written Exam
Practical Exam

Course Info

Minimum Entry Requirement

Knowledge and Skills

Able to operate using computer functions
Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)

Attitude

Positive Learning Attitude
Enthusiastic Learner

Experience

Minimum of 1 year of working experience.

Minimum Software/Hardware Requirement

Software:

You will need the following for this course:

Python 3 – free
Visual Studio Code – free

Hardware: Windows PC or Mac laptop

Funding Eligibility Criteria

Self-sponsored learners (individuals)

Singapore Citizens and Singapore Permanent Residents aged 21 and above.
Up to 50% course fee funding. Singapore Citizens aged 40 and above receive up to 70% under the Mid-career Enhanced Subsidy (MCES).
Singapore Citizens aged 25 and above can pay the remaining fee with SkillsFuture Credit.

Company-sponsored learners

Singapore Citizens and Singapore Permanent Residents who are direct employees of the sponsoring company.
Up to 50% course fee funding, or up to 70% for employees of SMEs (Enhanced Training Support for SMEs) and for Singapore Citizens aged 40 and above. An SME has no more than 200 employees or an annual turnover of no more than $100 million.
Employers can also claim Absentee Payroll funding for employees who attend during working hours.
Eligible companies can offset their out-of-pocket fees with SkillsFuture Enterprise Credit (SFEC).

Conditions for all funded learners

Attendance is taken digitally with Singpass for every session, including the assessment.
You must complete the course and pass all assessments (assessed as Competent).
If these conditions are not met, the funding is clawed back and the learner or employer pays the full course fee.
9% GST is charged on the full course fee before funding.
Promo and discount codes cannot be used on funded courses.
Any balance after funding can be paid in cash, with SkillsFuture Credit, with PSEA (Singapore Citizens with a PSEA).

How to Apply SkillsFuture Credit Claim for Individuals

Singapore Citizens aged 25 and above can use their SkillsFuture Credit (base tier) to pay the course fee after funding. The $4,000 mid-career top-up cannot be used for this course.

Register for this course as self-sponsored and tell us you will use SkillsFuture Credit. Do not pay the amount you plan to claim.
We email you an invoice showing the course fee after funding.
From 60 days before the course starts, and no later than the course start date, log in to MySkillsFuture with Singpass and click Claim credits.
Click Submit a Claim and search for this course by its course code, TGS-2021010367.
Select your class start date, enter the course fee payable after funding and the amount of credit to claim, then upload the invoice (PDF, JPG or PNG, under 4MB).
Review, accept the terms and click Agree and Submit. The credit is paid directly to us; processing can take up to 14 working days.

Changing or withdrawing: cancel the claim on MySkillsFuture at least one day before the course starts. If your class date changes, cancel the claim and submit a new one with the new date.

How to Apply SkillsFuture Enterprise Credit (SFEC)

SFEC helps companies pay for employee training. The current SFEC ends on 30 November 2026, and a redesigned SFEC starts on 1 December 2026.

Current SFEC: classes ending on or before 30 November 2026

Eligible companies received a one-off $10,000 credit, notified by letter to their Corppass administrator. Eligibility generally required at least 3 Singapore Citizen or PR employees and Skills Development Levy contributions.
SFEC covers up to 90% of the company's out-of-pocket course fee after other subsidies.

Check your company's SFEC eligibility and balance on EnterpriseSG.
Register your Singapore Citizen or PR employee for a class that ends by 30 November 2026, as company-sponsored, and pay the course fee after funding.
Your employee attends and completes the course. We submit the attendance and assessment results to SWDA.
No separate claim is needed. SFEC is calculated automatically once the course fee grant is approved and is paid quarterly to your company's IRAS GIRO or PayNow Corporate account.

Any unused balance of the current SFEC expires on 30 November 2026.

Redesigned SFEC from 1 December 2026

Companies with at least 3 resident employees receive a fresh $10,000 in an online SFEC wallet that offsets out-of-pocket fees upfront at enrolment, instead of reimbursing them afterwards. SWDA has not yet published the support rates and claim steps; see OurWorkforce or our SFEC guide.

How to Apply PSEA

Singapore Citizens with a Post-Secondary Education Account (PSEA), which stays open until around the year you turn 31, can use it to pay the course fee after funding for PSEA-approved courses. You can also use a sibling's PSEA after your own has been used up.

Check that this course shows the PSEA tag on its MySkillsFuture page.
Check your PSEA balance on MOE's Student Finance System with Singpass.
Download and complete the PSEA withdrawal form, then submit it to us.
We submit the withdrawal request to MOE. You (and your sibling, if you are using their account) authorise it in the Student Finance System. Nothing is withdrawn without this authorisation.
MOE pays us directly. If you have already paid, we refund the amount covered by PSEA.

More details: MOE PSEA overview.

Appeal Process

If you disagree with an assessment decision, you have the right to appeal.

When the assessor gives you feedback, say whether you agree with the outcome. If you agree, you and the assessor sign the Assessment Summary Record; if you disagree, do not sign it.
Discuss the decision with the assessor or the assessment manager first.
If you are still not satisfied, tell the assessor you intend to appeal. The assessor records this in the feedback section of the Assessment Summary Record and informs the assessment manager.
Lodge your appeal within 7 days, giving your reasons, using the Candidate Appeal Form. The assessor can help you write and lodge it.
An Assessment Appeal Panel reviews the information from you and the assessor and makes a decision. A record of the appeal and its outcome is kept.
You will be told the outcome within 2 weeks of lodging the appeal. The panel's decision is final.

Job Roles

AI Engineer
AI Agent Developer
Automation Engineer
Machine Learning Engineer
Data Scientist
Natural Language Processing Engineer
Conversational AI Developer
Solutions Architect (AI systems)
Business Process Automation Analyst
Knowledge Management Specialist
Customer Experience Analyst
Digital Transformation Specialist
Product Manager (AI products)
AI Quality and Evaluation Engineer
AI Governance and Risk Analyst

Trainers

Getting an AI agent to do the right thing reliably, run after run, is the engineering problem Dr. Alfred Ang spends much of his time on. A full-stack AI developer and Agentic AI solution architect, he designs multi-agent systems with the Claude Agent SDK, the OpenAI Agents SDK, the Google Gemini Agent SDK, Microsoft AutoGen, CrewAI, n8n, Langflow and Flowise, and he serves as Managing Director, CIO, CTO and Chief Instructional Designer of Tertiary Infotech Academy Pte Ltd, having founded Tertiary Courses. His GitHub portfolio of more than 300 public repositories shows harness thinking in practice. His skills repository packages reusable Claude Code skills, giving an agent structured instructions, tools and checks for recurring tasks. His wsq-courseware-generator-claude-streamlit platform uses the Claude Agent SDK to generate assessment plans, guides, lesson plans and slides, work that depends on tight instructions and output validation. AIInterviewing scores candidates against a 30-mark rubric for each role with STAR-based improvement tips, and n8n-hrportal wraps an HR chatbot in input and output guardrails with human-in-the-loop approval. His data and analytics foundation is equally strong: he is a Microsoft Certified Data Scientist (DP-100), AI Engineer Associate (AI-102) and Power BI Data Analyst (PL-300), an AWS Certified AI Practitioner, and holds a PhD in Electrical Engineering from NUS, a Graduate Diploma in Intelligent Robotics Systems from NUS-ISS and the Certificate in AI Ethics and Governance (Senior Professional) from NTU.

In WSQ Harness and Loop Engineering for AI Agents, Dr. Ang teaches learners to build the scaffolding that turns a capable model into a dependable agent, using text analytics as the working domain. The course starts with harness and loop engineering itself: the instructions, context, tools, memory, permissions, validation rules and evaluation mechanisms that guide agent behaviour, and the observe, plan, act, evaluate and retry cycle that lets an agent improve its own output. Learners then apply these ideas to text collection, cleaning and pre-processing for agent workflows, followed by text analytics, information extraction and feature engineering. Sentiment analysis becomes the test bed for iterative evaluation loops, and the final topic covers sentiment summarisation, visualisation and the optimisation of agent output. He gives particular weight to loop controls such as stopping conditions, error recovery, state management, human approval, output validation and performance monitoring, because these are where real agent projects succeed or fail. Drawing on his rubric-scoring and guardrail work, he shows how to define what good output looks like before asking an agent to produce it, and how to measure improvement rather than assume it. Sessions are hands-on and aligned to the WSQ competency standards, and as an ACTA-certified trainer and DACE-certified curriculum developer he balances concepts with guided practice. Learners also compare a single-pass prompt with a well-harnessed loop on the same task, so the value of each control is visible in the results. To see the agent harnesses and evaluation tools he has built, explore his GitHub portfolio at https://github.com/alfredang and connect with him on LinkedIn at https://www.linkedin.com/in/angchewhoe/

Bernard Peh is a data analytics and digital transformation trainer with extensive experience in business intelligence, automation and workflow optimisation. A certified Principal Trainer and ACLP-qualified educator, he has delivered numerous programmes in data analytics, R programming and AI-driven data visualisation. He is also a data scientist with more than two decades of experience, and as Senior Partner and Lead Data Scientist at Big Data Venture Capital he works hands-on with Python, data acquisition and cleaning, feature engineering, ETL and visualisation. His training emphasises the practical application of analytical tools to real-world business challenges, bridging data science and operational decision-making.

WSQ - Harness and Loop Engineering for AI Agents applies these data skills to agent workflows built around text analytics. Bernard guides learners through collecting, cleaning and pre-processing text, extracting information and engineering features, running sentiment analysis with iterative evaluation loops, and summarising and visualising agent outputs. His sessions introduce context management, tool use and output validation within an agent harness, so participants learn to measure and improve what an agent produces rather than trusting a single run. Learners leave able to turn raw text into insights that support customer understanding and data-informed strategy.

Quah Chee Yong is an ACLP-certified trainer and data science professional with extensive experience in Python, natural language processing (NLP) and machine learning. He applies NLP tools such as NLTK, spaCy and Gensim to sentiment analysis, topic modelling and text classification, and has delivered corporate workshops on text analytics, recommender systems and chatbot development. A data scientist with a strong background in data engineering and applied statistics, he has worked on analytics projects involving customer segmentation, predictive modelling and text-based data mining, using R, Python and SQL for decision support and process automation. He has led AI training programmes for SAP, Temasek Polytechnic and IMDA under the SGUnited Mid-Career Pathways initiative.

WSQ Harness and Loop Engineering for AI Agents applies agent design to text analytics, an area where his NLP experience is directly relevant. Learners design harnesses that combine instructions, context, tools and validation rules, then collect, clean and pre-process text for agent workflows. They carry out text analytics, information extraction and feature engineering, run sentiment analysis with iterative agent evaluation loops, and finish with sentiment summarisation, visualisation and agent output optimisation. Through step-by-step instruction and real-world cases, he helps participants turn textual data into structured insights and build agents whose output improves reliably with each iteration.

Dwight Nuwan Fonseka is Head of Data Science at Plano Pte. Ltd. and an ACLP-certified trainer with deep expertise in data analytics, machine learning and AI applications. He has extensive hands-on experience developing predictive models and deep learning solutions in Python and R with TensorFlow and Keras, including preparing data and evaluating model performance. His professional background spans healthcare, finance and customer analytics, where analysing customer data is central. Dwight teaches AI with an applied focus on both its opportunities and its risks, and he also holds a Masters in Education from NTU with eight years of teaching experience.

In WSQ Harness and Loop Engineering for AI Agents, Dwight brings his data preparation and model evaluation experience to building reliable agents for text analytics. He covers harness and loop engineering for agent workflows, then text collection, cleaning and pre-processing, followed by text analytics, information extraction and feature engineering. Learners apply sentiment analysis with iterative agent evaluation loops, and finish with sentiment summarisation, visualisation and output optimisation, drawing on his dashboard background. His emphasis on testing and evaluation helps participants design structured harnesses and loops that guide agent behaviour, validate results and steadily improve the quality of task execution.

Dr. Alvin Ang is an ACLP-certified trainer with a PhD in Operations Research from Nanyang Technological University and a strong track record in data science, machine learning and text analytics. He has taught extensively at universities and training institutions, delivering courses in R, Python, data visualisation and advanced analytics. His IBM and Kaggle certifications, together with published research in analytics and optimisation, underscore both his academic and applied expertise in the techniques that sit beneath modern AI agent workflows.

In WSQ - Harness and Loop Engineering for AI Agents, Dr. Ang focuses on both the theoretical underpinnings and hands-on practice. He trains learners to structure agent loops for text preprocessing, information extraction and output validation, applying methods such as sentiment analysis and natural language processing. Participants start with harness and loop engineering for AI agent text analytics, move through text collection, cleaning and pre-processing, and then cover information extraction and feature engineering. They finish with sentiment analysis, iterative agent evaluation loops, and sentiment summarisation, visualisation and output optimisation. His teaching balances analytical rigour with practical case studies, so learners can design reliable harnesses and apply them effectively in business, research and digital transformation contexts.