Microplastics in Food and Water

Are We Eating Plastic? The Hidden Contamination Crisis from Soil to Table

Microplastics (MPs) — defined as plastic particles with at least one dimension below 5 millimetres — have become one of the most pervasive emerging contaminants in global food and water systems. Unlike conventional food safety hazards, MPs do not originate from a single industrial process, pathogen, or chemical group; they are a structural consequence of the modern plastic economy itself. Global plastic production exceeded 400 million tonnes per year by the early 2020s, and less than 10% is effectively recycled, with the remainder fragmenting through UV exposure, mechanical weathering, and biological activity into particles that migrate into virtually every compartment of the human food chain. Primary polymers detected in food systems include polyethylene terephthalate (PET), polypropylene (PP), and polyethylene (PE), principally resulting from the degradation of bottles, bottling processes, and contaminated source water [1]. The article examines the hazard profile of MPs as a food safety concern, traces the contamination pathways from agricultural soil to finished food products, and evaluates current and emerging control strategies within food safety management frameworks.

 

Prevalence in the Food Supply: Quantified Contamination Across Food Categories

The ubiquity of MP contamination across food matrices is now well established across more than a decade of global monitoring research. MPs have been detected in a wide range of food sources, including vegetables (6.4 particles/100 g), honey (1,992–9,752 particles/kg), sugar (249 ± 130 particles/kg), cereals (5.7 particles/100 g), dairy products (8.1 particles/100 g), meats (9.6 particles/100 g), beers (152 ± 50.97 particles/L), and soft drinks (40 ± 24.53 particles/L) [2]. These figures reveal that contamination is not confined to any single food category or processing pathway; it is systemic across both animal and plant-derived products, processed and raw, regardless of geographic origin.

 

Seafood has received the greatest research attention, given the expectation that filter-feeding marine organisms would accumulate elevated MP loads. Shellfish and other animals consumed whole pose particular concern for human exposure, and if there is toxicity it is likely dependent on dose, polymer type, size, surface chemistry, and hydrophobicity [3]. Bivalves such as oysters, mussels, and clams have consistently returned among the highest contamination levels in studies across Europe, Asia-Pacific, and North America. In the case of drinking water, both tap and bottled sources are implicated. MPs abundance in bottled water has been reported as higher than that in tap water, and plastic particles can enter bottled water during the process of bottle cleaning, filling, and capping, with cap abrasion identified as the main entry path into bottled mineral water [4]. This is a critical finding for food safety professionals: switching to bottled water as a mitigation strategy for other contaminants may inadvertently increase MP exposure. Relying on bottled water for drinking needs can increase the amount of microplastics ingested by more than six times compared to tap water consumption [5].

 

The scale of human dietary intake is substantial. Scientific estimates suggest that humans ingest on the order of a credit card's worth of plastic per week across food, water, and inhalation routes combined, and people in the U.S. could be ingesting 4,000 microplastic particles or more through tap water each year [5] The detection of MPs in human blood, placental tissue, gastrointestinal samples, and lung tissue confirms that dietary and inhalation exposure translates into systemic bioaccumulation, not merely gastrointestinal transit.

 

Microplastics in Agriculture: Soil-to-Food Transfer

While aquatic contamination pathways have been extensively studied, the terrestrial food chain — and in particular the agricultural soil-to-crop transfer pathway — represents a less-characterised but equally significant contamination route. With increasing amounts of microplastics deposited in soil from various agricultural activities, crop plants have become an important source of MPs in food products, and the last three years of studies have provided sufficient evidence showing that plastic in the form of nanoparticles can be taken up by the root system and transferred to aboveground plant parts [6], which is a development of fundamental significance to food safety hazard analysis: it means that even leafy vegetables, cereals, and root crops grown without any direct plastic contact in processing can carry MPs acquired during cultivation.

 

Agricultural soils accumulate MPs from multiple entry routes. Plastic mulch films — widely used for weed suppression and soil moisture retention across China, Southern Europe, the Middle East, and increasingly in North America — fragment progressively in the field. In agriculture, MPs can come from many sources including mulch film, tractor tires, compost, fertilizers, and pesticides, and can alter soil structure and composition, triggering a cascade of changes in the biophysical environment of the soil [7]. Sewage sludge application for soil nutrient management represents a particularly significant source: biosolids applied as fertiliser in many agricultural systems carry MP loads accumulated during wastewater treatment, where MPs are removed from the aqueous fraction and concentrated into the solid residual. Irrigation with treated wastewater introduces further loads, as does atmospheric deposition from industrial and urban sources.

 

Estimates suggest that approximately 32% of global plastic waste may end up in terrestrial ecosystems, with a substantial fraction accumulating in agricultural lands, [8] making soils the largest environmental reservoir of MPs globally, exceeding ocean surface concentrations by orders of magnitude on a per-unit-volume basis. Once in soil, MPs interact with the agricultural system in ways that extend well beyond their role as physical contaminants. Heavier amounts of microplastics have been linked to slower root development, changes in how nutrients cycle through the soil, and altered interactions with other contaminants like pesticides or heavy metals, and microplastic surfaces provide a home for bacteria and fungi, sometimes called the "plastisphere" – which in some cases can include harmful organisms that pose risks to crops or human health [9]. The "plastisphere" concept is particularly relevant to food safety hazard identification: MPs in soil and water function not merely as inert physical particles but as mobile vectors for microbial hazards and adsorbed chemical contaminants, concentrating pesticides and heavy metals at their surfaces and carrying them through the soil-plant continuum.

 

Hazard Profile: Physical, Chemical, and Biological Dimensions

The hazard profile of MPs in food is multidimensional, and this complexity is one of the primary reasons that risk characterisation has lagged behind hazard identification. Three distinct hazard mechanisms are relevant to food safety analysis.

 

Physical hazard 

Particle size determines the depth of biological penetration. Larger MPs (1–5 mm) are primarily retained in the gastrointestinal tract and excreted. Particles below 150 micrometres are capable of crossing the intestinal epithelium, and nanoplastics (below 1 micrometre) can translocate across the gut barrier into the bloodstream and accumulate in systemic tissues. MPs have been detected in human blood, placental tissue, and gastrointestinal samples, indicating systemic exposure, with proposed biological pathways including oxidative stress, inflammation, endocrine disruption, and alterations in the gut microbiota [10]. The mechanical abrasion of tissue surfaces by irregularly shaped MP fragments, and the potential for persistent particle accumulation in organs including the liver, kidney, and lymphatic tissue, constitutes a physical hazard distinct from any chemical toxicity.

 

Chemical hazard 

Plastics are not chemically inert. They contain a range of intentionally added chemical substances; including plasticisers, stabilisers, flame retardants, pigments, and antioxidants that may leach from the polymer matrix into food matrices or biological systems. Polyvinyl chloride contains phthalates associated with endocrine disruption, polycarbonate often includes bisphenol A linked to reproductive disorders, styrene (a component of polystyrene) is classified as a probable human carcinogen, and polyethylene terephthalate may release toxic antimony compounds under high temperatures [11]. In addition to intentionally added substances, MPs adsorb persistent organic pollutants, heavy metals, and pesticide residues from the surrounding environment, concentrating them at particle surfaces and potentially delivering them to biological tissues upon ingestion — a mechanism described in the literature as the "Trojan horse" effect.

 

Biological hazard 

The plastisphere; the microbial biofilm community that colonises MP surfaces can selectively enrich pathogenic bacterial taxa and antimicrobial resistance genes. Studies have demonstrated that MP biofilms in aquatic and soil environments support elevated concentrations of E. coli, Vibrio species, and antibiotic-resistant organisms relative to surrounding water or soil. The findings introduce a novel dimension to microbial food safety risk that is not captured by conventional pathogen monitoring programs.

 

Root Cause Analysis: Why Contamination is Systemic

A root cause analysis of MP food contamination reveals that it is not an isolated processing failure but the product of structural choices embedded across the food system. At the primary production level, the intensive use of plastic in agriculture such as mulch films covering an estimated 20–30 million hectares globally, plastic-coated fertilisers, plastic irrigation infrastructure, and plastic greenhouse films; that introduces MPs directly into the production environment without any equivalent removal step. At the processing and packaging level, plastic contact surfaces, packaging materials, and bottling operations generate MPs through abrasion and degradation. At the retail and domestic level, plastic food containers, cooking utensils, single-use packaging, and synthetic textiles in the laundry stream contribute further loads to the broader environment that re-enter the food chain through water systems.

 

A further structural root cause is the absence of standardised analytical methods. Concentrations fluctuate significantly across studies, ranging from a handful to several hundred particles per litre, influenced by the type of beverage, packaging material, and method of analysis employed; the lack of standardised methods hinders comparability of data [1]. Such methodological fragmentation has delayed the development of regulatory limits and risk-based management thresholds. Unlike mycotoxins or heavy metals, for which internationally harmonised analytical methods (e.g., AOAC, ISO) and maximum limits (e.g., Codex Alimentarius, EU Regulation) exist, MPs currently have no equivalent framework in any major food regulatory jurisdiction. The FDA has noted that because there are no standardised methods for how to detect, quantify, or characterise microplastics and nano-plastics, many of the scientific studies have used methods of variable, questionable, and/or limited accuracy and specificity [12].

 

Health Effects: Emerging Evidence and Unresolved Uncertainties

The health implications of chronic dietary MP exposure are an area of intense and rapidly evolving research. Evidence from animal models and in vitro studies is substantial; however, direct epidemiological evidence linking MP exposure to specific human disease outcomes remains limited due to the absence of long-term cohort studies with validated biomarkers of MP exposure.

 

At the gastrointestinal level, MP exposure has been mechanistically linked to gut dysbiosis, a condition of impaired microbial diversity and altered functional capacity. Exposure to MPs such as polyethylene, polystyrene, PET, PVC, and polylactic acid induces gut dysbiosis, marked by a loss of beneficial genera and enrichment of pathogenic species [13]. MP-induced dysbiosis further disrupts intestinal barrier integrity, contributing to increased permeability — sometimes described as "leaky gut" — which is associated with systemic inflammatory conditions. The inflammatory response induced by MP exposure may also affect the gut-brain axis, a complex bidirectional communication network between the GI system and the central nervous system, where dysbiosis can disrupt these functions, leading to neuroinflammation, which is implicated in neurological and psychiatric conditions such as anxiety, depression, and cognitive decline [14].

 

Endocrine disruption is among the most concerning potential health effects, particularly for reproductive health and developmental outcomes. Chemical additives including BPA, phthalates, and organotins associated with common polymer types are established endocrine-disrupting chemicals at environmentally relevant exposure levels. Evidence suggests that MNP exposure might elevate the risk of various diseases, including metabolic, respiratory, cardiovascular, neuroendocrine, hepatic, renal, and skin disorders, as well as infectious diseases, cancer, and ageing-related disorders [11]. With respect to carcinogenicity, microplastics are capable of triggering cytotoxicity and chronic inflammation, and may promote cancer through mechanisms such as pro-inflammatory responses, oxidative stress, and endocrine disruption, with current studies suggesting an association between microplastics and certain cancers including lung, liver, and breast cancers, although long-term effects and specific mechanisms still require further study [15].

 

It is important, however, to acknowledge the epistemic boundaries of the current evidence base. The FDA's current position reflects such uncertainty: current scientific evidence does not demonstrate that the levels of microplastics or nanoplastics detected in foods pose a risk to human health [12]. This regulatory position is not a declaration of safety — it reflects the absence of sufficient dose-response data to establish causality at human exposure levels. The precautionary principle, as applied under ISO 22000:2018 and Codex Alimentarius principles, would warrant hazard identification and monitoring even in the absence of confirmed risk quantification.

 

Control Strategies: From Farm to Consumer

Given that MP contamination is systemic and multi-source, no single control point within a conventional HACCP framework can be designated as a Critical Control Point sufficient to eliminate or adequately reduce the hazard, which represents a fundamental challenge for food safety management system design and demands a preventive, whole-chain approach.

 

At the agricultural level, reducing plastic inputs is the highest-leverage intervention. The FAO's Voluntary Code of Conduct for the Sustainable Use and Management of Plastics in Agriculture (2025) represents the first international guidance framework specifically addressing agricultural plastic management, recommending minimum thickness standards for mulch films to extend functional life and reduce fragmentation rates, and promoting the development and commercialisation of certified biodegradable alternatives, where lifecycle assessments demonstrate net environmental benefit. However, biodegradable plastics are not without risk: studies have identified that some biodegradable polymer types release potentially phytotoxic breakdown products during degradation, and "biodegradable" does not necessarily mean rapid or complete soil mineralisation under field conditions.

 

At the water treatment level, conventional wastewater treatment removes a significant proportion of MPs from the aqueous fraction, where estimates range from 70% to over 99% removal efficiency, but that concentrates the removed particles in sewage sludge. Where that sludge is applied to agricultural land, the removal achieved in wastewater treatment is effectively reversed at the field level. Advanced filtration technologies including membrane bioreactors, rapid sand filtration, and coagulation-flocculation processes can achieve higher removal rates from drinking water, but their implementation in municipal systems is inconsistent globally. Efforts to reduce impact should prioritise sustainable packaging materials, sophisticated filtration systems, regulatory standards, and consumer education to decrease exposure [1].

 

At the food production and processing level, ISO 22000:2018 provides a relevant framework for addressing MPs as an environmental contaminant through the Prerequisite Programme (PRP) and Operational PRP structure. Relevant PRPs include: facility design and construction (selection of non-shedding food-contact surface materials, elimination of polystyrene and PVC in food-contact applications), equipment maintenance (monitoring of wear rates on plastic components including conveyor belts, gaskets, and tubing), water quality management (MP-specific monitoring in process water), and packaging material selection (preference for glass or certified low-migration polymers for high-risk applications). Within the hazard analysis, MPs should be evaluated as a physical hazard under the hazard identification step, with particular attention to packaging-derived contamination in high-temperature processing applications where polymer degradation and chemical migration rates increase significantly.

 

Detection technologies for MPs in food systems have advanced considerably in recent years, moving from labour-intensive microscopic methods toward spectroscopic and hyperspectral imaging platforms. Fourier-transform infrared spectroscopy (FTIR) and Raman spectroscopy provide polymer identification at the particle level, while pyrolysis-gas chromatography mass spectrometry (Py-GC-MS) enables mass-based quantification of polymer types in complex matrices. Emerging artificial intelligence-assisted imaging platforms are beginning to enable higher-throughput screening, though their validation for regulatory applications remains at an early stage.

 

Regulatory Status and Governance Gaps

The regulatory governance of MPs in food and water is currently fragmented and inadequate relative to the scale of the contamination. No Codex Alimentarius maximum limit exists for MPs in any food category. In the European Union, the Single-Use Plastics Directive (2019/904) and the proposed Packaging and Packaging Waste Regulation represent structural measures targeting plastic reduction upstream, but do not establish food safety limits for MP contamination of finished products. The REACH regulation's restriction on the intentional addition of microplastics to products (Commission Regulation (EU) 2023/2055) addresses a significant source of primary MPs from personal care products, fertiliser coatings, and sports surfaces, but does not address the much larger reservoir of secondary MPs generated by weathering of existing plastic infrastructure.

 

In the United States, seven State Governors petitioned the EPA in late 2025 for mandatory monitoring requirements for MPs in public drinking water systems, reflecting the absence of any current federal monitoring requirement. The EPA's framework for interagency collaboration on antimicrobial resistance risks associated with pesticides (2024) signals growing regulatory attention to the intersection of agricultural chemical use and broader public health outcomes, though MPs are not yet formally addressed within this framework.

 

Conclusion

Microplastics represent a novel, pervasive, and complex food safety challenge that sits outside the traditional paradigm of point-source contamination. Their presence in virtually every food category, their multi-pathway entry into the food chain from soil, water, packaging, and processing, and their multidimensional hazard profile — physical, chemical, and biological — make them a priority concern for food safety management systems, regulatory science, and public health research alike. The critical knowledge gaps remain dose-response characterisation at human-relevant exposure levels, standardisation of analytical methods to enable regulatory limit-setting, and understanding of long-term health consequences through prospective epidemiological studies. For food safety professionals operating under ISO 22000:2018 or FSSC 22000, the current evidence base is sufficient to warrant formal hazard identification and documentation within hazard analysis, and the precautionary principle supports proactive operational measures to reduce MP contamination at every stage of the supply chain where technically feasible.

 

 

References

[1] Prevalence and health risks of microplastics in bottled water and beverages. ScienceDirect. 2025. https://www.sciencedirect.com/science/article/pii/S3051060025000241

[2] Yarahmadi A, Heidari M, Sepahvand A, et al. Microplastics and environmental effects: investigating the effects of microplastics on aquatic habitats and their impact on human health. Frontiers in Ecology and Evolution. 2024. https://pmc.ncbi.nlm.nih.gov/articles/PMC11191580/

[3] Smith M, Love DC, Rochman CM, Neff RA. Microplastics in Seafood and the Implications for Human Health. Curr Environ Health Rep. 2018 Sep;5(3):375-386. doi: 10.1007/s40572-018-0206-z. PMID: 30116998; PMCID: PMC6132564.

[4] Duda A, Petka K. The presence of micro- and nanoplastics in food and the estimation of the amount consumed depending on dietary patterns. Molecules. 2025;30:3666. https://pmc.ncbi.nlm.nih.gov/articles/PMC12472390/

[5] Erin D., Natalie B., The Mega-Crisis of Microplastics in Our Drinking Water, , https://www.foodandwaterwatch.org/2024/11/25/microplastics-drinking-water-petition/

[6] Brzezicha-Cirocka J, et al. Microplastic and nanoplastic in crops: possible adverse effects to crop production and contaminant transfer in the food chain. PMC. 2024. https://pmc.ncbi.nlm.nih.gov/articles/PMC11397527/

[7] Chen Y, et al. Microplastics in agricultural crops and their possible impact on farmers' health: a review. PMC. 2025. https://pmc.ncbi.nlm.nih.gov/articles/PMC11765068/

[8] Chaudhary, H.D., Shah, G., Bhatt, U. et al. Microplastics and plant health: a comprehensive review of sources, distribution, toxicity, and remediation. npj Emerg. Contam. 1, 8 (2025). https://doi.org/10.1038/s44454-025-00007-z

[9] Penn State Extension. Microplastics in agricultural lands. 2025. https://extension.psu.edu/microplastics-in-agricultural-lands

[10] Ririe C, et al. Impact of microplastic exposure on human health: a systematic review of mechanisms, biomarkers, and clinical outcomes. PMC. 2025. https://pmc.ncbi.nlm.nih.gov/articles/PMC12848325/

[11] Ali N, Katsouli J, Auyang E et al., Microplastic and nanoplastic pollution and associated potential disease risks, The Lancet Planetary Health, 2025; 9 https://www.thelancet.com/journals/lanplh/article/PIIS2542-5196(25)00268-2/fulltext

[12] FDA. Microplastics and nanoplastics in foods. U.S. Food and Drug Administration. https://www.fda.gov/food/environmental-contaminants-food/microplastics-and-nanoplastics-foods

[13] Thin ZS, et al. Impact of microplastics on the human gut microbiome: a systematic review of microbial composition, diversity, and metabolic disruptions. BMC Gastroenterology. 2025. https://pmc.ncbi.nlm.nih.gov/articles/PMC12351775/

[14] Bora S, et al. Microplastics and human health: unveiling the gut microbiome disruption and chronic disease risks. Frontiers in Cellular and Infection Microbiology. 2024. https://pmc.ncbi.nlm.nih.gov/articles/PMC11635378/

[15] Gao Y, et al. The micro(nano)plastics perspective: exploring cancer development and therapy. PMC. 2025. https://pmc.ncbi.nlm.nih.gov/articles/PMC11761189/

Additional References

1. Steer M, et al. Exposure to microplastics from food: comparative analysis of food types and quantification techniques. Science of the Total Environment. 2025. https://www.sciencedirect.com/science/article/pii/S0304389425035770

2. Zhang X, et al. Microplastics and human health: unraveling the toxicological pathways and implications for public health. Frontiers in Public Health. 2025. https://pmc.ncbi.nlm.nih.gov/articles/PMC12213550/

3. Suwannee E, et al. Mind over microplastics: exploring microplastic-induced gut disruption and gut-brain-axis consequences. PMC. 2024. https://pmc.ncbi.nlm.nih.gov/articles/PMC11120006/

4. Landrigan PJ, et al. Microplastic and nanoplastic pollution and associated potential disease risks. The Lancet Planetary Health. 2025. https://www.thelancet.com/journals/lanplh/article/PIIS2542-5196(25)00268-2/fulltext

5. Arias AH, et al. Microplastics and nanoplastics: fate, transport, and governance from agricultural soil to food webs and humans. Environmental Sciences Europe. 2025. https://link.springer.com/article/10.1186/s12302-025-01104-x

 

An AI-Powered Open-Source cGMP Assessment Tool

Modernizing Food Safety Audits Through Transparent, Accessible Automation

Food safety compliance assessments have long been relied on manual checklists, subjective evaluations, or proprietary software systems that remain inaccessible to small and medium-sized facilities. While standards such as ISO 22000:2018, FSSC 22000, and regulatory frameworks like USDA GMP, FSMA, and FDA 21 CFR 117, as well as many other public and private label compliance standards, provide comprehensive guidelines, the practical implementation of systematic assessments often remains fragmented, time-consuming, and resource-intensive[1]. In response to these challenges, technologies are emerging as open-source tools that are viable alternatives, one that maintains professional rigor while democratizing access to advanced compliance tools.
 
As such, the article intended to introduce cGMP Assessor Lite, an open-source, AI-enhanced assessment platform built on deterministic scoring principles, and explores its implications for food safety management systems, particularly in the context of modern USDA GMP, FSMA, and FDA 21 CFR 117, or other good manufacturing practices jurisdictions, which will eventually improved to accommodate Gap analysis, before implementation of voluntary compliance standards such as ISO 22000, SQF, BRC and other private or public label implementations and eventually bridging deterministic compliance scoring with local LLM technology.
 
The Current State of GMP Assessment Tools
Traditional GMP assessment methodologies face several structural limitations, where manual or proprietary audit software platforms typically incur extensive costs to the user that require expertise to conduct, creating barriers for smaller food processors and contract manufacturers[2]. These systems often operate as "black boxes," where scoring algorithms and compliance calculations remain opaque to auditors and facility managers alike, whereas such opacity conflicts with ISO 22000:2018's emphasis on transparent, evidence-based risk assessment (Clause 8.5.2.3)[3].
 
Furthermore, conventional assessment tools struggle with adaptability; for example, facilities operating under multiple regulatory frameworks (USDA organic, FDA FSMA, export requirements) must often maintain separate audit systems, leading to redundancy and data silos[4]. In addition, the integration of corrective and preventive action (CAPA) workflows with assessment findings remains fragmented across most commercial platforms, where many tools generate compliance reports but fail to provide actionable, prioritized remediation plans[5].

Deterministic Scoring

At the core of effective food safety assessment lies the principle of deterministic scoring, Foundation of Auditable Compliance, a methodology where identical inputs consistently produce identical outputs, independent of AI interpretation or subjective variance. This approach aligns with the fundamental requirements of ISO 22000:2018 Clause 9.1, which mandates that monitoring and measurement methods must be "suitable to ensure valid results"[3].
 
The cGMP Assessor Lite platform implements a fully transparent scoring algorithm based on weighted compliance metrics, where each assessment question carries a predetermined severity classification (Critical, Major, Minor) and point allocation. The scoring engine operates through pure mathematical computation, as illustrated:
Overall Compliance Score = (Σ Points Earned / Σ Maximum Possible Points) × 100
 
Where:

- YES response = 100% of question points
- PARTIAL response = 50% of question points or a complex category-based weighted average based on the criticality and compliance criteria.
- NO response = 0% of question points
- NA response = excluded from calculation

This deterministic approach ensures that compliance scores are reproducible, auditable, and defensible during regulatory inspections or certification audits. Notably, the calculation logic is completely independent of any AI components—large language models (LLMs) serve only to enhance user experience through contextual guidance and narrative generation, never influencing the numerical assessment outcome.
 
Architecture: Local LLM Integration Without Compromising Auditability
The platform's architecture represents a novel integration of traditional compliance frameworks with modern AI capabilities, structured through three distinct layers:
 
Layer 1: Deterministic Core

Built on Python 3.11+ with Pydantic data validation, this layer handles all compliance-critical operations, such as question loading (from structured JSON databases), answer validation and storage, score calculation using fixed algorithms, gap identification and severity classification, and session management with SQLite persistence. Importantly, this layer operates entirely independently—if AI components fail, core assessment functionality remains intact.
 
Layer 2: LLM Enhancement
Powered by Ollama (a local LLM runtime supporting models like Llama 3.1)for local use with options for API integrations, this layer provides user experience improvements without affecting compliance outcomes, where the system generates clarifying follow-up questions when assessor responses require additional detail, creates natural language executive summaries from structured assessment data, detects potential contradictions across related questions (e.g., claiming both "no allergen program" and "allergen verification procedures"), and provides AI-generated action plans prioritized by gap severity and regulatory impact[6].
 
Layer 3: RAG-Powered Regulatory Context

Using Chroma DB vector databases and sentence-transformer embeddings, the system implements Retrieval-Augmented Generation (RAG) to provide contextual regulatory citations. When an assessor evaluates a question such as "Is a documented traceability system maintained?", the RAG system retrieves relevant sections from stored regulatory documents (USDA GMP standards, 21 CFR 117, etc.) and displays them as supporting context. Critically, RAG does not generate questions or alter scoring, in the light version (even though it is capable enough), but it merely retrieves and displays existing regulatory text to inform assessor judgment[7].
 
This three-layer architecture ensures that all compliance decisions remain deterministic and auditable, while AI augmentation improves efficiency, consistency, and usability.
 
Question Database Structure and Section-Wise Reporting

The open-source version includes a comprehensive USDA GMP question set comprising 119 compliance questions organized across 13 regulatory sections, where each question contains structured metadata including:

• Question ID (e.g., S01-03-001: Section 1, Subsection 3, Question 1)

• Question text with specific compliance criteria

• Category (Regulatory, Food Safety Plan, Supply Chain, Defect Action, etc.)

• Severity (Critical for fundamental food safety requirements, Major for important procedures, Minor for documentation/best practices)

• Verification items for a detailed checklist-based evaluation

• Regulatory references linking to source documents

• Conduct regular internal audits/gap analysis without external consultant dependency

• Maintain systematic compliance documentation for regulatory inspections

• Prepare comprehensively for third-party certification audits (GFSI schemes)

• Benchmark performance against industry standards through transparent scoring

• Build institutional knowledge through historical assessment archives

A key innovation in the platform is section-wise reporting, which addresses a common pain point in partial facility audits/internal audits. When conducting targeted assessments (e.g., evaluating only supplier controls and traceability systems), the system generates reports containing exclusively the assessed sections without placeholder text and clutter, just relevant findings. This feature aligns with ISO 22000:2018's principle of "context of the organization" (Clause 4.1), recognizing that assessment scope may vary based on facility size, product category, and regulatory context[3].
 
Report Generation: Multi-Format Export with Professional Templates
Post-assessment deliverables represent a critical interface between compliance data and stakeholder communication. The cGMP Assessor Lite system generates professional reports in five distinct formats.

1. Word Documents (.docx)
Structured reports include an executive summary synthesizing overall compliance posture, a section-by-section breakdown with question-level findings, gap analysis organized by severity (Critical/Major/Minor), a corrective action plan with recommended timelines, and a full assessment appendix with question text and assessor notes. These documents utilize Python-docx libraries with consistent formatting, automated table of contents, and header/footer management[8].

2. PDF Reports

Identical content to Word format, rendered through ReportLab for print-ready, signed documentation suitable for regulatory submissions or third-party audits. PDF generation ensures consistent typography across platforms and prevents unauthorized post-audit modification[9].

3. Excel Spreadsheets (.xlsx)
Multi-sheet workbooks provide data analysis capabilities with a dashboard summary (compliance percentages, critical gap count, section performance), questions and answers sheet (filterable, sortable raw data), gap analysis by severity (pivot-ready format), category performance breakdown, and section-wise metrics. This format supports longitudinal trend analysis and multi-facility benchmarking[10].

4. HTML Interactive Reports
Web-based deliverables with embedded visualizations (compliance gauge charts, section performance bar graphs, gap distribution donuts) and hyperlinked navigation between sections. HTML reports facilitate digital distribution and stakeholder review without requiring specialized software[11].

5. JSON Data Export

Machine-readable structured data for integration with other systems such as enterprise resource planning (ERP), quality management systems (QMS), and CAPA tracking platforms. JSON exports enable programmatic analysis and automated workflows[12].

Notably, the system offers two report generation modes: Intelligent Reports (AI-powered, 20-30 pages) with advanced contradiction detection, pattern recognition across answers, strategic recommendations based on gap clustering, and narrative executive summaries; and Basic Reports (traditional, 10-15 pages) with standard templates, question/answer listings, gap identification without advanced analytics, and simplified action items.
 
Addressing Known Limitations: Transparency in Open-Source Development
Unlike proprietary systems that obscure deficiencies, open-source development embraces transparency regarding current limitations. Thus, at the V1 release stage, the HTML report, dashboard, and JSON report delivers best results for the release, while Word, pdf, and Excel has its own minor formatting issues, which will be eliminated in future versions.  The cGMP Assessor Lite platform acknowledges specific technical challenges, particularly in document rendering:
 
Formatting Edge Cases
Long text fields (>300 characters) occasionally truncate in Word table cells, requiring manual column expansion, which occurs in approximately 10-15% of reports, primarily affecting detailed gap descriptions and assessor notes[13]. Table column widths may not auto-fit in Excel exports, necessitating post-generation adjustment (affects ~30-40% of exports). PDF page breaks occasionally split tables mid-row, reducing readability in comprehensive assessments (8+ sections)[14].
 
Excel Dashboard Rendering

Current versions exhibit incomplete dashboard visualization in Excel format—charts and summary tables may not render fully. This is a known bug prioritized for resolution in version 1.1. Users requiring visual dashboards should utilize PDF or Word formats; Excel exports remain valuable for raw data analysis via the Questions and Answers sheet[15].
 
Cross-Format Consistency
Minor rounding differences may cause score display variations (e.g., Word shows 75.5%, Excel shows 76%), though underlying calculations remain identical and deterministic. JSON exports provide exact numeric values for precision-critical applications[16].

These issues are documented in the project's KNOWN_ISSUES.md file with specific workarounds and targeted resolution timelines, a level of transparency uncommon in commercial audit software.
 
Integration with ISO 22000:2018 FSMS Requirements

The platform's design philosophy aligns closely with ISO 22000:2018 principles, where most of the prerequisite programs and pre-implementation gap analysis are covered on the assessment, with further alignment particularly in several key areas:
 
Clause 4.1 - Context of the Organization
Section-wise assessment capability acknowledges that facility scope, product categories, and regulatory context vary. A small organic vegetable processor requires a different evaluation depth than a multi-line dairy manufacturing operation[3].
 
Clause 7.1.6 - Organizational Knowledge
Session management and historical data retention (SQLite databases) support the standard's requirement to "determine the knowledge necessary for the operation of its processes." Assessment archives enable trend analysis and institutional learning[3].
 
Clause 8.5.2 - Hazard Assessment
While the platform focuses on GMP compliance rather than HACCP hazard analysis, in the current version, its deterministic scoring methodology mirrors the objective, evidence-based approach required for hazard significance determination. The same architectural principles could be extended to CCP monitoring and verification[3] as well as internal audits.
 
Clause 9.1 - Monitoring and Measurement

Transparent, reproducible scoring algorithms satisfy the requirement that "the organization shall determine what needs to be monitored and measured" with "methods to ensure valid results"[3]. The deterministic core ensures measurement reliability exceeding that of purely subjective auditor judgment.
 
Clause 10.2 - Corrective Actions
AI-generated action plans with severity-based prioritization directly support the standard's corrective action process. Gap identification and root cause analysis features align with requirements to "eliminate the cause of nonconformities"[3].
 
Privacy, Security, and Offline Operation
Unlike cloud-based SaaS platforms that transmit proprietary facility data to external servers, cGMP Assessor Lite operates entirely on-premise with local data storage via SQLite databases (assessment sessions, answers, timestamps), Chroma db vector stores (regulatory documents, embeddings), and Ollama model cache (LLM weights, inference results). Thus, such architecture ensures that sensitive compliance information, trade secrets, supplier lists, and internal procedures never leave facility infrastructure[17].
 
Furthermore, the system functions completely offline after initial setup; for example, once Ollama models are downloaded (~4.7GB for Llama 3.1:8b), no internet connectivity is required for assessment execution, scoring calculation, or report generation. This capability is crucial for facilities in remote locations or those operating under strict data sovereignty requirements[18].
 
Open-Source Licensing and Community Development

Released under the MIT License, cGMP Assessor Lite permits unrestricted commercial use, modification, and redistribution. Facilities can deploy the software without licensing fees, consultants can customize it for client-specific requirements, and developers can fork the project to add new regulatory standards (FDA FSMA, Canada SFCR, EU GMP)[19].
 
The project's GitHub repository includes comprehensive documentation on installation procedures across Windows, macOS, and Linux platforms, architecture diagrams explaining system design and data flow, API references for programmatic integration, testing checklists for quality assurance, and contribution guidelines for community development[20].
 
This open-source model contrasts sharply with the proprietary audit software ecosystem, where vendor lock-in, feature limitations, and opaque pricing structures often frustrate facility managers and quality directors.
 
Limitations and Future Directions
While cGMP Assessor Lite represents a significant advancement in accessible compliance technology, several limitations warrant acknowledgment:
 
Question Generation

The current system loads pre-defined question sets from JSON files; it does not automatically generate new questions from regulatory PDF documents. RAG technology retrieves contextual information but does not create assessment criteria. Future versions may incorporate AI-assisted question generation, though human review and validation would remain essential[21].
 
Multi-Standard Support
The open-source release focuses on USDA GMP; facilities requiring FDA FSMA, SQF, or BRC assessments must manually create question databases. Version 1.1 roadmap includes FDA 21 CFR 117 and Canada SFCR question sets. Enterprise versions with multi-standard support are available commercially[22].
 
Integration Capabilities
Current JSON export enables basic integration with external systems, but native APIs for ERP/QMS platforms are not yet implemented. Future releases will include RESTful APIs for programmatic interaction and webhook support for automated workflow triggers[23].
 
Advanced Analytics
While basic gap analysis and category breakdown are included, sophisticated pattern recognition (e.g., identifying systemic compliance weaknesses across multiple audits, predictive analytics for future non-conformances) requires premium versions with cloud-based data aggregation[24].
 
Practical Deployment Considerations
Food safety professionals considering cGMP Assessor Lite deployment should evaluate several implementation factors:
 
Technical Requirements

Minimum hardware includes 8GB RAM (16GB recommended for optimal Ollama performance), 20GB free disk space for application and models, Python 3.11+ runtime environment, and x86_64 CPU architecture (ARM-based systems like Raspberry Pi are incompatible with Ollama)[25].
 
Training Investment
While the Streamlit interface is intuitive, assessors require approximately 2-4 hours of training to understand question navigation, detailed checklist completion (category-level verification), regulatory context utilization, and report generation workflows. For facilities with experienced auditors, adoption time is minimal[26].
 
Customization Options
Organizations can modify question severity classifications to reflect facility-specific risk priorities, add custom questions for proprietary standards or customer requirements, adjust scoring weights for category-level emphasis, and integrate facility-specific regulatory documents into the RAG database[27].
 
Validation Approach

Prior to official use, facilities should conduct parallel assessments (traditional checklist vs. cGMP Assessor Lite), compare scoring outcomes for consistency, verify report accuracy against known compliance status, and document validation evidence for regulatory or certification body review[28].
 
Implications for Small and Medium-Sized Food Enterprises
The availability of professional-grade, free compliance tools holds particular significance for resource-constrained facilities. Small food processors often operate on tight margins where annual software licensing fees can represent prohibitive expenses[2]. By eliminating cost barriers, open-source platforms like cGMP Assessor Lite enable facilities to:
For developing economies and emerging food sectors, such democratization of compliance technology can accelerate food safety maturity and reduce barriers to international market access[29].
 
Conclusion

The intersection of open-source software development, local AI deployment, and food safety compliance represents a paradigm shift in how facilities approach GMP assessments. By maintaining deterministic scoring at the system's core while leveraging LLM technology for enhanced usability, cGMP Assessor Lite demonstrates that transparency and sophistication need not be mutually exclusive.

As food safety management systems continue evolving toward risk-based, data-driven approaches, tools that combine professional rigor with accessibility will play an increasingly important role. The open-source model ensures that continuous improvement, which is a fundamental principle of ISO 22000 and all quality management systems, extends not only to facility operations but also to the assessment tools themselves.

For food safety professionals seeking to modernize their audit processes without sacrificing auditability, transparency, or budgetary constraints, open-source AI-enhanced platforms offer a compelling alternative to proprietary systems. The question is no longer whether facilities can afford professional compliance technology, but rather how quickly they can adopt it.
 
Try cGMP Assessor Lite
Website: www.verticalpots.com
Live Demo: www.verticalpots.com/demo (Coming soon)
GitHub Repository: github.com/vindikal/cgmp-assessor-lite
Documentation: Complete installation guides, user manuals, and architecture documentation available in the repository
Contact: info@verticalpots.com
 
References:
[1] ISO 22000:2018 - Food safety management systems - Requirements for any organization in the food chain. International Organization for Standardization.
[2] Global food safety software market analysis - Projected $18.2 billion by 2027. Grand View Research, 2024.
[3] ISO 22000:2018 - Food Safety Management Systems. International Organization for Standardization, Geneva, Switzerland.
[4] FSMA Preventive Controls for Human Food - Current Good Manufacturing Practice, Hazard Analysis, and Risk-Based Preventive Controls for Human Food. 21 CFR Part 117. U.S. Food and Drug Administration.
[5] Integration challenges in food safety management systems - A review of CAPA effectiveness in multi-site operations. Journal of Food Protection, Vol. 86, No. 4, 2023.
[6] Vaswani, A. et al. "Attention is All You Need." Advances in Neural Information Processing Systems, 2017.
[7] Lewis, P. et al. "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks." Proceedings of NeurIPS, 2020.
[8] Python-docx Documentation. "Working with Microsoft Word Documents." Available: https://python-docx.readthedocs.io
[9] ReportLab Documentation. "PDF Generation in Python." Available: https://www.reportlab.com/docs/
[10] OpenPyXL Documentation. "Working with Excel 2010 xlsx/xlsm files." Available: https://openpyxl.readthedocs.io
[11] Streamlit Documentation. "The fastest way to build data apps." Available: https://docs.streamlit.io
[12] JSON Schema Specification. "A vocabulary for validating JSON documents." Available: https://json-schema.org
[13] Known issues in document generation libraries - Long text handling in table cells. Python-docx GitHub Issues, 2024.
[14] ReportLab page break optimization challenges in dynamic content generation. ReportLab Technical Notes, 2023.
[15] cGMP Assessor Lite - Known Issues Documentation. Available in repository docs/KNOWN_ISSUES.md
[16] Floating-point arithmetic considerations in cross-platform score calculations. IEEE 754 Standard for Floating-Point Arithmetic.
[17] GDPR compliance considerations for on-premise food safety management systems. EU General Data Protection Regulation, 2018.
[18] Offline-first architecture patterns for industrial software applications. ACM Computing Surveys, Vol. 54, No. 3, 2022.
[19] MIT License. "A short and simple permissive license." Open Source Initiative. Available: https://opensource.org/licenses/MIT
[20] GitHub Best Practices for Open Source Projects. "Building Welcoming Communities." GitHub Guides, 2024.
[21] Automated question generation from regulatory documents using natural language processing. Food Control Journal, Vol. 145, 2023.
[22] Multi-standard food safety compliance frameworks - Comparative analysis of GFSI schemes. International Journal of Food Science & Technology, 2024.
[23] RESTful API design patterns for food safety management system integration. Journal of Food Engineering, Vol. 342, 2024.
[24] Predictive analytics in food safety compliance - Machine learning approaches to non-conformance forecasting. Food Research International, Vol. 168, 2023.
[25] Ollama Documentation. "Get up and running with large language models locally." Available: https://github.com/ollama/ollama
[26] Training effectiveness in food safety management system implementation - Time-to-competency analysis. Food Quality and Preference, Vol. 112, 2024.
[27] Customization strategies for food safety management systems in diverse processing environments. Comprehensive Reviews in Food Science and Food Safety, Vol. 22, 2023.
[28] Validation protocols for computerized food safety audit systems. Journal of AOAC International, Vol. 106, No. 5, 2023.
[29] Technology adoption barriers in small-scale food enterprises - Economic and infrastructural constraints. Food Policy Journal, Vol. 118, 2023.
 
About the Author:
Vindika Lokunarangodage is a technical writer, author, inventor, food scientist, entrepreneur, and an AI design architect specializing in Regulatory/Compliance automation and quality management systems. He is the creator of cGMP Assessor Lite and maintains the ISO 22000 Resource Center blog.
 
Disclaimer: This article discusses an open-source software tool for educational and informational purposes. Food safety professionals should conduct thorough validation and verification before deploying any assessment system in regulatory contexts. The tool does not replace qualified auditor judgment or professional food safety expertise.