British University in Egypt

This study employs a multi‐perspective modeling approach combining Response Surface Methodology (RSM), Machine Learning (ML), Artificial Neural Networks (ANNW), and Simulated Annealing (SA) to optimize Equal Channel Angular Pressing (ECAP) parameters for improving the mechanical and corrosion properties of AA7075 alloy. The investigation examines microstructural evolution, mechanical, and corrosion behavior under varying die angles (90° and 120°), processing routes (A, Bc, C), and up to four passes. Significant grain refinement was achieved, with the average grain size reduced from 16.3 to 1.68 μm for route Bc after four passes at 90°. Hardness nearly doubled from 92 to 177 HV under the same conditions, with routes A and C reaching 169 and 156 HV, respectively. Tensile strength increased from 283 to 352 MPa for 4Bc at 90°, while 120° conditions showed slightly lower but still improved performance. Corrosion analysis revealed route‐dependent behaviors, with route Bc at 90° reducing the corrosion rate to 0.0298 mm/year, compared to 0.0345 mm/year for the as‐received alloy. ML‐based models achieved high predictive accuracy (R² near unity), and RSM‐SA optimization closely matched experimental results. This integrated framework provides actionable insights for tailoring ECAP parameters to enhance AA7075's properties for industrial and construction applications.

Background Psychiatric nurses are exposed to patients experiencing severe emotional, psychological and behavioural challenges, which can lead to diminished empathy, compassion and overall well‐being. Compassion fatigue, primarily work‐related burnout, stems explicitly from the emotional strain of caregiving. The increasing prevalence of compassion fatigue among psychiatric nurses is a significant issue that threatens their ability to deliver competent and compassionate care. Aim This study seeks to explore the relationship between compassion fatigue, spiritual care and the competence of psychiatric nurses, emphasising the effect of compassion fatigue on spiritual and competent care. Method This study employed a cross‐sectional and correlational design on 322 psychiatric nurses from four hospitals in Alexandria, Sohag, Portsaid and Cairo, selected using convenience sampling. Data were collected through anonymous self‐administered questionnaires distributed from March to May 2024. The instruments used included the Compassion Fatigue Self‐Test (CFST) scale, the Spirituality and Spiritual Care Rating Scale (SSCRS), the Self‐Liking and Competence Scale‐Revised Version (SLCS‐R) and a demographic questionnaire. Findings The study's findings revealed significant relationships between compassion fatigue, spirituality, spiritual care and competence among psychiatric nurses. Nurses reported a mean compassion fatigue score of 128.22, and the analyses showed that compassion fatigue negatively correlated with both spirituality and spiritual care ( r = −0.411, p < 0.001) and competence ( r = −0.196, p < 0.001). Additionally, spirituality and spiritual care were positively correlated with competence ( r = 0.357, p < 0.001). Also, linear regression analyses indicated that compassion fatigue negatively impacted spirituality and spiritual care ( β = −0.196, p < 0.001). Implication Enhancing nurses' spiritual care competence through training and support can foster a more compassionate and spiritually supportive environment for patients, which is crucial in psychiatric care settings where patients often face complex emotional and mental health challenges. Conclusion These findings suggest that psychiatric nurses can improve their ability to deliver spiritually and professionally competent care by mitigating compassion fatigue, thus improving patient outcomes and nurse well‐being.

Viscosity is a key physical property in the production process of paint. In this research, statistical modeling was used to analyze and predict the viscosity of water-based architectural paint as part of quality control in a coating factory. In this sense, quality technicians constantly seek to improve this indicator. The Viscosity difference is modelled as a function of temperature in the ranges of 19–25 °C and 25–32 °C. Parametric polynomial regression, ANOVA analysis, residual plots, and Box-Cox transformation were used as statistical tools for data analytics and prediction. Model corrections were applied by using Cochrane–Orcutt transformation and assumptions were tested using the Kolmogorov–Smirnov statistics by Lilliefors, Breusch–Pagan, and Durbin–Watson. Improved Maximum Dissimilarity algorithm with the small group filter and representative initial set selection was used for selecting the best representative data to validate the models and three supervised machine learning methods (Random Forest, K-nearest neighbors, and Gradient-boosted trees) were employed through hyperparameter optimization, it was found that Random Forest gave the best performance. Two regression models were obtained: a second-degree polynomial model for samples with a temperature less than 25 °C and a simple linear non-parametric model one for samples at temperature greater than 25 °C. Adjusted coefficients of determination are 0.968 and 0.978, respectively. Finally, using the proposed predictive models could reduce the turnaround time by 48.5%.

Aims The primary aim was to monitor the healing of the periapical radiolucencies of adolescents’ mature permanent teeth with apical periodontitis after root canal retreatment with two REPs techniques at 24 months of follow-up. The secondary aim was to assess clinical outcomes and positive responses of retreated teeth to pulp sensibility tests. Methodology Forty adolescents with 48 teeth were enroled and randomly allocated into two equal groups after being matched according to their periapical index (PAI) scores. Root canal retreatment was performed with blood clot (BC) formation in one group and platelet-rich fibrin (PRF) in the other group. The healing process was tracked using standardized two-dimensional radiographic images to record the changes in the PAI scores after 3, 6, 12, and 24 months. Additionally, the clinical signs and symptoms and the positive responses to pulp sensibility tests were monitored. The difference between the PAI medians was analysed using the Mann–Whitney U test. The main impact of time on the PAI values and the interaction between time and the REPs technique were assessed using the general linear model (GLM). The alpha level of significance was 5%. Results After two years of follow-up, there was no significant difference between the two groups clinically and in the PAI medians. The overall success rates in the BC and PRF groups were 95% and 100%, respectively ( P > 0.05). Positive pulp responses were detected in 71% of the BC group and 73% in the PRF group ( P > 0.05). The EPT mean values in the BC and PRF groups were 40.86 ± 6.60 and 37.9 ± 15.22, respectively ( P > 0.05). Time had a significant impact on the PAI scores over the follow-up periods ( P > 0.0001), while the interaction effect of time with the REPs technique had no significant effect on the PAI scores ( P = 0.126). Conclusions REPs were effective in the retreatment of mature maxillary permanent incisors with apical periodontitis with a comparable reduction in the periapical radiolucencies and clinical outcomes associated with approximately similar positive responses to thermal and electric pulp tests.

Background: Fluorouracil (5‐FU) is one of the most popular chemotherapeutic agents used in various cancer therapy protocols. Cell‐free therapy utilizing exosomes is gaining increased popularity as a safer option due to concerns over potential tumor progression following stem cell therapy. Methods: Parotid glands of albino were treated with a single bone marrow mesenchymal stem cell (BMMSC)‐derived exosomes injection (100 μg/kg/dose suspended in 0.2 mL phosphate‐buffered saline [PBS]), a single 5‐Fu injection (20 mg/kg), and BMMSC‐derived exosomes plus 5‐FU and compared to control group (daily saline injections). After 30 days, the parotid glands were examined using qualitative histological evaluation, immunohistochemical evaluation using rabbit polyclonal mouse antibody to Ki‐67, caspase 3, and iNOS , as well as quantitative real‐time polymerase chain reaction (RT‐PCR) to evaluate gene expression of TGFβ1 , TNF-α , and BCL-2 . Results: Histological examination of the parotid gland revealed that BMMSC‐derived exosomes restored the glands’ architecture and repaired most of the distortion created by 5‐FU. Immunohistochemical expression of tumor proliferation and cell death markers were restored to normal levels in the exosome‐treated groups that were similar to the control group. Furthermore, BMMSC‐derived exosomes reversed the effects of 5‐FU on quantitative gene expression levels and showed a significant decrease in TNF-α ( p < 0.001) and a significant increase in TGFβ ( p < 0.0001) and BCL-2 ( p < 0.05) when compared to 5‐FU treatment. Conclusion: Within the limitations of the current study, BMMSC‐derived exosomes have the potential to counteract the cytotoxic effects of 5‐FU on the parotid glands of rats in vivo. Further studies are deemed necessary to simulate clinical scenarios.

Developing efficient antiviral protectives is a new approach against respiratory emerging viruses. This study aims to synthesize silver nanoparticles (Ag NPs) via a green technique using crocin to provide a virucidal effect and to enhance the protection of polyacrylonitrile (PAN) nanofibrous face masks or respirators against viruses. The influence of formulation and process variables on the particle size (PS) of Ag NPs was studied using D-optimal response surface design. The selected NPs were loaded into PAN nanofibers (NFs). MTT colorimetric assay was performed to determine the safety of the prepared NPs and NFs on Vero cells. Further, an immunofluorescent assay was performed to determine the composite's ability to inhibit the ACE2-SARS-CoV-2 spike protein interaction and prevent viral infection. The selected NPs possessed a small PS of 23.21 ± 0.86 nm, a PDI of 0.23 ± 0.019, and a ZP of-21.8 ± 1.82 mV. The optimum NF composite was fabricated with a PAN concentration of 8% w/v loaded with 0.25% w/w Ag NPs, with a feeding rate of 0.7 mL/h and an applied voltage of 23.5 kV. The resultant NFs displayed an acceptable morphology and a mean diameter of 378.88 ± 91.12 nm. In vitro cytotoxicity studies on Vero cells revealed the biocompatibility of crocin and Ag NPs. Moreover, Ag-PAN NFs were proven biologically safe. The immunofluorescent assay showed that Ag-PAN NFs demonstrated the least IC50 value of 10.99 µg/mL, indicating their potent effect on inhibiting SARS-CoV-2 infection. Ag-PAN NFs are a promising safe antiviral composite that has the potential to be used in face masks.

This study aimed at generating preliminary evidence for the potential utility of repurposing the clinically approved anti‐ischemic drug trimetazidine (TMZ) against methotrexate (MTX)‐induced hepatotoxicity. In this study, rats received MTX (30 mg/kg) with or without TMZ pretreatment (20 mg/kg). MTX caused a 2.7–3.6‐fold increase in serum transaminases, while TMZ pretreatment caused a 37%–40% reduction. Regarding oxidative markers, MTX significantly suppressed the antioxidant glutathione (GSH) levels by 37% and elevated malondialdehyde (MDA) levels by 29%, while TMZ boosted GSH levels by 40% and reduced MDA levels by 20%. Next, we assessed nuclear factor kappa B (NF‐κB) (p‐65), nuclear factor erythroid 2‐related factor 2 (Nrf2) and hemoxygenase‐1 (HO‐1) to find that MTX significantly elevated the levels of the proinflammatory nuclear factor kappa B (NF‐κB) (p65) by 2.4‐fold, while TMZ pretreatment reduced its levels by 48%. Conversely, MTX decreased the levels of Nrf2, HO‐1, and adenosine triphosphate (ATP) by 55%–71%, while TMZ led to a threefold increase in their levels. Regarding apoptosis, MTX caused a five to sixfold elevation in B‐cell lymphoma 2 associated X (Bax)/B‐cell lymphoma 2 (BCL2) ratio and caspase‐3, while TMZ pretreatment caused a threefold reduction in their levels. An in silico analysis of TMZ protein target‐prediction revealed statistically enriched pathways related to oxidative stress, inflammation, and apoptosis. In conclusion, pretreatment with TMZ successfully ameliorated MTX‐induced alterations in serum aminotransferases, liver histology, oxidative stress, and apoptosis. Pathway enrichment analysis (PEA) showed that TMZ is involved in multiple signaling and immune‐related pathways that might be, at least partly, implicated in its cytoprotective effects.

The RANK/RANKL/OPG signaling pathway plays a crucial role in breast cancer progression and metastasis. However, its expression patterns and potential implications in breast cancer stem cells remain poorly understood. This study aimed to characterize the expression profile of this pathway in breast cancer stem cells isolated from two distinct breast cancer cell lines: MDA‐MB‐231 and MCF‐7. Mammospheres (MS), representing breast cancer stem cells, were generated using agar‐coated 6 well tissue culture plates in suitable mammospheres culture conditions. Flow cytometric analysis showed enrichment of the CD44 ⁺ /CD24 ⁻ subpopulations in the mammospheres cultures, with MDA‐MB‐231 exhibiting a higher percentage compared to MCF‐7. The isolated MS from both cell lines showed upregulation of stemness markers OCT4 and SOX2, with MS. MDA‐MB‐231 demonstrating higher expression levels. Analysis of the RANK/RANKL/OPG axis revealed differential expression patterns between the two cell lines. RANK expression was significantly upregulated in MS. MDA‐MB‐231 but not in MS. MCF‐7. Interestingly, while OPG mRNA levels were elevated in mammospheres from both cell lines, secreted OPG protein levels were paradoxically reduced in the mammospheres conditioned media. Additionally, RUNX2, an osteoblastic marker, and a downstream target of RANK signaling, showed a decreased expression in both mammospheres compared to adherent cells. These findings suggest a complex, context‐dependent regulation of the RANK/RANKL/OPG pathway in breast cancer stem cells, potentially contributing to the aggressive nature and metastatic propensity of triple‐negative breast cancer. This study provides novel insights into the molecular characteristics of breast cancer stem cells and underscores the complexity of OPG/RANK/RANKL axis expression in them; a role yet to be fully elucidated.

Background:Becium grandiflorum is a fragrant perennial shrub of the Lamiaceae family. Objectives: The current study aimed to explore the cytotoxic potential of the n-hexane fraction from Becium grandiflorum aerial parts and, further, isolate its major diterpene and conduct in vitro and in vivo anticancer activities along with its molecular mechanism and synergy with doxorubicin. Methods: The hydroalcoholic extract of Becium grandiflorum aerial parts was fractionated, and the n-hexane fraction was analyzed via GC-MS. The major isolated diterpene, 18-epoxy-pimara-8(14),15-diene (epoxy-pimaradiene), was quantified using UPLC-PDA. Cytotoxicity assays were conducted on HCT-116, MCF-7, MDA-MB-231, and HepG2 cell lines. The synergistic effect with doxorubicin was tested on HepG2 cells. In vivo anticancer activity was evaluated using the Ehrlich ascites carcinoma model, and molecular docking analyzed Bax-Bcl2 interactions. Results: The n-hexane fraction contained 21 compounds, mainly oxygenated diterpenes, and the major isolated compound was epoxy-pimaradiene, with a quantity of 0.3027 mg/mg. N-Hexane fraction and epoxy-pimaradiene exhibited strong cytotoxicity against HepG2 cells, induced apoptosis, and G2/M arrest. The combination of epoxy-pimaradiene with doxorubicin lowered the IC50 of doxorubicin from 4 µM to 1.78 µM. In vivo, both reduced tumor growth and increased necrotic tumor areas. Molecular docking revealed disruption of Bax-Bcl2. Conclusions: The findings suggest that B. grandiflorum and its major diterpene, epoxy-pimaradiene, exhibit potent anticancer activity, particularly against liver cancer cells. Epoxy-pimaradiene enhances doxorubicin’s efficacy, induces apoptosis, and inhibits tumor progression. Further studies are needed to explore their therapeutic potential.

A search is presented for the pair production of new heavy resonances, each decaying into a top quark (t) or antiquark and a gluon (g). The analysis uses data recorded with the CMS detector from proton–proton collisions at a center-of-mass energy of 13 $\,\text {Te}\hspace{-.08em}\text {V}$ Te V at the LHC, corresponding to an integrated luminosity of 138 $\,\text {fb}^{-1}$ fb - 1 . Events with one muon or electron, multiple jets, and missing transverse momentum are selected. After using a deep neural network to enrich the data sample with signal-like events, distributions in the scalar sum of the transverse momenta of all reconstructed objects are analyzed in the search for a signal. No significant deviations from the standard model prediction are found. Upper limits at 95% confidence level are set on the product of cross section and branching fraction squared for the pair production of excited top quarks in the $\text {t}^{*} \rightarrow {\text {t}} {\text {g}}$ t ∗ → tg decay channel. The upper limits range from 120 to 0.8 $\,\text {fb}$ fb for a $\text {t}^{*}$ t ∗ with spin-1/2 and from 15 to 1.0 $\,\text {fb}$ fb for a $\text {t}^{*}$ t ∗ with spin-3/2. These correspond to mass exclusion limits up to 1050 and 1700 $\,\text {Ge}\hspace{-.08em}\text {V}$ Ge V for spin-1/2 and spin-3/2 $\text {t}^{*}$ t ∗ particles, respectively. These are the most stringent limits to date on the existence of $\text {t}^{*} \rightarrow {\text {t}} {\text {g}}$ t ∗ → tg resonances.

State reconstruction and peacebuilding processes provide windows of opportunity to reshape existing political settlements especially through addressing underlying power dynamics.

Secure image encryption is critical for protecting sensitive data such as satellite imagery, which is pivotal for national security and environmental monitoring. However, existing encryption methods often face challenges such as vulnerability to traffic analysis, limited randomness, and insufficient resistance to attacks. To address these gaps, this article proposes a novel multiple image encryption (MIE) algorithm that integrates hyperchaotic systems, Singular Value Decomposition (SVD), counter mode RC5, a chaos-based Hill cipher, and a custom S-box generated via a modified Blum Blum Shub (BBS) algorithm. The proposed MIE algorithm begins by merging multiple satellite images into an augmented image, enhancing security against traffic analysis. The encryption process splits the colored image into RGB channels, with each channel undergoing four stages: additive confusion using a memristor hyperchaotic key transformed by SVD, RC5 encryption in counter mode with XOR operations, Hill cipher encryption using a 6D hyperchaotic key and invertible matrices mod 256, and substitution with a custom S-box generated by a modified BBS. Experimental results demonstrate the proposed algorithm’s superior encryption efficiency, enhanced randomness, and strong resistance to cryptanalytic, differential, and brute-force attacks. These findings highlight the MIE algorithm’s potential for securing satellite imagery in real-time applications, ensuring confidentiality and robustness against modern security threats.

Alzheimer’s disease (AD), the most common dementia in the elderly, poses a challenge for early diagnosis due to its progressive nature and hidden microstructural changes. While traditional T1 and T2 weighted MRI can assess macro-structural brain atrophy, diffusion tensor imaging (DTI) unveils these hidden microstructural alterations. This study explores the use of DTI data, specifically visual patterns in Fractional Anisotropy (FA), Mean Diffusivity (MD), and Radial Diffusivity (RD) maps, to characterize AD progression. This paper proposes a computer-aided diagnosis (CAD) framework employing SIFT and SURF descriptors and a bag-of-words approach to build AD-specific signatures for the hippocampus region, known to be heavily affected by the disease. These signatures are extracted from MD, FA, and RD maps and used to differentiate between AD, mild cognitive impairment (MCI), and normal controls (NC) in both multiclass and binary classification scenarios. Additionally, we investigate late fusion of visual map features for enhanced decision-making. The experiments were accomplished with a subset of participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset formed of AD patients (n = 35), Early Mild Cognitive Impairment (EMCI) (n = 6), Late Mild Cognitive Impairment (LMCI) (n = 24) and cognitively healthy elderly Normal Controls (NC) (n = 31). Promising preliminary results demonstrate the potential of the proposed system as a useful tool to capture the AD leanness with achieving accuracies of 87.5%, 87.4%, 89%, and 95.2% for MD, FA, RD, and fusion of features respectively for the multiclass system using SIFT features. Using FA features for binary discrimination achieves 97.5%. Moreover, the fusion based on the decision level model reached an accuracy of 93.3% AD/MCI, 95.7% AD/NC, and 93.3% MCI/NC (96.2 ± 3.6 MCI vs. NC, 97.5 ± 5 AD vs. NC). Furthermore, fusion of features led to a noteworthy precision boost of 96%. These findings suggest that our DTI-based CAD framework holds promise as a reliable and accurate tool for capturing AD progression, paving the way for earlier diagnosis and potentially improved patient outcomes.

We examined differences and similarities between groups sampled from the Mediterranean region in social orientation, cognitive style, self-construal, and honor, face, dignity values, and concerns using a large battery of tasks and measures. We did this by conducting secondary data set analyses focusing on comparisons between nine pairs of samples recruited from the Mediterranean region (Spain, Italy, Greece, Turkey, Cyprus [Greek and Turkish Cypriot communities], Lebanon [Muslim Lebanese and Christian Lebanese], Egypt) that have overlapping and divergent features in terms of religious, ethnic, national, and linguistic factors as well as various physical and socioecological characteristics. Across 38 different psychological characteristics, comparisons between Turkish and Turkish Cypriot samples and between Christian and Muslim samples from Lebanon revealed that they were most similar to each other. In contrast, Greek and Turkish samples were the least similar. Our analyses of intercorrelations between variables, variability, and size of differences provide additional insights into the within-region variation in social orientation, cognitive style, self-construal indicators, as well as honor, face, and dignity values and concerns. Our research contributes to the growing literature on regional variation of psychological processes while raising important pointers for the role of background and socioecological characteristics in cultural group similarities and differences.

This chapter introduces the foundational concepts essential to understanding and applying prompt engineering effectively. It begins with an overview of artificial intelligence (AI), its historical evolution, and the transformative impact of generative AI in various domains. The discussion highlights the pivotal role of natural language processing (NLP) in bridging human–computer communication, with a focus on large language models (LLMs) and their capabilities. Key topics include pre-training and fine-tuning, the distinctions between prompting AI and web searches, and the significance of crafting precise and context-aware prompts to optimise AI interactions. The chapter further explores prompt engineering techniques, patterns, and optimisation strategies, emphasising the importance of safety and ethical considerations. By synthesising these elements, this chapter lays the groundwork for leveraging prompt engineering as a critical skill for enhancing AI reliability and adaptability across diverse applications.

This chapter explores the fundamental principles of effective prompt design, an essential element in prompt engineering. Unlike specific techniques, these principles are versatile, applied across diverse AI models and contexts, and they possess enduring relevance. Key topics covered include clarity, specificity, and conciseness, which collectively enhance the quality of AI interactions by eliminating ambiguity and over-complication. The chapter also emphasises the importance of providing contextual information, incorporating instructional details, and leveraging domain knowledge to optimise the relevance and accuracy of AI outputs. Readers will learn to utilise action verbs, specify output formats, and use examples to guide AI responses effectively. Structural considerations, such as prompt templates and component separation, are highlighted for their role in improving clarity and coherence. The chapter concludes with insights on iterative refinement, creativity, and staying updated with advancements in AI, providing readers with a comprehensive framework to craft prompts that generate precise, relevant, and innovative results. This guidance empowers users to harness AI’s full potential across various domains, ensuring interactions are both efficient and meaningful.

This chapter explores the critical security risks inherent in prompt engineering for AI-driven systems. Key vulnerabilities include prompt injection, where malicious inputs can alter system behaviour, and prompt leaking, where sensitive or proprietary information is unintentionally revealed. The chapter addresses advanced threats such as jailbreaking, adversarial prompts, and model manipulation, which exploit model weaknesses to bypass safeguards. Risks like model poisoning and contextual drift highlight how interactions can subtly corrupt AI outputs or lead to unintended behaviours. Emphasis is placed on the challenges of balancing openness with protection in role-based prompting, mitigating social engineering exploits, and preventing input validation attacks. The chapter also examines the risks posed by output manipulation, bias amplification, and resource exhaustion, underscoring the necessity for robust safeguards to maintain system integrity. Solutions discussed include prompt isolation, input sanitisation, session resets, and ethical constraints, providing a comprehensive framework to address these evolving threats. The chapter concludes with actionable strategies for building secure and resilient AI systems, ensuring they operate reliably and ethically across diverse applications.

This chapter examines the multifaceted challenges in prompt engineering, which are essential for optimising human-AI interactions. It begins with managing ambiguity in human language and balancing specificity and flexibility in prompts, addressing the need for precision while fostering creativity. Consistency across responses and bias mitigation are discussed as pivotal for building trust and ensuring ethical outputs. The chapter also delves into challenges like leveraging domain-specific knowledge and designing prompts to uphold privacy and ethical considerations. Cross-model portability and the explainability of AI responses are explored, highlighting the variability and opacity of AI behaviour across models. Additionally, the text addresses issues of model limitations, hallucinations, and the impact of model updates on prompt effectiveness. The chapter concludes by emphasising safety, security, and the evolving art of prompt engineering, underscoring its role in designing adaptive and responsible AI interactions across diverse applications.

This chapter provides an overview of essential tools and resources in prompt engineering, highlighting their role in optimising interactions with large language models (LLMs). It introduces key tools such as OpenAI Playground, LangChain, and Guidance, which facilitate prompt creation, testing, and optimisation, alongside platforms like PromptHub and PromptBase that foster community collaboration. Specialised resources like AIPRM and Haystack support advanced tasks, including prompt management and integration with real-time information retrieval systems. The chapter also details online resources, including courses, tutorials, and documentation from organisations such as DeepLearning. AI and OpenAI, catering to a range of skill levels. Additionally, it presents a curated list of recent books that offer in-depth insights into the art and science of prompt engineering. Together, these tools and resources form a comprehensive foundation for mastering prompt engineering, empowering users to achieve precision, creativity, and efficiency in AI-driven applications.

This chapter explores key techniques for effective prompt engineering, categorising methods into basic, advanced, and professional levels. Basic techniques such as direct instruction, question-based, and open-ended prompting establish foundational approaches for clear and concise AI interactions. Advanced strategies like chain-of-thought prompting and role-based prompting delve into nuanced methods that enhance contextual understanding and reasoning capabilities. The chapter also introduces professional-level techniques, including iterative prompting and task decomposition, which refine complex processes and foster adaptability. These strategies emphasise optimising prompt clarity, contextual relevance, and structural coherence to achieve precise, actionable, and creative AI responses. By systematically applying these techniques, users can harness AI’s potential across diverse applications, ensuring outputs that align with specific objectives and user intent.